11687 lines
285 KiB
YAML
11687 lines
285 KiB
YAML
# GENERATED by 'coyote --generate-models'
|
|
# DO NOT hand-edit model data.
|
|
# Hand-owned behavior lives in quirks.yaml; this file is the embedded offline fallback.
|
|
- provider: openai
|
|
models:
|
|
- name: gpt-6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.5
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gpt-6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gpt-6-astra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gpt-5.6
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.4
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.2
|
|
output_price: 1.2
|
|
cache_read_price: 0.02
|
|
cache_write_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.4
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.5
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.5-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 30.0
|
|
output_price: 180.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: high
|
|
- name: gpt-5.4-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.75
|
|
output_price: 4.5
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: gpt-5.4-nano
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.2
|
|
output_price: 1.25
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: gpt-5.4
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.5
|
|
output_price: 15.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: gpt-5.4-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 30.0
|
|
output_price: 180.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.3-chat-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-5.3-codex
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.3-codex-spark
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 32000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: gpt-5.2
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: gpt-5.2-chat-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- name: gpt-5.2-pro
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 21.0
|
|
output_price: 168.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5.1
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: none
|
|
- name: gpt-5-pro
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 15.0
|
|
output_price: 120.0
|
|
max_output_tokens: 272000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- high
|
|
- name: gpt-5
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: gpt-5-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gpt-5-nano
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.05
|
|
output_price: 0.4
|
|
cache_read_price: 0.005
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: o3-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 20.0
|
|
output_price: 80.0
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: o3
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
cache_read_price: 0.5
|
|
patch:
|
|
body:
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: o4-mini
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.275
|
|
patch:
|
|
body:
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: gpt-4.1
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4.1-mini
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.4
|
|
output_price: 1.6
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4.1-nano
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: o1-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 150.0
|
|
output_price: 600.0
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: o3-mini
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.55
|
|
patch:
|
|
body:
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
max_output_tokens: 100000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: o1
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 60.0
|
|
cache_read_price: 7.5
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gpt-4o-2024-11-20
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4o-2024-08-06
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4o-mini
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4o
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4o-2024-05-13
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 5.0
|
|
output_price: 15.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 30.0
|
|
output_price: 60.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: gpt-4-turbo
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 10.0
|
|
output_price: 30.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-3.5-turbo
|
|
type: chat
|
|
max_input_tokens: 16385
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
cache_read_price: 0.0
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: text-embedding-3-large
|
|
type: embedding
|
|
input_price: 0.13
|
|
max_tokens_per_chunk: 8191
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: text-embedding-3-small
|
|
type: embedding
|
|
input_price: 0.02
|
|
max_tokens_per_chunk: 8191
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: o4-mini-high
|
|
type: chat
|
|
real_name: o4-mini
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
patch:
|
|
body:
|
|
reasoning_effort: high
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
reasoning:
|
|
effort: high
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: o3-high
|
|
type: chat
|
|
real_name: o3
|
|
max_input_tokens: 200000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
patch:
|
|
body:
|
|
reasoning_effort: high
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
reasoning:
|
|
effort: high
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: o3-mini-high
|
|
type: chat
|
|
real_name: o3-mini
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
patch:
|
|
body:
|
|
reasoning_effort: high
|
|
max_tokens: null
|
|
temperature: null
|
|
top_p: null
|
|
responses:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
reasoning:
|
|
effort: high
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
system_prompt_prefix: Formatting re-enabled
|
|
- name: chat-latest
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-5.1-chat-latest
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: none
|
|
- name: gpt-5-chat-latest
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- provider: gemini
|
|
models:
|
|
- name: gemini-3.8-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.7-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.6-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: gemini-flash-lite-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.1-flash-lite-image
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.25
|
|
output_price: 30.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- high
|
|
- name: gemini-omni-flash-preview
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.5
|
|
output_price: 17.5
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
- name: gemini-3.5-live-translate-preview
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
input_price: 3.5
|
|
output_price: 21.0
|
|
max_output_tokens: 32768
|
|
- name: gemini-3-pro-image
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 2.0
|
|
output_price: 120.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- name: gemini-3.1-flash-image
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 60.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- high
|
|
- name: gemini-3.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.5
|
|
output_price: 9.0
|
|
cache_read_price: 0.15
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: gemini-3.1-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: minimal
|
|
- name: deep-research-max-preview-04-2026
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deep-research-preview-04-2026
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemma-4-26b-a4b-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0675
|
|
output_price: 0.225
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemma-4-31b-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.09
|
|
output_price: 0.34
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-3.1-flash-live-preview
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.75
|
|
output_price: 4.5
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: lyria-3-clip-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
- name: lyria-3-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
- name: gemini-3.1-flash-lite-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.1-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: gemini-3.1-pro-preview-customtools
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3-flash-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: gemini-2.5-computer-use-preview-10-2025
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-2.5-flash-image
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.3
|
|
output_price: 30.0
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
- name: gemini-2.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-2.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-2.5-pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: text-embedding-004
|
|
type: embedding
|
|
input_price: 0.0
|
|
max_tokens_per_chunk: 2048
|
|
default_chunk_size: 1500
|
|
max_batch_size: 100
|
|
- name: gemini-3-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: gemma-3-27b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 8192
|
|
- provider: claude
|
|
models:
|
|
- name: claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-sonnet-4-6:thinking
|
|
type: chat
|
|
real_name: claude-sonnet-4-6
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-6:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-6
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-5
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-opus-4-5-20251101
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-opus-4-5-20251101:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-5-20251101
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-haiku-4-5
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-haiku-4-5-20251001
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-haiku-4-5-20251001:thinking
|
|
type: chat
|
|
real_name: claude-haiku-4-5-20251001
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-sonnet-4-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-sonnet-4-5-20250929
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-sonnet-4-5-20250929:thinking
|
|
type: chat
|
|
real_name: claude-sonnet-4-5-20250929
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-1-20250805
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-1-20250805:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-1-20250805
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-20250514
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-20250514:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-20250514
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- provider: mistral
|
|
models:
|
|
- name: zai-glm-5-3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.14
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: zai-glm-5-2
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.14
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- max
|
|
- name: mistral-medium-2604
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: mistral-medium-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: mistral-small-2603
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 256000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: mistral-small-latest
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 256000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: devstral-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: devstral-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: labs-devstral-small-2512
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 256000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: devstral-medium-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: mistral-medium-2508
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: devstral-medium-2507
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: devstral-small-2507
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: mistral-small-2506
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: devstral-small-2505
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: mistral-medium-2505
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: magistral-medium-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 5.0
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: magistral-small
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: mistral-large-2411
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: mistral-large-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral-large-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: pixtral-large-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ministral-3b-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.04
|
|
output_price: 0.04
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: ministral-8b-latest
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.1
|
|
output_price: 0.1
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: pixtral-12b
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.15
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral-nemo
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.15
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: open-mistral-nemo
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.15
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: codestral-latest
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: open-mixtral-8x22b
|
|
type: chat
|
|
max_input_tokens: 64000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: mistral-embed
|
|
type: embedding
|
|
max_input_tokens: 8092
|
|
input_price: 0.1
|
|
output_price: 0.0
|
|
max_output_tokens: 3072
|
|
max_tokens_per_chunk: 8092
|
|
default_chunk_size: 2000
|
|
- name: open-mixtral-8x7b
|
|
type: chat
|
|
max_input_tokens: 32000
|
|
input_price: 0.7
|
|
output_price: 0.7
|
|
max_output_tokens: 32000
|
|
supports_function_calling: true
|
|
- name: open-mistral-7b
|
|
type: chat
|
|
max_input_tokens: 8000
|
|
input_price: 0.25
|
|
output_price: 0.25
|
|
max_output_tokens: 8000
|
|
supports_function_calling: true
|
|
- name: magistral-small-latest
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
- name: devstral-small-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
supports_function_calling: true
|
|
- name: ministral-14b-latest
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 0.2
|
|
supports_function_calling: true
|
|
- provider: ai21
|
|
models:
|
|
- name: jamba-large
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
supports_function_calling: true
|
|
- name: jamba-mini
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.2
|
|
output_price: 0.4
|
|
supports_function_calling: true
|
|
- provider: cohere
|
|
models:
|
|
- name: north-mini-code-1-0
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: command-a-plus-05-2026
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: command-a-translate-08-2025
|
|
type: chat
|
|
max_input_tokens: 8000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8000
|
|
supports_function_calling: true
|
|
- name: command-a-reasoning-08-2025
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 32000
|
|
supports_function_calling: true
|
|
- name: command-a-vision-07-2025
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8000
|
|
supports_vision: true
|
|
- name: command-a-03-2025
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8000
|
|
supports_function_calling: true
|
|
- name: c4ai-aya-vision-32b
|
|
type: chat
|
|
max_input_tokens: 16000
|
|
max_output_tokens: 4000
|
|
supports_vision: true
|
|
- name: c4ai-aya-vision-8b
|
|
type: chat
|
|
max_input_tokens: 16000
|
|
max_output_tokens: 4000
|
|
supports_vision: true
|
|
- name: command-r7b-arabic-02-2025
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.0375
|
|
output_price: 0.15
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: command-r7b-12-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.0375
|
|
output_price: 0.15
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: c4ai-aya-expanse-32b
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
max_output_tokens: 4000
|
|
- name: c4ai-aya-expanse-8b
|
|
type: chat
|
|
max_input_tokens: 8000
|
|
max_output_tokens: 4000
|
|
- name: command-r-08-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: command-r-plus-08-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: embed-v4.0
|
|
type: embedding
|
|
input_price: 0.12
|
|
max_tokens_per_chunk: 2048
|
|
default_chunk_size: 2000
|
|
max_batch_size: 96
|
|
- name: embed-english-v3.0
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- name: embed-multilingual-v3.0
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- name: rerank-v3.5
|
|
type: reranker
|
|
max_input_tokens: 4096
|
|
- name: rerank-english-v3.0
|
|
type: reranker
|
|
max_input_tokens: 4096
|
|
- name: rerank-multilingual-v3.0
|
|
type: reranker
|
|
max_input_tokens: 4096
|
|
- provider: xai
|
|
oauth:
|
|
client_id: b1a00492-073a-47ea-816f-4c329264a828
|
|
token_url: https://auth.x.ai/oauth2/token
|
|
flow: pkce
|
|
client_secret: null
|
|
authorize_url: https://auth.x.ai/oauth2/authorize
|
|
redirect_uri: null
|
|
redirect_port: 56121
|
|
device_authorization_url: null
|
|
scopes:
|
|
- openid
|
|
- profile
|
|
- email
|
|
- offline_access
|
|
- grok-cli:access
|
|
- api:access
|
|
token_request_format: form_url_encoded
|
|
resource: null
|
|
extra_authorize_params:
|
|
plan: generic
|
|
referrer: coyote
|
|
extra_token_params: {}
|
|
extra_token_headers: {}
|
|
extra_request_headers: {}
|
|
echo_pkce_in_token_exchange: true
|
|
use_pkce_in_device_flow: false
|
|
include_state_in_token_exchange: true
|
|
models:
|
|
- name: grok-4.7
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: grok-4.6
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: grok-4.5
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: grok-4.3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: grok-build-0.1
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 1.0
|
|
output_price: 2.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 256000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: grok-4.20-0309-non-reasoning
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: grok-4.20-0309-reasoning
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: grok-4.20-multi-agent-0309
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: grok-4.20
|
|
type: chat
|
|
real_name: grok-4.20-multi-agent-0309
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
supports_function_calling: true
|
|
- name: grok-4.20-reasoning
|
|
type: chat
|
|
real_name: grok-4.20-0309-reasoning
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
supports_function_calling: true
|
|
- name: grok-4.20-non-reasoning
|
|
type: chat
|
|
real_name: grok-4.20-0309-non-reasoning
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
supports_function_calling: true
|
|
- name: grok-4-1-fast-non-reasoning
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.2
|
|
output_price: 0.5
|
|
supports_function_calling: true
|
|
- name: grok-4-1-fast-reasoning
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.2
|
|
output_price: 0.5
|
|
supports_function_calling: true
|
|
- name: grok-code-fast-1
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.2
|
|
output_price: 1.5
|
|
supports_function_calling: true
|
|
- name: grok-3
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
supports_function_calling: true
|
|
- name: grok-3-mini
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.3
|
|
output_price: 0.5
|
|
supports_function_calling: true
|
|
- provider: perplexity
|
|
models:
|
|
- name: sonar-deep-research
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
max_output_tokens: 32768
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: sonar
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.0
|
|
output_price: 1.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
- name: sonar-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: sonar-reasoning-pro
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: sonar-reasoning
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
- provider: groq
|
|
models:
|
|
- name: qwen/qwen3.8-27b
|
|
type: chat
|
|
max_input_tokens: 131042
|
|
input_price: 0.8
|
|
output_price: 4.0
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- default
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: qwen/qwen3.6-27b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.6
|
|
output_price: 3.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- default
|
|
- name: canopylabs/orpheus-v1-english
|
|
type: chat
|
|
max_input_tokens: 4000
|
|
max_output_tokens: 50000
|
|
- name: canopylabs/orpheus-arabic-saudi
|
|
type: chat
|
|
max_input_tokens: 4000
|
|
max_output_tokens: 50000
|
|
- name: openai/gpt-oss-safeguard-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: groq/compound
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
max_output_tokens: 8192
|
|
- name: groq/compound-mini
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
max_output_tokens: 8192
|
|
- name: openai/gpt-oss-120b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai/gpt-oss-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: meta-llama/llama-prompt-guard-2-22m
|
|
type: chat
|
|
max_input_tokens: 512
|
|
input_price: 0.03
|
|
output_price: 0.03
|
|
max_output_tokens: 512
|
|
- name: meta-llama/llama-prompt-guard-2-86m
|
|
type: chat
|
|
max_input_tokens: 512
|
|
input_price: 0.04
|
|
output_price: 0.04
|
|
max_output_tokens: 512
|
|
- name: allam-2-7b
|
|
type: chat
|
|
max_input_tokens: 4096
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 4096
|
|
- name: llama-3.3-70b-versatile
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.59
|
|
output_price: 0.79
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: llama-3.1-8b-instant
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.08
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-4-maverick-17b-128e-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-4-scout-17b-16e-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2-instruct-0905
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-32b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
- provider: vertexai
|
|
models:
|
|
- name: claude-opus-5-5@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gemini-3.8-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-fable-5-1@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: gemini-3.7-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.5
|
|
output_price: 9.0
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: xai/grok-4.6
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-5@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gemini-3.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.6-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-flash-lite-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-sonnet-5@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: zai-org/glm-5.2-maas
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.14
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: claude-fable-5@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-8@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: gemini-3-pro-image
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 2.0
|
|
output_price: 120.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-3.1-flash-image
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 60.0
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- high
|
|
- name: gemini-3.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.5
|
|
output_price: 9.0
|
|
cache_read_price: 0.15
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: gemini-3.1-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: minimal
|
|
- name: xai/grok-4.3
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-7@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: xai/grok-4.20-non-reasoning
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xai/grok-4.20-reasoning
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-3.1-flash-lite-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-3.1-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: gemini-3.1-pro-preview-customtools
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-sonnet-4-6@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: zai-org/glm-5-maas
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 3.2
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-6@default
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: zai-org/glm-4.7-maas
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/deepseek-v3.2-maas
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.56
|
|
output_price: 1.68
|
|
cache_read_price: 0.056
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: gemini-3-flash-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: xai/grok-4.1-fast-non-reasoning
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.2
|
|
output_price: 0.5
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xai/grok-4.1-fast-reasoning
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.2
|
|
output_price: 0.5
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 30000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2-thinking-maas
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 2.5
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-5@20251101
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: claude-opus-4-5@20251101:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-5@20251101
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: claude-haiku-4-5@20251001
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-haiku-4-5@20251001:thinking
|
|
type: chat
|
|
real_name: claude-haiku-4-5@20251001
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: claude-sonnet-4-5@20250929
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-sonnet-4-5@20250929:thinking
|
|
type: chat
|
|
real_name: claude-sonnet-4-5@20250929
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: deepseek-ai/deepseek-v3.1-maas
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.6
|
|
output_price: 1.7
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: gemini-2.5-flash-image
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.3
|
|
output_price: 30.0
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
- name: qwen/qwen3-235b-a22b-instruct-2507-maas
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.22
|
|
output_price: 0.88
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-1@20250805
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
cache_read_price: 1.5
|
|
cache_write_price: 18.75
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-120b-maas
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.09
|
|
output_price: 0.36
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai/gpt-oss-20b-maas
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.07
|
|
output_price: 0.25
|
|
cache_read_price: 0.007
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: gemini-2.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: gemini-2.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gemini-2.5-pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4@20250514
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
cache_read_price: 1.5
|
|
cache_write_price: 18.75
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-sonnet-4@20250514
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/llama-3.3-70b-instruct-maas
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: meta/llama-4-maverick-17b-128e-instruct-maas
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.35
|
|
output_price: 1.15
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: text-embedding-005
|
|
type: embedding
|
|
max_input_tokens: 20000
|
|
input_price: 0.025
|
|
max_tokens_per_chunk: 2048
|
|
default_chunk_size: 1500
|
|
max_batch_size: 5
|
|
- name: text-multilingual-embedding-002
|
|
type: embedding
|
|
max_input_tokens: 20000
|
|
input_price: 0.2
|
|
max_tokens_per_chunk: 2048
|
|
default_chunk_size: 1500
|
|
max_batch_size: 5
|
|
- name: gemini-3-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-opus-4-6
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: claude-opus-4-6:thinking
|
|
type: chat
|
|
real_name: claude-opus-4-6
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: claude-sonnet-4-6:thinking
|
|
type: chat
|
|
real_name: claude-sonnet-4-6
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
patch:
|
|
body:
|
|
temperature: null
|
|
top_p: null
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
default_reasoning_effort: high
|
|
- name: claude-3-5-haiku@20241022
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.8
|
|
output_price: 4.0
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral-small-2503
|
|
type: chat
|
|
max_input_tokens: 32000
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
supports_function_calling: true
|
|
- name: codestral-2501
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
supports_function_calling: true
|
|
- provider: bedrock
|
|
models:
|
|
- name: anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: au.anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.openai.gpt-6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.5
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.openai.gpt-6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: jp.anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.11
|
|
output_price: 0.55
|
|
cache_read_price: 0.011
|
|
cache_write_price: 0.1375
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-opus-5-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.11
|
|
output_price: 0.55
|
|
cache_read_price: 0.011
|
|
cache_write_price: 0.1375
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.openai.gpt-6-astra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-6-astra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 11.0
|
|
output_price: 55.0
|
|
cache_read_price: 1.1
|
|
cache_write_price: 13.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-6-astra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 11.0
|
|
output_price: 55.0
|
|
cache_read_price: 1.1
|
|
cache_write_price: 13.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: anthropic.claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 11.0
|
|
output_price: 55.0
|
|
cache_read_price: 0.275
|
|
cache_write_price: 13.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: global.xai.grok-4.6
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: us.xai.grok-4.6
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.2
|
|
output_price: 6.6
|
|
cache_read_price: 0.55
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: xai.grok-4.6
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.2
|
|
output_price: 6.6
|
|
cache_read_price: 0.55
|
|
max_output_tokens: 500000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: au.anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: jp.anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: global.moonshotai.kimi-k3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.moonshotai.kimi-k3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: global.openai.gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.2
|
|
output_price: 1.2
|
|
cache_read_price: 0.02
|
|
cache_write_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.openai.gpt-5.6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.4
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.openai.gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: in.openai.gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.22
|
|
output_price: 1.32
|
|
cache_read_price: 0.022
|
|
cache_write_price: 0.275
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: in.openai.gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.2
|
|
output_price: 13.2
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.22
|
|
output_price: 1.32
|
|
cache_read_price: 0.022
|
|
cache_write_price: 0.275
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-5.6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.44
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: openai.gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.2
|
|
output_price: 13.2
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.22
|
|
output_price: 1.32
|
|
cache_read_price: 0.022
|
|
cache_write_price: 0.275
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-5.6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 4.4
|
|
output_price: 22.0
|
|
cache_read_price: 0.44
|
|
cache_write_price: 5.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.openai.gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.2
|
|
output_price: 13.2
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: au.anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: jp.anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.2
|
|
output_price: 11.0
|
|
cache_read_price: 0.22
|
|
cache_write_price: 2.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic.claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 11.0
|
|
output_price: 55.0
|
|
cache_read_price: 1.1
|
|
cache_write_price: 13.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 11.0
|
|
output_price: 55.0
|
|
cache_read_price: 1.1
|
|
cache_write_price: 13.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: au.anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: jp.anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: openai.gpt-5.5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 33.0
|
|
cache_read_price: 0.55
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: xai.grok-4.3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: au.anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: eu.anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: global.anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: jp.anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: us.anthropic.claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: google.gemma-4-26b-a4b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.13
|
|
output_price: 0.4
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: google.gemma-4-31b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.14
|
|
output_price: 0.4
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: google.gemma-4-e2b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.04
|
|
output_price: 0.08
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: nvidia.nemotron-super-3-120b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 0.65
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: openai.gpt-5.4
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.75
|
|
output_price: 16.5
|
|
cache_read_price: 0.275
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: au.anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: eu.anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: global.anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: jp.anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: us.anthropic.claude-sonnet-4-6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: us.anthropic.claude-sonnet-4-6:thinking
|
|
type: chat
|
|
real_name: us.anthropic.claude-sonnet-4-6
|
|
max_input_tokens: 1000000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
patch:
|
|
body:
|
|
inferenceConfig:
|
|
temperature: null
|
|
topP: null
|
|
additionalModelRequestFields:
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
default_reasoning_effort: high
|
|
- name: minimax.minimax-m2.5
|
|
type: chat
|
|
max_input_tokens: 196608
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: zai.glm-5
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 1.0
|
|
output_price: 3.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: anthropic.claude-opus-4-6-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: au.anthropic.claude-opus-4-6-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: eu.anthropic.claude-opus-4-6-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: global.anthropic.claude-opus-4-6-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
- name: us.anthropic.claude-opus-4-6-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: us.anthropic.claude-opus-4-6-v1:thinking
|
|
type: chat
|
|
real_name: us.anthropic.claude-opus-4-6-v1
|
|
max_input_tokens: 1000000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
patch:
|
|
body:
|
|
inferenceConfig:
|
|
temperature: null
|
|
topP: null
|
|
additionalModelRequestFields:
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
default_reasoning_effort: high
|
|
- name: qwen.qwen3-coder-next
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 1.2
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: moonshotai.kimi-k2.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 3.0
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: zai.glm-4.7-flash
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.07
|
|
output_price: 0.4
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: minimax.minimax-m2.1
|
|
type: chat
|
|
max_input_tokens: 196608
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: zai.glm-4.7
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: nvidia.nemotron-nano-3-30b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.06
|
|
output_price: 0.24
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: mistral.devstral-2-123b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: amazon.nova-2-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.33
|
|
output_price: 2.75
|
|
cache_read_price: 0.0825
|
|
cache_write_price: 0.33
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: eu.amazon.nova-2-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.374
|
|
output_price: 3.157
|
|
cache_read_price: 0.0935
|
|
cache_write_price: 0.374
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: global.amazon.nova-2-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.3
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: jp.amazon.nova-2-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.396
|
|
output_price: 3.311
|
|
cache_read_price: 0.099
|
|
cache_write_price: 0.396
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: mistral.ministral-3-14b-instruct
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.2
|
|
output_price: 0.2
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral.ministral-3-3b-instruct
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.1
|
|
output_price: 0.1
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral.ministral-3-8b-instruct
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.15
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral.mistral-large-3-675b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.amazon.nova-2-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.33
|
|
output_price: 2.75
|
|
cache_read_price: 0.0825
|
|
cache_write_price: 0.33
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: deepseek.v3.2
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.62
|
|
output_price: 1.85
|
|
max_output_tokens: 81920
|
|
supports_function_calling: true
|
|
- name: moonshot.kimi-k2-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 2.5
|
|
max_output_tokens: 16000
|
|
supports_function_calling: true
|
|
- name: anthropic.claude-opus-4-5-20251101-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: eu.anthropic.claude-opus-4-5-20251101-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: global.anthropic.claude-opus-4-5-20251101-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: us.anthropic.claude-opus-4-5-20251101-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: us.anthropic.claude-opus-4-5-20251101-v1:0:thinking
|
|
type: chat
|
|
real_name: us.anthropic.claude-opus-4-5-20251101-v1:0
|
|
max_input_tokens: 200000
|
|
input_price: 5.5
|
|
output_price: 27.5
|
|
cache_read_price: 0.55
|
|
cache_write_price: 6.875
|
|
patch:
|
|
body:
|
|
inferenceConfig:
|
|
temperature: null
|
|
topP: null
|
|
additionalModelRequestFields:
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: openai.gpt-oss-safeguard-120b
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai.gpt-oss-safeguard-20b
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.07
|
|
output_price: 0.2
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: nvidia.nemotron-nano-12b-v2
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.2
|
|
output_price: 0.6
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: minimax.minimax-m2
|
|
type: chat
|
|
max_input_tokens: 204608
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: au.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 5.5
|
|
cache_read_price: 0.11
|
|
cache_write_price: 1.375
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: eu.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 5.5
|
|
cache_read_price: 0.11
|
|
cache_write_price: 1.375
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: global.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: jp.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 5.5
|
|
cache_read_price: 0.11
|
|
cache_write_price: 1.375
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 5.5
|
|
cache_read_price: 0.11
|
|
cache_write_price: 1.375
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.anthropic.claude-haiku-4-5-20251001-v1:0:thinking
|
|
type: chat
|
|
real_name: us.anthropic.claude-haiku-4-5-20251001-v1:0
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 5.5
|
|
cache_read_price: 0.11
|
|
cache_write_price: 1.375
|
|
patch:
|
|
body:
|
|
inferenceConfig:
|
|
temperature: null
|
|
topP: null
|
|
additionalModelRequestFields:
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: au.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: eu.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: global.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: jp.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.anthropic.claude-sonnet-4-5-20250929-v1:0:thinking
|
|
type: chat
|
|
real_name: us.anthropic.claude-sonnet-4-5-20250929-v1:0
|
|
max_input_tokens: 200000
|
|
input_price: 3.3
|
|
output_price: 16.5
|
|
cache_read_price: 0.33
|
|
cache_write_price: 4.125
|
|
patch:
|
|
body:
|
|
inferenceConfig:
|
|
temperature: null
|
|
topP: null
|
|
additionalModelRequestFields:
|
|
thinking:
|
|
type: enabled
|
|
budget_tokens: 16000
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: qwen.qwen3-vl-235b-a22b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.53
|
|
output_price: 2.66
|
|
max_output_tokens: 262000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral.magistral-small-2509
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 40000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen.qwen3-next-80b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 1.2
|
|
max_output_tokens: 262000
|
|
supports_function_calling: true
|
|
- name: deepseek.v3-v1:0
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.58
|
|
output_price: 1.68
|
|
max_output_tokens: 81920
|
|
supports_function_calling: true
|
|
- name: nvidia.nemotron-nano-9b-v2
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.06
|
|
output_price: 0.23
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: anthropic.claude-opus-4-1-20250805-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
cache_read_price: 1.5
|
|
cache_write_price: 18.75
|
|
max_output_tokens: 32000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai.gpt-oss-120b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai.gpt-oss-120b-1:0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai.gpt-oss-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.07
|
|
output_price: 0.3
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai.gpt-oss-20b-1:0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.07
|
|
output_price: 0.3
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: us-gov.openai.gpt-oss-120b-1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.18
|
|
output_price: 0.72
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: us-gov.openai.gpt-oss-20b-1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.084
|
|
output_price: 0.36
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: us.anthropic.claude-opus-4-1-20250805-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
cache_read_price: 1.5
|
|
cache_write_price: 18.75
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen.qwen3-coder-30b-a3b-v1:0
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: qwen.qwen3-coder-480b-a35b-v1:0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.45
|
|
output_price: 1.8
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen.qwen3-235b-a22b-2507-v1:0
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.22
|
|
output_price: 0.88
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: mistral.voxtral-mini-3b-2507
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.04
|
|
output_price: 0.04
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: mistral.voxtral-small-24b-2507
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: apac.anthropic.claude-sonnet-4-20250514-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: eu.anthropic.claude-sonnet-4-20250514-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: global.anthropic.claude-sonnet-4-20250514-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.anthropic.claude-sonnet-4-20250514-v1:0
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.amazon.nova-premier-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.625
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 5120
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.writer.palmyra-x5-v1:0
|
|
type: chat
|
|
max_input_tokens: 1040000
|
|
input_price: 0.6
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: writer.palmyra-x5-v1:0
|
|
type: chat
|
|
max_input_tokens: 1040000
|
|
input_price: 0.6
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: eu.mistral.pixtral-large-2502-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistral.pixtral-large-2502-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.mistral.pixtral-large-2502-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta.llama4-maverick-17b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.24
|
|
output_price: 0.97
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta.llama4-scout-17b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 10000000
|
|
input_price: 0.17
|
|
output_price: 0.66
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.meta.llama4-maverick-17b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.24
|
|
output_price: 0.97
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.meta.llama4-scout-17b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 10000000
|
|
input_price: 0.17
|
|
output_price: 0.66
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen.qwen3-32b-v1:0
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: google.gemma-3-12b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.09
|
|
output_price: 0.29
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: google.gemma-3-27b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.23
|
|
output_price: 0.38
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: google.gemma-3-4b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.04
|
|
output_price: 0.08
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
- name: deepseek.r1-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.35
|
|
output_price: 5.4
|
|
max_output_tokens: 32768
|
|
- name: us.deepseek.r1-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.35
|
|
output_price: 5.4
|
|
max_output_tokens: 32768
|
|
- name: meta.llama3-3-70b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: us.meta.llama3-3-70b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 8192
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: amazon.nova-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.06
|
|
output_price: 0.24
|
|
cache_read_price: 0.015
|
|
cache_write_price: 0.06
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: amazon.nova-micro-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.035
|
|
output_price: 0.14
|
|
cache_read_price: 0.00875
|
|
cache_write_price: 0.035
|
|
max_output_tokens: 10000
|
|
supports_function_calling: true
|
|
- name: amazon.nova-pro-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.8
|
|
output_price: 3.2
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.8
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: apac.amazon.nova-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.063
|
|
output_price: 0.252
|
|
cache_read_price: 0.01575
|
|
cache_write_price: 0.063
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: apac.amazon.nova-micro-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.037
|
|
output_price: 0.148
|
|
cache_read_price: 0.00925
|
|
cache_write_price: 0.037
|
|
max_output_tokens: 10000
|
|
supports_function_calling: true
|
|
- name: apac.amazon.nova-pro-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.84
|
|
output_price: 3.36
|
|
cache_read_price: 0.21
|
|
cache_write_price: 0.84
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ca.amazon.nova-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.064
|
|
output_price: 0.256
|
|
cache_read_price: 0.016
|
|
cache_write_price: 0.064
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: eu.amazon.nova-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.069
|
|
output_price: 0.276
|
|
cache_read_price: 0.01725
|
|
cache_write_price: 0.069
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: eu.amazon.nova-micro-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.04
|
|
output_price: 0.16
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.04
|
|
max_output_tokens: 10000
|
|
supports_function_calling: true
|
|
- name: eu.amazon.nova-pro-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.92
|
|
output_price: 3.68
|
|
cache_read_price: 0.23
|
|
cache_write_price: 0.92
|
|
max_output_tokens: 10000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.amazon.nova-lite-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.06
|
|
output_price: 0.24
|
|
cache_read_price: 0.015
|
|
cache_write_price: 0.06
|
|
max_output_tokens: 5120
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.amazon.nova-micro-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.035
|
|
output_price: 0.14
|
|
cache_read_price: 0.00875
|
|
cache_write_price: 0.035
|
|
max_output_tokens: 5120
|
|
supports_function_calling: true
|
|
- name: us.amazon.nova-pro-v1:0
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.8
|
|
output_price: 3.2
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.8
|
|
max_output_tokens: 5120
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: us.writer.palmyra-x4-v1:0
|
|
type: chat
|
|
max_input_tokens: 122880
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: writer.palmyra-x4-v1:0
|
|
type: chat
|
|
max_input_tokens: 122880
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: meta.llama3-1-70b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: meta.llama3-1-8b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.22
|
|
output_price: 0.22
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: us.meta.llama3-1-70b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 4096
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: us.meta.llama3-1-8b-instruct-v1:0
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.22
|
|
output_price: 0.22
|
|
max_output_tokens: 4096
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: cohere.embed-english-v3
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- name: cohere.embed-multilingual-v3
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- provider: cloudflare
|
|
models:
|
|
- name: '@cf/zai-org/glm-5.3-flash'
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.15
|
|
output_price: 0.5
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 1048576
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: '@cf/qwen/qwen3.8-27b'
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.45
|
|
output_price: 3.2
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 262144
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- xhigh
|
|
- name: '@cf/zai-org/glm-5.3'
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.26
|
|
max_output_tokens: 1048576
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: '@cf/deepseek-ai/deepseek-v4-pro-0813'
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.32
|
|
output_price: 3.96
|
|
cache_read_price: 0.044
|
|
max_output_tokens: 1048576
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- high
|
|
- max
|
|
- name: '@cf/deepseek-ai/deepseek-v4-flash-0731'
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.44
|
|
output_price: 1.32
|
|
cache_read_price: 0.014
|
|
max_output_tokens: 1048576
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- high
|
|
- max
|
|
- name: '@cf/zai-org/glm-5.2'
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.26
|
|
max_output_tokens: 256000
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- max
|
|
- name: '@cf/moonshotai/kimi-k2.7-code'
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.19
|
|
max_output_tokens: 262144
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: '@cf/moonshotai/kimi-k2.6'
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.16
|
|
max_output_tokens: 256000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: '@cf/google/gemma-4-26b-a4b-it'
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 16384
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- high
|
|
- name: '@cf/nvidia/nemotron-3-120b-a12b'
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 256000
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: '@cf/zai-org/glm-4.7-flash'
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0605
|
|
output_price: 0.4
|
|
max_output_tokens: 131072
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: '@cf/ibm-granite/granite-4.0-h-micro'
|
|
type: chat
|
|
max_input_tokens: 131000
|
|
input_price: 0.017
|
|
output_price: 0.112
|
|
max_output_tokens: 131000
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: '@cf/aisingapore/gemma-sea-lion-v4-27b-it'
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.351
|
|
output_price: 0.555
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
- name: '@cf/openai/gpt-oss-120b'
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.35
|
|
output_price: 0.75
|
|
max_output_tokens: 16384
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: '@cf/openai/gpt-oss-20b'
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.2
|
|
output_price: 0.3
|
|
max_output_tokens: 16384
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: '@cf/qwen/qwen3-30b-a3b-fp8'
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.0509
|
|
output_price: 0.335
|
|
max_output_tokens: 32768
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: '@cf/meta/llama-4-scout-17b-16e-instruct'
|
|
type: chat
|
|
max_input_tokens: 131000
|
|
input_price: 0.27
|
|
output_price: 0.85
|
|
max_output_tokens: 16384
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: '@cf/mistralai/mistral-small-3.1-24b-instruct'
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.351
|
|
output_price: 0.555
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: '@cf/qwen/qwq-32b'
|
|
type: chat
|
|
max_input_tokens: 24000
|
|
input_price: 0.66
|
|
output_price: 1.0
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
- name: '@cf/deepseek-ai/deepseek-r1-distill-qwen-32b'
|
|
type: chat
|
|
max_input_tokens: 80000
|
|
input_price: 0.497
|
|
output_price: 4.881
|
|
max_output_tokens: 80000
|
|
require_max_tokens: true
|
|
- name: '@cf/meta/llama-3.3-70b-instruct-fp8-fast'
|
|
type: chat
|
|
max_input_tokens: 24000
|
|
input_price: 0.293
|
|
output_price: 2.253
|
|
max_output_tokens: 24000
|
|
require_max_tokens: true
|
|
supports_function_calling: true
|
|
- name: '@cf/qwen/qwen2.5-coder-32b-instruct'
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.66
|
|
output_price: 1.0
|
|
max_output_tokens: 32768
|
|
require_max_tokens: true
|
|
- name: '@cf/meta/llama-3.2-11b-vision-instruct'
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.0485
|
|
output_price: 0.676
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
- name: '@cf/meta/llama-3.2-1b-instruct'
|
|
type: chat
|
|
max_input_tokens: 60000
|
|
input_price: 0.027
|
|
output_price: 0.201
|
|
max_output_tokens: 60000
|
|
require_max_tokens: true
|
|
- name: '@cf/meta/llama-3.2-3b-instruct'
|
|
type: chat
|
|
max_input_tokens: 80000
|
|
input_price: 0.0509
|
|
output_price: 0.335
|
|
max_output_tokens: 80000
|
|
require_max_tokens: true
|
|
- name: '@cf/meta/llama-3.1-8b-instruct-fp8'
|
|
type: chat
|
|
max_input_tokens: 32000
|
|
input_price: 0.152
|
|
output_price: 0.287
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
- name: '@cf/meta/llama-guard-3-8b'
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.484
|
|
output_price: 0.03
|
|
max_output_tokens: 131072
|
|
require_max_tokens: true
|
|
- name: '@cf/baai/bge-large-en-v1.5'
|
|
type: embedding
|
|
input_price: 0.0
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- name: '@cf/google/gemma-3-12b-it'
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 2048
|
|
require_max_tokens: true
|
|
- provider: ernie
|
|
models:
|
|
- name: ernie-4.5-turbo-128k
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.112
|
|
output_price: 0.448
|
|
- name: ernie-4.5-turbo-vl-32k
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.42
|
|
output_price: 1.26
|
|
supports_vision: true
|
|
- name: ernie-5.0-thinking-preview
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.4
|
|
output_price: 5.6
|
|
- name: ernie-x1.1-preview
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.14
|
|
output_price: 0.56
|
|
- name: bge-large-zh
|
|
type: embedding
|
|
input_price: 0.07
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 16
|
|
- name: bge-large-en
|
|
type: embedding
|
|
input_price: 0.07
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 16
|
|
- name: bce-reranker-base
|
|
type: reranker
|
|
max_input_tokens: 1024
|
|
input_price: 0.07
|
|
- provider: qianwen
|
|
models:
|
|
- name: qwen3.8-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.47
|
|
cache_read_price: 0.016
|
|
cache_write_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- xhigh
|
|
- name: qwen3.8-max
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- xhigh
|
|
- name: deepseek-v4-flash-0731
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.2
|
|
output_price: 0.4
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- high
|
|
- max
|
|
- name: kimi-k3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: glm-5.2
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.28
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: qwen3.7-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.625
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.7-max
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 7.5
|
|
cache_read_price: 0.5
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: qwen3.6-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.1875
|
|
output_price: 1.125
|
|
cache_write_price: 0.234375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.6-27b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 3.6
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.6-max-preview
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.3
|
|
output_price: 7.8
|
|
cache_read_price: 0.13
|
|
cache_write_price: 1.625
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3.6-35b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.248
|
|
output_price: 1.485
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.6-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.625
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.5-122b-a10b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 3.2
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.5-27b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.3
|
|
output_price: 2.4
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.5-35b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
cache_read_price: 0.1563
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.5-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.4
|
|
output_price: 2.4
|
|
patch:
|
|
body:
|
|
enable_thinking: false
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3.5-397b-a17b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 3.6
|
|
cache_read_price: 0.225
|
|
patch:
|
|
body:
|
|
enable_thinking: false
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3-max
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.2
|
|
output_price: 6.0
|
|
cache_read_price: 0.156
|
|
cache_write_price: 0.975
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-max:thinking
|
|
type: chat
|
|
real_name: qwen3-max
|
|
max_input_tokens: 262144
|
|
input_price: 1.2
|
|
output_price: 6.0
|
|
cache_read_price: 0.156
|
|
cache_write_price: 0.975
|
|
patch:
|
|
body:
|
|
enable_thinking: true
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-vl-plus
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 1.6
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3-omni-flash
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.43
|
|
output_price: 1.66
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3-asr-flash
|
|
type: chat
|
|
max_input_tokens: 53248
|
|
input_price: 0.035
|
|
output_price: 0.035
|
|
max_output_tokens: 4096
|
|
- name: qwen3-next-80b-a3b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 2.0
|
|
cache_read_price: 0.07
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen3-next-80b-a3b-thinking
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 6.0
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.05
|
|
output_price: 0.4
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen3-coder-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.3
|
|
output_price: 1.5
|
|
cache_read_price: 0.039
|
|
cache_write_price: 0.2438
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-coder-plus
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.13
|
|
cache_write_price: 0.8125
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-14b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.35
|
|
output_price: 1.4
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen3-235b-a22b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 2.8
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen3-32b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 2.8
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen3-8b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.18
|
|
output_price: 0.7
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen3-coder-30b-a3b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.45
|
|
output_price: 2.25
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-coder-480b-a35b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen3-vl-235b-a22b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 2.8
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen3-vl-30b-a3b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.2
|
|
output_price: 0.8
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qvq-max
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.2
|
|
output_price: 4.8
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwq-plus
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.8
|
|
output_price: 2.4
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen-omni-turbo
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.07
|
|
output_price: 0.27
|
|
max_output_tokens: 2048
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen-mt-plus
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
input_price: 2.46
|
|
output_price: 7.37
|
|
max_output_tokens: 8192
|
|
- name: qwen-mt-turbo
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
input_price: 0.16
|
|
output_price: 0.49
|
|
max_output_tokens: 8192
|
|
- name: qwen2-5-omni-7b
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
max_output_tokens: 2048
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen-turbo
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen-vl-ocr
|
|
type: chat
|
|
max_input_tokens: 34096
|
|
input_price: 0.72
|
|
output_price: 0.72
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
- name: qwen2-5-14b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.35
|
|
output_price: 1.4
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen2-5-32b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 2.8
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen2-5-72b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.4
|
|
output_price: 5.6
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen2-5-7b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.175
|
|
output_price: 0.7
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen2-5-vl-72b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.8
|
|
output_price: 8.4
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen2-5-vl-7b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.35
|
|
output_price: 1.05
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen-vl-max
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.8
|
|
output_price: 3.2
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen-max
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 1.6
|
|
output_price: 6.4
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.4
|
|
output_price: 1.2
|
|
cache_read_price: 0.052
|
|
cache_write_price: 0.325
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen-vl-plus
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.21
|
|
output_price: 0.63
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen-plus-character-ja
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.5
|
|
output_price: 1.4
|
|
max_output_tokens: 512
|
|
supports_function_calling: true
|
|
- name: qwen3.5-plus:thinking
|
|
type: chat
|
|
real_name: qwen3.5-plus
|
|
max_input_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: qwen3.5-397b-a17b:thinking
|
|
type: chat
|
|
real_name: qwen3.5-397b-a17b
|
|
max_input_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: text-embedding-v4
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 2000
|
|
max_batch_size: 10
|
|
- name: text-embedding-v3
|
|
type: embedding
|
|
input_price: 0.1
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 2000
|
|
max_batch_size: 10
|
|
- name: qwen3-vl-flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
supports_vision: true
|
|
- name: qwen3-235b-a22b-instruct-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.28
|
|
output_price: 1.12
|
|
supports_function_calling: true
|
|
- name: qwen3-235b-a22b-thinking-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.28
|
|
output_price: 2.8
|
|
- name: qwen3-30b-a3b-instruct-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.105
|
|
output_price: 0.42
|
|
supports_function_calling: true
|
|
- name: qwen3-30b-a3b-thinking-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.105
|
|
output_price: 1.05
|
|
- name: qwen3-vl-32b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.28
|
|
output_price: 1.12
|
|
supports_vision: true
|
|
- name: qwen3-vl-8b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.07
|
|
output_price: 0.28
|
|
supports_vision: true
|
|
- name: qwen3-coder-next
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
- provider: hunyuan
|
|
models:
|
|
- name: hunyuan-2.0-instruct-20251111
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.112
|
|
output_price: 0.28
|
|
supports_function_calling: true
|
|
- name: hunyuan-2.0-thinking-20251109
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.14
|
|
output_price: 0.56
|
|
supports_function_calling: true
|
|
- name: hunyuan-vision-1.5-instruct
|
|
type: chat
|
|
max_input_tokens: 24576
|
|
input_price: 0.42
|
|
output_price: 1.26
|
|
supports_vision: true
|
|
- name: hunyuan-embedding
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 1024
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- provider: moonshot
|
|
models:
|
|
- name: kimi-k3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: kimi-k2.7-code
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.19
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: kimi-k2.7-code-highspeed
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.9
|
|
output_price: 8.0
|
|
cache_read_price: 0.38
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: kimi-k2.6
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.16
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- provider: deepseek
|
|
models:
|
|
- name: deepseek-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.003
|
|
max_output_tokens: 393216
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: deepseek-v4-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.003
|
|
max_output_tokens: 393216
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: deepseek-v4-flash-vision-exp
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.003
|
|
max_output_tokens: 393216
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: deepseek-v4-pro
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.435
|
|
output_price: 0.87
|
|
cache_read_price: 0.003625
|
|
max_output_tokens: 393216
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: deepseek-chat
|
|
type: chat
|
|
max_input_tokens: 64000
|
|
input_price: 0.56
|
|
output_price: 1.68
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: deepseek-reasoner
|
|
type: chat
|
|
max_input_tokens: 64000
|
|
input_price: 0.56
|
|
output_price: 1.68
|
|
max_output_tokens: 32768
|
|
- provider: zhipuai
|
|
models:
|
|
- name: glm-5.3-flashx
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.37
|
|
output_price: 1.25
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: glm-5.3-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: glm-5.3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.26
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: glm-5.2
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.26
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- high
|
|
- max
|
|
- name: glm-5v-turbo
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 22.0
|
|
cache_read_price: 1.2
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: glm-5.1
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.4
|
|
output_price: 4.4
|
|
cache_read_price: 0.26
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-5
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 1.0
|
|
output_price: 3.2
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-5:instruct
|
|
type: chat
|
|
real_name: glm-5
|
|
max_input_tokens: 204800
|
|
input_price: 1.0
|
|
output_price: 3.2
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.0
|
|
patch:
|
|
body:
|
|
thinking:
|
|
type: disabled
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.7-flash
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
cache_read_price: 0.0
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.7-flashx
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.07
|
|
output_price: 0.4
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.7
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.7:instruct
|
|
type: chat
|
|
real_name: glm-4.7
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
cache_write_price: 0.0
|
|
patch:
|
|
body:
|
|
thinking:
|
|
type: disabled
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.6v
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: glm-4.6v-flash
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
cache_read_price: 0.0
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: glm-4.6
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: glm-4.5v
|
|
type: chat
|
|
max_input_tokens: 64000
|
|
input_price: 0.6
|
|
output_price: 1.8
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: glm-4.5
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: glm-4.5-air
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.2
|
|
output_price: 1.1
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: glm-4.5-flash
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
cache_read_price: 0.0
|
|
cache_write_price: 0.0
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: embedding-3
|
|
type: embedding
|
|
max_input_tokens: 8192
|
|
input_price: 0.07
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 2000
|
|
- name: rerank
|
|
type: reranker
|
|
max_input_tokens: 4096
|
|
input_price: 0.112
|
|
- provider: minimax
|
|
models:
|
|
- name: MiniMax-M3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 512000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2.7
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.06
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2.7-highspeed
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.4
|
|
cache_read_price: 0.06
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2.5-highspeed
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.4
|
|
cache_read_price: 0.06
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2.5
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2.1
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: MiniMax-M2
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: minimax-m3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.2
|
|
output_price: 16.8
|
|
supports_function_calling: true
|
|
- name: minimax-m2.7
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.294
|
|
output_price: 1.176
|
|
supports_function_calling: true
|
|
- name: minimax-m2.5
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.294
|
|
output_price: 1.176
|
|
supports_function_calling: true
|
|
- name: minimax-m2.5-highspeed
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.588
|
|
output_price: 2.352
|
|
supports_function_calling: true
|
|
- name: minimax-m2.1
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.294
|
|
output_price: 1.176
|
|
supports_function_calling: true
|
|
- name: minimax-m2.1-highspeed
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.588
|
|
output_price: 2.352
|
|
supports_function_calling: true
|
|
- provider: openrouter
|
|
models:
|
|
- name: google/gemini-3-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: google/gemini-2.0-flash-001
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.0-flash-lite-001
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-fable-5-1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-opus-4-8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-opus-4-7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: mistralai/devstral-small
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.07
|
|
output_price: 0.28
|
|
supports_function_calling: true
|
|
- name: ai21/jamba-large-1.7
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.1-fast
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
input_price: 0.2
|
|
output_price: 0.5
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-code-fast-1
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.2
|
|
output_price: 1.5
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-2.0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.8
|
|
output_price: 1.6
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-3.0
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 3.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.75
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-3.0-mini
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 1.4
|
|
cache_read_price: 0.18
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-3.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 3.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.75
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-3.5-mini
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.7
|
|
output_price: 1.4
|
|
cache_read_price: 0.18
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: aion-labs/aion-rp-llama-3.1-8b
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.8
|
|
output_price: 1.6
|
|
max_output_tokens: 29491
|
|
- name: amazon/nova-2-lite-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: amazon/nova-lite-v1
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.06
|
|
output_price: 0.24
|
|
max_output_tokens: 5120
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: amazon/nova-micro-v1
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.035
|
|
output_price: 0.14
|
|
max_output_tokens: 5120
|
|
supports_function_calling: true
|
|
- name: amazon/nova-premier-v1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.625
|
|
max_output_tokens: 32000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: amazon/nova-pro-v1
|
|
type: chat
|
|
max_input_tokens: 300000
|
|
input_price: 0.8
|
|
output_price: 3.2
|
|
max_output_tokens: 5120
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthracite-org/magnum-v4-72b
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 2.5
|
|
output_price: 5.0
|
|
max_output_tokens: 4096
|
|
- name: anthropic/claude-fable-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-fable-5.1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-fable-5.1:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.125
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-fable-5:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-haiku-4.5
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-haiku-4.5:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.5
|
|
output_price: 2.5
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.625
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.1
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 75.0
|
|
cache_read_price: 1.5
|
|
cache_write_price: 18.75
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.1:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 7.5
|
|
output_price: 37.5
|
|
cache_read_price: 0.75
|
|
cache_write_price: 9.375
|
|
max_output_tokens: 32000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.5
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.5:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.25
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-opus-4.6:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.25
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.7
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.7:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.25
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.8
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-4.8:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.25
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-opus-5.5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-5.5:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-opus-5:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.5
|
|
output_price: 12.5
|
|
cache_read_price: 0.25
|
|
cache_write_price: 3.125
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-sonnet-4
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-sonnet-4.5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-sonnet-4.5:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
cache_read_price: 0.15
|
|
cache_write_price: 1.875
|
|
max_output_tokens: 64000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-sonnet-4.6
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
cache_write_price: 3.75
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-sonnet-4.6:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
cache_read_price: 0.15
|
|
cache_write_price: 1.875
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: anthropic/claude-sonnet-5
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: high
|
|
- name: anthropic/claude-sonnet-5:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 128000
|
|
require_max_tokens: true
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: arcee-ai/trinity-large-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.25
|
|
output_price: 0.8
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 80000
|
|
supports_function_calling: true
|
|
- name: baidu/ernie-4.5-vl-424b-a47b
|
|
type: chat
|
|
max_input_tokens: 123000
|
|
input_price: 0.42
|
|
output_price: 1.25
|
|
max_output_tokens: 16000
|
|
supports_vision: true
|
|
- name: bytedance-seed/seed-1.6
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance-seed/seed-1.6-flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance-seed/seed-2-1-turbo
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 2.5
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance-seed/seed-2.0-code
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance-seed/seed-2.0-lite
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance-seed/seed-2.0-mini
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: bytedance/ui-tars-1.5-7b
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 2048
|
|
supports_vision: true
|
|
- name: cognitivecomputations/dolphin-mistral-24b-venice-edition
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.2
|
|
output_price: 0.9
|
|
max_output_tokens: 8192
|
|
- name: cohere/command-a
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 8192
|
|
- name: cohere/command-a-plus
|
|
type: chat
|
|
max_input_tokens: 192000
|
|
input_price: 0.3
|
|
output_price: 1.5
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: cohere/command-r-08-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: cohere/command-r-plus-08-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 4000
|
|
supports_function_calling: true
|
|
- name: cohere/command-r7b-12-2024
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.0375
|
|
output_price: 0.15
|
|
max_output_tokens: 4000
|
|
- name: cohere/north-mini-code:free
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-chat
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.32
|
|
output_price: 0.89
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-chat-v3-0324
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.25
|
|
output_price: 1.0
|
|
max_output_tokens: 147456
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-chat-v3.1
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.25
|
|
output_price: 0.95
|
|
cache_read_price: 0.13
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-r1
|
|
type: chat
|
|
max_input_tokens: 64000
|
|
input_price: 0.7
|
|
output_price: 2.5
|
|
max_output_tokens: 16000
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-r1-0528
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.5
|
|
output_price: 2.15
|
|
cache_read_price: 0.35
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-r1-distill-llama-70b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.8
|
|
output_price: 0.8
|
|
max_output_tokens: 7372
|
|
- name: deepseek/deepseek-v3.1-terminus
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.27
|
|
output_price: 1.0
|
|
cache_read_price: 0.135
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v3.2
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.269
|
|
output_price: 0.4
|
|
cache_read_price: 0.1345
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v3.2-exp
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.27
|
|
output_price: 0.41
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.047
|
|
output_price: 0.0941
|
|
cache_read_price: 0.0094
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4-flash-0731
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.021
|
|
output_price: 0.32
|
|
cache_read_price: 0.016
|
|
max_output_tokens: 943718
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4-flash-vision-exp
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.22
|
|
output_price: 0.66
|
|
cache_read_price: 0.007
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4-pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.348
|
|
output_price: 0.696
|
|
cache_read_price: 0.029
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4-pro-0813
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.264
|
|
output_price: 0.792
|
|
cache_read_price: 0.0088
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4.1-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.006
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek/deepseek-v4.1-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.112
|
|
output_price: 0.336
|
|
cache_read_price: 0.0034
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: dots-studio/dots-3-note-preview:free
|
|
type: chat
|
|
max_input_tokens: 512000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 460800
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: fireworks/ember-1
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: low
|
|
- name: google/gemini-2.5-flash-image
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: google/gemini-2.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.5-flash-lite:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.5-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.15
|
|
output_price: 1.25
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 65535
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.5-pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: google/gemini-2.5-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-2.5-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.625
|
|
output_price: 5.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3-flash-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.05
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: google/gemini-3-flash-preview:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3-pro-image
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3-pro-image-preview
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
- name: google/gemini-3.1-flash-image
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
- name: google/gemini-3.1-flash-image-preview
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
max_output_tokens: 58982
|
|
supports_vision: true
|
|
- name: google/gemini-3.1-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: minimal
|
|
- name: google/gemini-3.1-flash-lite-image
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
max_output_tokens: 58982
|
|
supports_vision: true
|
|
- name: google/gemini-3.1-flash-lite-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.25
|
|
output_price: 1.5
|
|
cache_read_price: 0.025
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.1-flash-lite:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.125
|
|
output_price: 0.75
|
|
cache_read_price: 0.0125
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.1-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: high
|
|
- name: google/gemini-3.1-pro-preview-customtools
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.1-pro-preview:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.0
|
|
output_price: 6.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.5-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.5
|
|
output_price: 9.0
|
|
cache_read_price: 0.15
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: google/gemini-3.5-flash-lite
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 2.5
|
|
cache_read_price: 0.03
|
|
cache_write_price: 0.0833
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.5-flash-lite:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.15
|
|
output_price: 1.25
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.5-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 4.5
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.6-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.6-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.375
|
|
output_price: 1.875
|
|
cache_read_price: 0.0375
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.7-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.7-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.375
|
|
output_price: 1.875
|
|
cache_read_price: 0.0375
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.8-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemini-3.8-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.375
|
|
output_price: 1.875
|
|
cache_read_price: 0.0375
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-2-27b-it
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.65
|
|
output_price: 0.65
|
|
max_output_tokens: 2048
|
|
- name: google/gemma-3-12b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.15
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-3-27b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.08
|
|
output_price: 0.45
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 117964
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-3-4b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.1
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
- name: google/gemma-4-26b-a4b-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0675
|
|
output_price: 0.225
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-26b-a4b-it:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-31b-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.09
|
|
output_price: 0.34
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-31b-it:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/lyria-3-clip-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
- name: google/lyria-3-pro-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
- name: gryphe/mythomax-l2-13b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.08
|
|
output_price: 0.11
|
|
max_output_tokens: 3686
|
|
- name: ibm-granite/granite-4.0-h-micro
|
|
type: chat
|
|
max_input_tokens: 131000
|
|
input_price: 0.017
|
|
output_price: 0.112
|
|
max_output_tokens: 117900
|
|
- name: ibm-granite/granite-4.2-8b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.06
|
|
output_price: 0.25
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: inception/mercury-2
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.25
|
|
output_price: 0.75
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 50000
|
|
supports_function_calling: true
|
|
- name: inception/mercury-2.5
|
|
type: chat
|
|
max_input_tokens: 260000
|
|
input_price: 0.04
|
|
output_price: 0.15
|
|
cache_read_price: 0.004
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: inclusionai/ling-3.0-flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.021
|
|
output_price: 0.063
|
|
cache_read_price: 0.0042
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: inclusionai/ling-3.0-flash-fin
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.06
|
|
output_price: 0.18
|
|
cache_read_price: 0.012
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: inclusionai/ling-3.0-flash-fin:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: inclusionai/ling-3.0-flash-sante:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: inclusionai/ling-3.0-flash-vl
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.021
|
|
output_price: 0.0616
|
|
cache_read_price: 0.0042
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: inference-net/schematron-v2-small
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.05
|
|
output_price: 0.23
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 4096
|
|
- name: inference-net/schematron-v2-turbo
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.03
|
|
output_price: 0.15
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 8192
|
|
- name: kwaipilot/kat-coder-pro-v2.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.74
|
|
output_price: 2.96
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: liquid/lfm-2.5-2.6b:free
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: mancer/weaver
|
|
type: chat
|
|
max_input_tokens: 8000
|
|
input_price: 0.4
|
|
output_price: 0.75
|
|
max_output_tokens: 6000
|
|
- name: meituan/longcat-2.0
|
|
type: chat
|
|
max_input_tokens: 1048756
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.006
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-3.1-70b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 0.4
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-3.1-8b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.08
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-3.2-1b-instruct
|
|
type: chat
|
|
max_input_tokens: 60000
|
|
input_price: 0.027
|
|
output_price: 0.201
|
|
max_output_tokens: 54000
|
|
- name: meta-llama/llama-3.2-3b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.33
|
|
max_output_tokens: 117964
|
|
- name: meta-llama/llama-3.3-70b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.1
|
|
output_price: 0.32
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-4-maverick
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1875
|
|
output_price: 0.6525
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-4-scout
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta-llama/llama-guard-4-12b
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.18
|
|
output_price: 0.18
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
- name: meta/muse-glimmer-30b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/muse-spark-1.1
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 4.25
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/muse-spark-1.2
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 4.25
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/muse-spark-1.2-contributor
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
cache_read_price: 0.002
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/muse-spark-1.3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.25
|
|
output_price: 4.25
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: meta/muse-spark-1.3-contributor
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
cache_read_price: 0.002
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: microsoft/phi-4
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
input_price: 0.07
|
|
output_price: 0.14
|
|
max_output_tokens: 14745
|
|
- name: microsoft/wizardlm-2-8x22b
|
|
type: chat
|
|
max_input_tokens: 65535
|
|
input_price: 0.62
|
|
output_price: 0.62
|
|
max_output_tokens: 8000
|
|
- name: minimax/minimax-01
|
|
type: chat
|
|
max_input_tokens: 1000192
|
|
input_price: 0.2
|
|
output_price: 1.1
|
|
max_output_tokens: 900172
|
|
supports_vision: true
|
|
- name: minimax/minimax-m1
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.4
|
|
output_price: 2.2
|
|
max_output_tokens: 40000
|
|
supports_function_calling: true
|
|
- name: minimax/minimax-m2
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
max_output_tokens: 176947
|
|
supports_function_calling: true
|
|
- name: minimax/minimax-m2-her
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 2048
|
|
- name: minimax/minimax-m2.1
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: minimax/minimax-m2.5
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.27
|
|
output_price: 1.08
|
|
cache_read_price: 0.027
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: minimax/minimax-m2.7
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: minimax/minimax-m3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.3
|
|
output_price: 1.2
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 512000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/codestral-2508
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 204800
|
|
supports_function_calling: true
|
|
- name: mistralai/codestral-2508:batch
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.15
|
|
output_price: 0.45
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 204800
|
|
supports_function_calling: true
|
|
- name: mistralai/devstral-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 209715
|
|
supports_function_calling: true
|
|
- name: mistralai/ministral-14b-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 0.2
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/ministral-3b-2512
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.1
|
|
output_price: 0.1
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 104857
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/ministral-8b-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 0.15
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/ministral-8b-2512:batch
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.075
|
|
output_price: 0.075
|
|
cache_read_price: 0.0075
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-large
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 102400
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-large-2407
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 104857
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-large-2512
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-large-2512:batch
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.25
|
|
output_price: 0.75
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-medium-3
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 104857
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-medium-3-5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.5
|
|
output_price: 7.5
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-medium-3-5:batch
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-medium-3.1
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 2.0
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 104857
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-medium-3.1:batch
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.2
|
|
output_price: 1.0
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 104857
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-nemo
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.019
|
|
output_price: 0.03
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-saba
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.2
|
|
output_price: 0.6
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 26214
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-small-24b-instruct-2501
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.05
|
|
output_price: 0.08
|
|
max_output_tokens: 16384
|
|
- name: mistralai/mistral-small-2603
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-small-2603:batch
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
cache_read_price: 0.0075
|
|
max_output_tokens: 209715
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-small-3.1-24b-instruct
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.351
|
|
output_price: 0.555
|
|
max_output_tokens: 102400
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mistral-small-3.2-24b-instruct
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.0938
|
|
output_price: 0.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: mistralai/mixtral-8x22b-instruct
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 52428
|
|
supports_function_calling: true
|
|
- name: mistralai/voxtral-small-24b-2507
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 26214
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.57
|
|
output_price: 2.3
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2-0905
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 2.5
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 2.5
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.45
|
|
output_price: 2.25
|
|
cache_read_price: 0.07
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2.6
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.16
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k2.7-code
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6562
|
|
output_price: 3.3
|
|
cache_read_price: 0.18
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/kimi-k3:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.28
|
|
output_price: 11.4
|
|
cache_read_price: 0.228
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: morph/morph-v3-fast
|
|
type: chat
|
|
max_input_tokens: 81920
|
|
input_price: 0.8
|
|
output_price: 1.2
|
|
max_output_tokens: 38000
|
|
- name: morph/morph-v3-large
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.9
|
|
output_price: 1.9
|
|
max_output_tokens: 131072
|
|
- name: nousresearch/hermes-3-llama-3.1-405b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.0
|
|
output_price: 1.0
|
|
max_output_tokens: 16384
|
|
- name: nousresearch/hermes-3-llama-3.1-70b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.7
|
|
output_price: 0.7
|
|
max_output_tokens: 16384
|
|
- name: nousresearch/hermes-4-405b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 1.0
|
|
output_price: 3.0
|
|
max_output_tokens: 117964
|
|
- name: nvidia/nemotron-3-nano-30b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3-super-120b-a12b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.08
|
|
output_price: 0.45
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3-super-120b-a12b:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3-ultra-550b-a55b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.6
|
|
output_price: 2.4
|
|
cache_read_price: 0.12
|
|
max_output_tokens: 182520
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3-ultra-550b-a55b:free
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3.5-content-safety
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.2
|
|
output_price: 0.2
|
|
max_output_tokens: 117964
|
|
supports_vision: true
|
|
- name: nvidia/nemotron-3.5-content-safety:free
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: nvidia/nemotron-3.5-lightning
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.08
|
|
output_price: 0.2
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: nvidia/nemotron-3.5-lightning:free
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: openai/gpt-3.5-turbo
|
|
type: chat
|
|
max_input_tokens: 16385
|
|
input_price: 0.5
|
|
output_price: 1.5
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: openai/gpt-3.5-turbo-0613
|
|
type: chat
|
|
max_input_tokens: 4095
|
|
input_price: 1.0
|
|
output_price: 2.0
|
|
max_output_tokens: 3685
|
|
supports_function_calling: true
|
|
- name: openai/gpt-3.5-turbo-16k
|
|
type: chat
|
|
max_input_tokens: 16385
|
|
input_price: 3.0
|
|
output_price: 4.0
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: openai/gpt-3.5-turbo-instruct
|
|
type: chat
|
|
max_input_tokens: 4095
|
|
input_price: 1.5
|
|
output_price: 2.0
|
|
max_output_tokens: 3685
|
|
- name: openai/gpt-3.5-turbo:batch
|
|
type: chat
|
|
max_input_tokens: 16385
|
|
input_price: 0.25
|
|
output_price: 0.75
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4
|
|
type: chat
|
|
max_input_tokens: 8191
|
|
input_price: 30.0
|
|
output_price: 60.0
|
|
max_output_tokens: 4096
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4-turbo
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 10.0
|
|
output_price: 30.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4-turbo:batch
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 5.0
|
|
output_price: 15.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1-mini
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.4
|
|
output_price: 1.6
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1-mini:batch
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.2
|
|
output_price: 0.8
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1-nano
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1-nano:batch
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
cache_read_price: 0.0125
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4.1:batch
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
input_price: 1.0
|
|
output_price: 4.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-2024-05-13
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 5.0
|
|
output_price: 15.0
|
|
max_output_tokens: 4096
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-2024-08-06
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-2024-11-20
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-mini
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-mini-2024-07-18
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o-mini:batch
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-4o:batch
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.25
|
|
output_price: 5.0
|
|
cache_read_price: 0.625
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- minimal
|
|
- low
|
|
- medium
|
|
- high
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5-image
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 10.0
|
|
output_price: 10.0
|
|
cache_read_price: 1.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
- name: openai/gpt-5-image-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 2.5
|
|
output_price: 2.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
- name: openai/gpt-5-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5-mini:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.125
|
|
output_price: 1.0
|
|
cache_read_price: 0.0125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5-nano
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.05
|
|
output_price: 0.4
|
|
cache_read_price: 0.005
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5-nano:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.025
|
|
output_price: 0.2
|
|
cache_read_price: 0.0025
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5-pro
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 15.0
|
|
output_price: 120.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5-pro:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 7.5
|
|
output_price: 60.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.1
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.1-codex
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.13
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.1-codex-max
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.25
|
|
output_price: 10.0
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.1-codex-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.25
|
|
output_price: 2.0
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.1:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.625
|
|
output_price: 5.0
|
|
cache_read_price: 0.0625
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.2
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: openai/gpt-5.2-chat
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 32000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.2-codex
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.2-pro
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 21.0
|
|
output_price: 168.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.2-pro:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 10.5
|
|
output_price: 84.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.2:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.875
|
|
output_price: 7.0
|
|
cache_read_price: 0.0875
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.3-codex
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 1.75
|
|
output_price: 14.0
|
|
cache_read_price: 0.175
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.4
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.5
|
|
output_price: 15.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: openai/gpt-5.4-image-2
|
|
type: chat
|
|
max_input_tokens: 272000
|
|
input_price: 8.0
|
|
output_price: 15.0
|
|
cache_read_price: 2.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
- name: openai/gpt-5.4-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.75
|
|
output_price: 4.5
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: openai/gpt-5.4-mini:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.375
|
|
output_price: 2.25
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.4-nano
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.2
|
|
output_price: 1.25
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: none
|
|
- name: openai/gpt-5.4-nano:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.1
|
|
output_price: 0.625
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.4-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 30.0
|
|
output_price: 180.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.4-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 15.0
|
|
output_price: 90.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.4:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.25
|
|
output_price: 7.5
|
|
cache_read_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.5
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.5-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 30.0
|
|
output_price: 180.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
default_reasoning_effort: high
|
|
- name: openai/gpt-5.5-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 15.0
|
|
output_price: 90.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.5:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.5
|
|
output_price: 15.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-5.6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.2
|
|
output_price: 1.2
|
|
cache_read_price: 0.02
|
|
cache_write_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-luna-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.2
|
|
output_price: 1.2
|
|
cache_read_price: 0.02
|
|
cache_write_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-luna-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.6
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-luna:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.6
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-sol-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-sol-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-sol:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-terra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-terra-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-terra-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5.6-terra:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- max
|
|
default_reasoning_effort: medium
|
|
- name: openai/gpt-5:batch
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.625
|
|
output_price: 5.0
|
|
cache_read_price: 0.0625
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-astra
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-astra-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-astra-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-astra:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 5.0
|
|
output_price: 25.0
|
|
cache_read_price: 0.5
|
|
cache_write_price: 6.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-luna
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.5
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-luna-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.5
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-luna-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.05
|
|
output_price: 0.25
|
|
cache_read_price: 0.005
|
|
cache_write_price: 0.0625
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-luna:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.05
|
|
output_price: 0.25
|
|
cache_read_price: 0.005
|
|
cache_write_price: 0.0625
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-sol
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-sol-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-sol-pro:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-6-sol:batch
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-audio
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.5
|
|
output_price: 10.0
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: openai/gpt-audio-mini
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.6
|
|
output_price: 2.4
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: openai/gpt-chat-latest
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-120b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-120b:batch
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.0296
|
|
output_price: 0.136
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.018
|
|
output_price: 0.09
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-20b:batch
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.024
|
|
output_price: 0.112
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-safeguard-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.075
|
|
output_price: 0.3
|
|
cache_read_price: 0.0375
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: openai/o1
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 15.0
|
|
output_price: 60.0
|
|
cache_read_price: 7.5
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o1-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 150.0
|
|
output_price: 600.0
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
- name: openai/o3
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o3-mini
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.55
|
|
max_output_tokens: 100000
|
|
supports_function_calling: true
|
|
- name: openai/o3-mini-high
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.55
|
|
max_output_tokens: 100000
|
|
supports_function_calling: true
|
|
- name: openai/o3-mini:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.55
|
|
output_price: 2.2
|
|
cache_read_price: 0.275
|
|
max_output_tokens: 100000
|
|
supports_function_calling: true
|
|
- name: openai/o3-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 20.0
|
|
output_price: 80.0
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o3:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 4.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o4-mini
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.275
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o4-mini-high
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.1
|
|
output_price: 4.4
|
|
cache_read_price: 0.275
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openai/o4-mini:batch
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.55
|
|
output_price: 2.2
|
|
cache_read_price: 0.1375
|
|
max_output_tokens: 100000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openrouter/auto
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openrouter/auto-beta
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openrouter/bodybuilder
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
- name: openrouter/free
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: openrouter/fusion
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
- name: openrouter/pareto-code
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
- name: perceptron/perceptron-mk1
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.15
|
|
output_price: 1.5
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
- name: perceptron/perceptron-mk1.5
|
|
type: chat
|
|
max_input_tokens: 36864
|
|
input_price: 0.15
|
|
output_price: 1.5
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: perplexity/sonar
|
|
type: chat
|
|
max_input_tokens: 127072
|
|
input_price: 1.0
|
|
output_price: 1.0
|
|
max_output_tokens: 114364
|
|
supports_vision: true
|
|
- name: perplexity/sonar-deep-research
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
patch:
|
|
body:
|
|
include_reasoning: true
|
|
max_output_tokens: 115200
|
|
- name: perplexity/sonar-pro
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
max_output_tokens: 8000
|
|
supports_vision: true
|
|
- name: perplexity/sonar-pro-search
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 3.0
|
|
output_price: 15.0
|
|
max_output_tokens: 8000
|
|
supports_vision: true
|
|
- name: perplexity/sonar-reasoning-pro
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 2.0
|
|
output_price: 8.0
|
|
patch:
|
|
body:
|
|
include_reasoning: true
|
|
max_output_tokens: 115200
|
|
supports_vision: true
|
|
- name: poolside/laguna-s-2.1
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.09
|
|
output_price: 0.18
|
|
cache_read_price: 0.009
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: poolside/laguna-s-2.1:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: poolside/laguna-xs-2.1
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.06
|
|
output_price: 0.12
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: poolside/laguna-xs-2.1:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: prism-ml/ternary-bonsai-2-27b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.075
|
|
output_price: 0.5
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen-2.5-72b-instruct
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.36
|
|
output_price: 0.4
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen/qwen-2.5-7b-instruct
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
max_output_tokens: 29491
|
|
supports_function_calling: true
|
|
- name: qwen/qwen-2.5-coder-32b-instruct
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.66
|
|
output_price: 1.0
|
|
max_output_tokens: 29491
|
|
- name: qwen/qwen-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.26
|
|
output_price: 0.78
|
|
cache_read_price: 0.052
|
|
cache_write_price: 0.325
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen/qwen-plus-2025-07-28
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.26
|
|
output_price: 0.78
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen/qwen2.5-vl-72b-instruct
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
input_price: 0.8
|
|
output_price: 1.0
|
|
cache_read_price: 0.4
|
|
max_output_tokens: 115200
|
|
supports_vision: true
|
|
- name: qwen/qwen3-14b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.12
|
|
output_price: 0.24
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-235b-a22b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.455
|
|
output_price: 1.82
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-235b-a22b-2507
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0875
|
|
output_price: 0.35
|
|
cache_read_price: 0.0175
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-235b-a22b-thinking-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.23
|
|
output_price: 2.3
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-30b-a3b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.12
|
|
output_price: 0.5
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-30b-a3b-instruct-2507
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-30b-a3b-thinking-2507
|
|
type: chat
|
|
max_input_tokens: 81920
|
|
input_price: 0.2
|
|
output_price: 2.4
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-32b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.08
|
|
output_price: 0.28
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-8b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.117
|
|
output_price: 0.455
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-coder
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.3
|
|
output_price: 1.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-coder-30b-a3b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.07
|
|
output_price: 0.28
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-coder-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.195
|
|
output_price: 0.975
|
|
cache_read_price: 0.039
|
|
cache_write_price: 0.2438
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-coder-next
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.12
|
|
output_price: 0.8
|
|
cache_read_price: 0.07
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-coder-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.65
|
|
output_price: 3.25
|
|
cache_read_price: 0.13
|
|
cache_write_price: 0.8125
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-max
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.78
|
|
output_price: 3.9
|
|
cache_read_price: 0.156
|
|
cache_write_price: 0.975
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-max-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.78
|
|
output_price: 3.9
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-next-80b-a3b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 1.1
|
|
cache_read_price: 0.07
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-next-80b-a3b-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 1.2
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-235b-a22b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.21
|
|
output_price: 1.9
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-235b-a22b-thinking
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 4.0
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-30b-a3b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-30b-a3b-thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 2.4
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-32b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.104
|
|
output_price: 0.416
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-8b-instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.117
|
|
output_price: 0.455
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3-vl-8b-thinking
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.18
|
|
output_price: 2.1
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-122b-a10b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.26
|
|
output_price: 2.08
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-27b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.195
|
|
output_price: 1.56
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-35b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.3125
|
|
output_price: 1.25
|
|
cache_read_price: 0.1563
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-397b-a17b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.55
|
|
output_price: 3.5
|
|
cache_read_price: 0.225
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-9b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.15
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-flash-02-23
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.065
|
|
output_price: 0.26
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-plus-02-15
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.26
|
|
output_price: 1.56
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.5-plus-20260420
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.3
|
|
output_price: 1.8
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.6-27b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.32
|
|
output_price: 3.2
|
|
max_output_tokens: 81920
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.6-35b-a3b
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.15
|
|
output_price: 1.0
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.6-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.1875
|
|
output_price: 1.125
|
|
cache_write_price: 0.2344
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.6-max-preview
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.027
|
|
output_price: 6.162
|
|
cache_write_price: 1.2838
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.6-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.325
|
|
output_price: 1.95
|
|
cache_write_price: 0.4063
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.7-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.03
|
|
output_price: 0.13
|
|
cache_read_price: 0.006
|
|
cache_write_price: 0.038
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.7-max
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.475
|
|
output_price: 4.425
|
|
cache_read_price: 0.295
|
|
cache_write_price: 1.8438
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.7-plus
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.32
|
|
output_price: 1.28
|
|
cache_read_price: 0.064
|
|
cache_write_price: 0.4
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-2.4t-a95b
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-27b
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.42
|
|
output_price: 3.0
|
|
cache_read_price: 0.085
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-27b:free
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 235929
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.47
|
|
cache_read_price: 0.016
|
|
cache_write_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-max-0902
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-max-prime
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: qwen/qwen3.8-omni-flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.15
|
|
output_price: 0.47
|
|
cache_read_price: 0.016
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: rekaai/reka-edge
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
input_price: 0.1
|
|
output_price: 0.1
|
|
max_output_tokens: 14745
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: rekaai/reka-flash-3
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
max_output_tokens: 58982
|
|
- name: relace/relace-apply-3
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.85
|
|
output_price: 1.25
|
|
max_output_tokens: 128000
|
|
- name: relace/relace-search
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 1.0
|
|
output_price: 3.0
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: sakana/fugu-max
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: sakana/fugu-ultra
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: sakana/fugu-ultra-v2
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 5.0
|
|
output_price: 30.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: sakana/sakana-namazu
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.95
|
|
output_price: 4.0
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: sao10k/l3-lunaris-8b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.04
|
|
output_price: 0.05
|
|
max_output_tokens: 7372
|
|
- name: sao10k/l3.1-euryale-70b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.85
|
|
output_price: 0.85
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: sao10k/l3.3-euryale-70b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.65
|
|
output_price: 0.75
|
|
max_output_tokens: 16384
|
|
- name: stealth/space-bunny-alpha
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 524288
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: stepfun/step-3.5-flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: stepfun/step-3.7-flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 1.15
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 230400
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: tencent/hunyuan-a13b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.14
|
|
output_price: 0.57
|
|
max_output_tokens: 117964
|
|
- name: tencent/hy-mt2-1.8b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.044
|
|
output_price: 0.177
|
|
max_output_tokens: 4096
|
|
- name: tencent/hy-mt2-30b-a3b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.074
|
|
output_price: 0.295
|
|
max_output_tokens: 4096
|
|
- name: tencent/hy-mt2-7b
|
|
type: chat
|
|
max_input_tokens: 8192
|
|
input_price: 0.074
|
|
output_price: 0.295
|
|
max_output_tokens: 4096
|
|
- name: tencent/hy3
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.132
|
|
output_price: 0.528
|
|
cache_read_price: 0.033
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: tencent/hy3-preview
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.18
|
|
output_price: 0.6
|
|
cache_read_price: 0.06
|
|
max_output_tokens: 235929
|
|
supports_function_calling: true
|
|
- name: tencent/hy4-preview
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.834
|
|
output_price: 2.501
|
|
cache_read_price: 0.042
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: thedrummer/cydonia-24b-v4.1
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.3
|
|
output_price: 0.5
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 117964
|
|
- name: thedrummer/skyfall-36b-v2
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.55
|
|
output_price: 0.8
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 29491
|
|
- name: thedrummer/unslopnemo-12b
|
|
type: chat
|
|
max_input_tokens: 1024000
|
|
input_price: 0.4
|
|
output_price: 0.4
|
|
max_output_tokens: 819200
|
|
- name: thinkingmachines/inkling
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 1.0
|
|
output_price: 4.05
|
|
cache_read_price: 0.17
|
|
max_output_tokens: 471859
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: thinkingmachines/inkling-small
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.45
|
|
output_price: 1.2
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: thinkingmachines/inkling-small:free
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: thinkingmachines/inkling:free
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.0
|
|
output_price: 0.0
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: typesafe/jev-router
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
supports_vision: true
|
|
- name: unbiased/pareto
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 2.5
|
|
output_price: 7.5
|
|
cache_read_price: 0.25
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: undi95/remm-slerp-l2-13b
|
|
type: chat
|
|
max_input_tokens: 6144
|
|
input_price: 0.35
|
|
output_price: 0.65
|
|
max_output_tokens: 5529
|
|
- name: upstage/solar-mini4
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
cache_read_price: 0.005
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: upstage/solar-pro-3
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.15
|
|
output_price: 0.6
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: upstage/solar-pro4
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.09
|
|
output_price: 0.36
|
|
cache_read_price: 0.018
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: writer/palmyra-x5
|
|
type: chat
|
|
max_input_tokens: 1040000
|
|
input_price: 0.6
|
|
output_price: 6.0
|
|
max_output_tokens: 8192
|
|
- name: x-ai/grok-4.20
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 1800000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.20-multi-agent
|
|
type: chat
|
|
max_input_tokens: 2000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 1800000
|
|
supports_vision: true
|
|
- name: x-ai/grok-4.3
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.25
|
|
output_price: 2.5
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 900000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.3:batch
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 1.0
|
|
output_price: 2.0
|
|
cache_read_price: 0.16
|
|
max_output_tokens: 900000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.5
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 450000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.6
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 450000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-4.7
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 1.6
|
|
output_price: 4.8
|
|
cache_read_price: 0.4
|
|
max_output_tokens: 450000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: x-ai/grok-build-0.1
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 1.0
|
|
output_price: 2.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 230400
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xiaomi/mimo-v2.5
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.14
|
|
output_price: 0.28
|
|
cache_read_price: 0.0028
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xiaomi/mimo-v2.5-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.435
|
|
output_price: 0.87
|
|
cache_read_price: 0.0036
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: xiaomi/mimo-v2.6-flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.14
|
|
output_price: 0.28
|
|
cache_read_price: 0.0028
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xiaomi/mimo-v2.6-pro
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.435
|
|
output_price: 0.87
|
|
cache_read_price: 0.0036
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: xiaomi/mimo-v2.6-pro-ultraspeed
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 4.35
|
|
output_price: 8.7
|
|
cache_read_price: 0.036
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.5
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.5-air
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.13
|
|
output_price: 0.85
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 98304
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.5v
|
|
type: chat
|
|
max_input_tokens: 65536
|
|
input_price: 0.6
|
|
output_price: 1.8
|
|
cache_read_price: 0.11
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.6
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.43
|
|
output_price: 1.75
|
|
cache_read_price: 0.08
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.6v
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
cache_read_price: 0.055
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.7
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 2.2
|
|
cache_read_price: 0.11
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-4.7-flash
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 0.0605
|
|
output_price: 0.4
|
|
max_output_tokens: 117964
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.6
|
|
output_price: 1.92
|
|
cache_read_price: 0.12
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5-turbo
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 1.2
|
|
output_price: 4.0
|
|
cache_read_price: 0.24
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.1
|
|
type: chat
|
|
max_input_tokens: 204800
|
|
input_price: 0.9646
|
|
output_price: 3.0316
|
|
cache_read_price: 0.1791
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.2
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.6496
|
|
output_price: 2.0416
|
|
cache_read_price: 0.1206
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.3794
|
|
output_price: 1.1924
|
|
cache_read_price: 0.0705
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3-flash
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.04
|
|
output_price: 0.5
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3-flash:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.06
|
|
output_price: 0.2
|
|
cache_read_price: 0.012
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3-flashx
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.37
|
|
output_price: 1.25
|
|
cache_read_price: 0.09
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3-prime
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.8
|
|
output_price: 8.8
|
|
cache_read_price: 0.56
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5.3:batch
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.45
|
|
output_price: 2.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: z-ai/glm-5v-turbo
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 1.2
|
|
output_price: 4.0
|
|
cache_read_price: 0.24
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~anthropic/claude-fable-latest
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 0.25
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~anthropic/claude-haiku-latest
|
|
type: chat
|
|
max_input_tokens: 200000
|
|
input_price: 1.0
|
|
output_price: 5.0
|
|
cache_read_price: 0.1
|
|
cache_write_price: 1.25
|
|
max_output_tokens: 64000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~anthropic/claude-opus-latest
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 4.0
|
|
output_price: 20.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 5.0
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~anthropic/claude-sonnet-latest
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~deepseek/deepseek-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.035
|
|
output_price: 0.29
|
|
cache_read_price: 0.001
|
|
max_output_tokens: 384000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~deepseek/deepseek-pro-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.2495
|
|
output_price: 0.7484
|
|
cache_read_price: 0.0079
|
|
max_output_tokens: 393216
|
|
supports_function_calling: true
|
|
- name: ~deepseek/deepseek-v4-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.021
|
|
output_price: 0.32
|
|
cache_read_price: 0.016
|
|
max_output_tokens: 943718
|
|
supports_function_calling: true
|
|
- name: ~google/gemini-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 3.75
|
|
cache_read_price: 0.075
|
|
cache_write_price: 0.0417
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~google/gemini-pro-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 0.375
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~moonshotai/kimi-latest
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.0301
|
|
output_price: 9.043
|
|
cache_read_price: 0.3
|
|
max_output_tokens: 943718
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~openai/gpt-astra-latest
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 10.0
|
|
output_price: 50.0
|
|
cache_read_price: 1.0
|
|
cache_write_price: 12.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~openai/gpt-luna-latest
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 0.1
|
|
output_price: 0.5
|
|
cache_read_price: 0.01
|
|
cache_write_price: 0.125
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~openai/gpt-mini-latest
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
input_price: 0.75
|
|
output_price: 4.5
|
|
cache_read_price: 0.075
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~openai/gpt-sol-latest
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 10.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~openai/gpt-terra-latest
|
|
type: chat
|
|
max_input_tokens: 1050000
|
|
input_price: 2.0
|
|
output_price: 12.0
|
|
cache_read_price: 0.2
|
|
cache_write_price: 2.5
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~x-ai/grok-latest
|
|
type: chat
|
|
max_input_tokens: 500000
|
|
input_price: 1.6
|
|
output_price: 4.8
|
|
cache_read_price: 0.4
|
|
max_output_tokens: 450000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~z-ai/glm-flash-latest
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.04
|
|
output_price: 0.5
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ~z-ai/glm-latest
|
|
type: chat
|
|
max_input_tokens: 1310720
|
|
input_price: 0.3794
|
|
output_price: 1.1924
|
|
cache_read_price: 0.0705
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- provider: github
|
|
models:
|
|
- name: gpt-5
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-5-mini
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-5-nano
|
|
type: chat
|
|
max_input_tokens: 400000
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4.1
|
|
type: chat
|
|
max_input_tokens: 1047576
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: gpt-4o
|
|
type: chat
|
|
max_input_tokens: 128000
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: text-embedding-3-large
|
|
type: embedding
|
|
max_tokens_per_chunk: 8191
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: text-embedding-3-small
|
|
type: embedding
|
|
max_tokens_per_chunk: 8191
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: llama-4-maverick-17b-128e-instruct-fp8
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
supports_vision: true
|
|
- name: llama-4-scout-17b-16e-instruct
|
|
type: chat
|
|
max_input_tokens: 327680
|
|
supports_vision: true
|
|
- name: llama-3.3-70b-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
- name: mistral-medium-2505
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: mistral-small-2503
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: codestral-2501
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
supports_function_calling: true
|
|
- name: cohere-embed-v3-english
|
|
type: embedding
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- name: cohere-embed-v3-multilingual
|
|
type: embedding
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 96
|
|
- name: deepseek-r1-0528
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
- name: deepseek-v3-0324
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
- name: mai-ds-r1
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
- name: phi-4
|
|
type: chat
|
|
max_input_tokens: 16384
|
|
- name: phi-4-mini-instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
- name: phi-4-reasoning
|
|
type: chat
|
|
max_input_tokens: 33792
|
|
- name: phi-4-mini-reasoning
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
- name: grok-3
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
- name: grok-3-mini
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
- provider: deepinfra
|
|
models:
|
|
- name: XiaomiMiMo/MiMo-V2.6-Flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.14
|
|
output_price: 0.28
|
|
cache_read_price: 0.0028
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: XiaomiMiMo/MiMo-V2.6-Pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.435
|
|
output_price: 0.87
|
|
cache_read_price: 0.0036
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V4.1-Flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.2
|
|
output_price: 0.6
|
|
cache_read_price: 0.006
|
|
max_output_tokens: 384000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- high
|
|
- xhigh
|
|
- max
|
|
- name: Qwen/Qwen3.8-Flash
|
|
type: chat
|
|
max_input_tokens: 1000000
|
|
input_price: 0.113
|
|
output_price: 0.382
|
|
cache_read_price: 0.0141
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-5.3-Flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.15
|
|
output_price: 0.5
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: deepseek-ai/DeepSeek-V4-Flash-Vision-Exp
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.44
|
|
output_price: 1.32
|
|
cache_read_price: 0.014
|
|
max_output_tokens: 384000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- high
|
|
- max
|
|
- name: Qwen/Qwen3.8-27B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 2.5
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- xhigh
|
|
- name: zai-org/GLM-5.3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.9
|
|
output_price: 4.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: Qwen/Qwen3.8-2.4T-A95B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 2.0
|
|
output_price: 6.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- xhigh
|
|
- name: deepseek-ai/DeepSeek-V4-Pro-0813
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.3
|
|
output_price: 2.6
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- high
|
|
- max
|
|
- name: Qwen/Qwen3.8-Max
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 1.65
|
|
output_price: 4.951
|
|
cache_read_price: 0.206
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V4-Flash-0731
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.06
|
|
output_price: 0.18
|
|
cache_read_price: 0.015
|
|
max_output_tokens: 384000
|
|
supports_function_calling: true
|
|
- name: thinkingmachines/Inkling-Small
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.45
|
|
output_price: 1.2
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/Kimi-K3
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 2.85
|
|
output_price: 14.25
|
|
cache_read_price: 0.285
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- high
|
|
- max
|
|
- name: thinkingmachines/Inkling
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.95
|
|
output_price: 4.05
|
|
cache_read_price: 0.16
|
|
max_output_tokens: 1048576
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: tencent/Hy3
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.13
|
|
output_price: 0.53
|
|
cache_read_price: 0.033
|
|
max_output_tokens: 128000
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-5.2
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.75
|
|
output_price: 2.4
|
|
cache_read_price: 0.14
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: moonshotai/Kimi-K2.7-Code
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.68
|
|
output_price: 3.4
|
|
cache_read_price: 0.136
|
|
max_output_tokens: 262144
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: MiniMaxAI/MiniMax-M3
|
|
type: chat
|
|
max_input_tokens: 524288
|
|
input_price: 0.28
|
|
output_price: 1.1
|
|
cache_read_price: 0.056
|
|
max_output_tokens: 512000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: stepfun-ai/Step-3.7-Flash
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 1.15
|
|
cache_read_price: 0.04
|
|
max_output_tokens: 256000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.7-Max
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 2.5
|
|
output_price: 7.5
|
|
cache_read_price: 0.5
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: nvidia/Nemotron-3-Nano-Omni-30B-A3B-Reasoning
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 0.8
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V4-Flash
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.09
|
|
output_price: 0.18
|
|
cache_read_price: 0.018
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: deepseek-ai/DeepSeek-V4-Pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.3
|
|
output_price: 2.6
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- xhigh
|
|
- name: Qwen/Qwen3.6-27B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.32
|
|
output_price: 3.2
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: XiaomiMiMo/MiMo-V2.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.14
|
|
output_price: 0.28
|
|
cache_read_price: 0.0028
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: XiaomiMiMo/MiMo-V2.5-Pro
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 1.0
|
|
output_price: 3.0
|
|
cache_read_price: 0.2
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: moonshotai/Kimi-K2.6
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.75
|
|
output_price: 3.5
|
|
cache_read_price: 0.15
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-5.1
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 1.05
|
|
output_price: 3.5
|
|
cache_read_price: 0.205
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-26B-A4B-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.07
|
|
output_price: 0.34
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-31B-it
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.13
|
|
output_price: 0.38
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-4-E4B-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.02
|
|
output_price: 0.1
|
|
max_output_tokens: 8192
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.6-35B-A3B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.95
|
|
max_output_tokens: 81920
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: MiniMaxAI/MiniMax-M2.7
|
|
type: chat
|
|
max_input_tokens: 196608
|
|
input_price: 0.25
|
|
output_price: 1.0
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.5-122B-A10B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.29
|
|
output_price: 2.4
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.5-27B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.26
|
|
output_price: 2.6
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.5-9B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.1
|
|
output_price: 0.15
|
|
max_output_tokens: 65536
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ByteDance/Seed-2.0-code
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- none
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: ByteDance/Seed-2.0-mini
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.1
|
|
output_price: 0.4
|
|
cache_read_price: 0.02
|
|
max_output_tokens: 32000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: ByteDance/Seed-2.0-pro
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 0.5
|
|
output_price: 3.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 128000
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: MiniMaxAI/MiniMax-M2.5
|
|
type: chat
|
|
max_input_tokens: 196608
|
|
input_price: 0.15
|
|
output_price: 1.15
|
|
cache_read_price: 0.03
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-5
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.6
|
|
output_price: 2.08
|
|
cache_read_price: 0.12
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.5-35B-A3B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.14
|
|
output_price: 1.0
|
|
cache_read_price: 0.05
|
|
max_output_tokens: 81920
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3.5-397B-A17B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.45
|
|
output_price: 3.0
|
|
cache_read_price: 0.22
|
|
max_output_tokens: 81920
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: moonshotai/Kimi-K2.5
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.45
|
|
output_price: 2.25
|
|
cache_read_price: 0.07
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-4.7-Flash
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.06
|
|
output_price: 0.4
|
|
cache_read_price: 0.01
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-4.7
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.4
|
|
output_price: 1.75
|
|
cache_read_price: 0.08
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: nvidia/Nemotron-3-Nano-30B-A3B
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.05
|
|
output_price: 0.2
|
|
cache_read_price: 0.025
|
|
max_output_tokens: 262144
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V3.2
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.26
|
|
output_price: 0.38
|
|
cache_read_price: 0.13
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-4.6
|
|
type: chat
|
|
max_input_tokens: 202752
|
|
input_price: 0.5
|
|
output_price: 2.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-Max
|
|
type: chat
|
|
max_input_tokens: 256000
|
|
input_price: 1.2
|
|
output_price: 6.0
|
|
cache_read_price: 0.24
|
|
max_output_tokens: 65536
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-VL-235B-A22B-Instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.2
|
|
output_price: 0.88
|
|
cache_read_price: 0.11
|
|
max_output_tokens: 32768
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-Next-80B-A3B-Instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.09
|
|
output_price: 1.1
|
|
max_output_tokens: 32768
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V3.1
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.25
|
|
output_price: 0.95
|
|
cache_read_price: 0.13
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: openai/gpt-oss-120b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.037
|
|
output_price: 0.17
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: openai/gpt-oss-20b
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.03
|
|
output_price: 0.14
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
reasoning_levels:
|
|
- low
|
|
- medium
|
|
- high
|
|
- name: nvidia/Llama-3.3-Nemotron-Super-49B-v1.5
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 0.4
|
|
max_output_tokens: 131072
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.3
|
|
output_price: 1.0
|
|
cache_read_price: 0.1
|
|
max_output_tokens: 66536
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-235B-A22B-Instruct-2507
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.09
|
|
output_price: 0.55
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-R1-0528
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.5
|
|
output_price: 2.15
|
|
cache_read_price: 0.35
|
|
max_output_tokens: 64000
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-30B-A3B
|
|
type: chat
|
|
max_input_tokens: 40960
|
|
input_price: 0.12
|
|
output_price: 0.5
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
|
|
type: chat
|
|
max_input_tokens: 1048576
|
|
input_price: 0.2
|
|
output_price: 0.8
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
- name: meta-llama/Llama-4-Scout-17B-16E-Instruct
|
|
type: chat
|
|
max_input_tokens: 327680
|
|
input_price: 0.1
|
|
output_price: 0.3
|
|
max_output_tokens: 16384
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-32B
|
|
type: chat
|
|
max_input_tokens: 40960
|
|
input_price: 0.08
|
|
output_price: 0.28
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V3-0324
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.24
|
|
output_price: 0.9
|
|
cache_read_price: 0.135
|
|
max_output_tokens: 163840
|
|
supports_function_calling: true
|
|
- name: google/gemma-3-12b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.15
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-3-27b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.1
|
|
output_price: 0.2
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: google/gemma-3-4b-it
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.05
|
|
output_price: 0.1
|
|
max_output_tokens: 131072
|
|
supports_vision: true
|
|
supports_function_calling: true
|
|
- name: deepseek-ai/DeepSeek-V3
|
|
type: chat
|
|
max_input_tokens: 163840
|
|
input_price: 0.32
|
|
output_price: 0.89
|
|
max_output_tokens: 8192
|
|
supports_function_calling: true
|
|
- name: meta-llama/Llama-3.3-70B-Instruct-Turbo
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.1
|
|
output_price: 0.32
|
|
max_output_tokens: 16384
|
|
supports_function_calling: true
|
|
- name: BAAI/bge-large-en-v1.5
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- name: BAAI/bge-m3
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: intfloat/e5-large-v2
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- name: intfloat/multilingual-e5-large
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- name: thenlper/gte-large
|
|
type: embedding
|
|
input_price: 0.01
|
|
max_tokens_per_chunk: 512
|
|
default_chunk_size: 1000
|
|
max_batch_size: 100
|
|
- name: Qwen/Qwen3-Max-Thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 1.2
|
|
output_price: 6.0
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-Next-80B-A3B-Thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.14
|
|
output_price: 1.4
|
|
- name: Qwen/Qwen3-235B-A22B-Thinking-2507
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.13
|
|
output_price: 0.6
|
|
- name: Qwen/Qwen3-Coder-480B-A35B-Instruct
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.4
|
|
output_price: 1.6
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-Coder-30B-A3B-Instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.07
|
|
output_price: 0.27
|
|
supports_function_calling: true
|
|
- name: Qwen/Qwen3-VL-8B-Instruct
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.18
|
|
output_price: 0.69
|
|
supports_vision: true
|
|
- name: mistralai/Mistral-Small-3.2-24B-Instruct-2506
|
|
type: chat
|
|
max_input_tokens: 32768
|
|
input_price: 0.06
|
|
output_price: 0.12
|
|
- name: moonshotai/Kimi-K2-Instruct-0905
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.5
|
|
output_price: 2.0
|
|
supports_function_calling: true
|
|
- name: moonshotai/Kimi-K2-Thinking
|
|
type: chat
|
|
max_input_tokens: 262144
|
|
input_price: 0.55
|
|
output_price: 2.5
|
|
supports_function_calling: true
|
|
- name: MiniMaxAI/MiniMax-M2.1
|
|
type: chat
|
|
max_input_tokens: 196608
|
|
input_price: 0.27
|
|
output_price: 0.95
|
|
supports_function_calling: true
|
|
- name: zai-org/GLM-4.6V
|
|
type: chat
|
|
max_input_tokens: 131072
|
|
input_price: 0.3
|
|
output_price: 0.9
|
|
supports_vision: true
|
|
- provider: jina
|
|
models:
|
|
- name: jina-embeddings-v3
|
|
type: embedding
|
|
input_price: 0.0
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 2000
|
|
max_batch_size: 100
|
|
- name: jina-clip-v2
|
|
type: embedding
|
|
input_price: 0.0
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 1500
|
|
max_batch_size: 100
|
|
- name: jina-colbert-v2
|
|
type: embedding
|
|
input_price: 0.0
|
|
max_tokens_per_chunk: 8192
|
|
default_chunk_size: 1500
|
|
max_batch_size: 100
|
|
- name: jina-reranker-v2-base-multilingual
|
|
type: reranker
|
|
max_input_tokens: 8192
|
|
input_price: 0.0
|
|
- name: jina-colbert-v2
|
|
type: reranker
|
|
max_input_tokens: 8192
|
|
input_price: 0.0
|
|
- provider: voyageai
|
|
models:
|
|
- name: voyage-3-large
|
|
type: embedding
|
|
max_input_tokens: 120000
|
|
input_price: 0.18
|
|
max_tokens_per_chunk: 32000
|
|
default_chunk_size: 2000
|
|
max_batch_size: 128
|
|
- name: voyage-3
|
|
type: embedding
|
|
max_input_tokens: 320000
|
|
input_price: 0.06
|
|
max_tokens_per_chunk: 32000
|
|
default_chunk_size: 2000
|
|
max_batch_size: 128
|
|
- name: voyage-3-lite
|
|
type: embedding
|
|
max_input_tokens: 1000000
|
|
input_price: 0.02
|
|
max_tokens_per_chunk: 32000
|
|
default_chunk_size: 1000
|
|
max_batch_size: 128
|
|
- name: rerank-2
|
|
type: reranker
|
|
max_input_tokens: 16000
|
|
input_price: 0.05
|
|
- name: rerank-2-lite
|
|
type: reranker
|
|
max_input_tokens: 8000
|
|
input_price: 0.02
|