From 0dc9dd91c399762579accfd34d517df7ed40fdb9 Mon Sep 17 00:00:00 2001 From: Alex Clarke Date: Wed, 16 Sep 2026 12:51:49 -0600 Subject: [PATCH] chore(TASK-043): regenerate model catalog Add responses sub-patches to the six o-series quirks entries (temperature and top_p removal; reasoning.effort high for the -high aliases) and regenerate models.yaml from live models.dev/openrouter data, picking up expected upstream price and model drift. --- models.yaml | 88 ++++++++++++++++++++++++++++++++++++++--------------- quirks.yaml | 30 ++++++++++++++++++ 2 files changed, 93 insertions(+), 25 deletions(-) diff --git a/models.yaml b/models.yaml index a002557..b2e1673 100644 --- a/models.yaml +++ b/models.yaml @@ -351,6 +351,10 @@ 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 @@ -370,6 +374,10 @@ 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 @@ -429,6 +437,10 @@ 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: @@ -540,6 +552,12 @@ 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 @@ -556,6 +574,12 @@ 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 @@ -571,6 +595,12 @@ 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 @@ -6947,9 +6977,9 @@ - name: deepseek/deepseek-v4-flash type: chat max_input_tokens: 1048576 - input_price: 0.0886 - output_price: 0.1772 - cache_read_price: 0.0177 + input_price: 0.084 + output_price: 0.168 + cache_read_price: 0.0168 max_output_tokens: 384000 supports_function_calling: true - name: deepseek/deepseek-v4-flash-0731 @@ -6997,10 +7027,10 @@ - name: deepseek/deepseek-v4-pro-0813 type: chat max_input_tokens: 1048576 - input_price: 0.9834 - output_price: 2.9502 - cache_read_price: 0.0328 - max_output_tokens: 384000 + input_price: 0.5795 + output_price: 1.7384 + cache_read_price: 0.0184 + max_output_tokens: 393216 supports_function_calling: true - name: deepseek/deepseek-v4-pro-0813:batch type: chat @@ -8022,9 +8052,9 @@ - name: moonshotai/kimi-k3 type: chat max_input_tokens: 1048576 - input_price: 2.6481 - output_price: 13.2827 - cache_read_price: 0.3026 + input_price: 3.0 + output_price: 15.0 + cache_read_price: 0.3 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -9405,9 +9435,9 @@ - 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 + input_price: 0.13 + output_price: 0.52 + max_output_tokens: 32768 supports_vision: true supports_function_calling: true - name: qwen/qwen3-vl-30b-a3b-thinking @@ -9716,6 +9746,14 @@ input_price: 0.65 output_price: 0.75 max_output_tokens: 16384 + - name: stealth/union-alpha + type: chat + max_input_tokens: 262144 + input_price: 0.0 + output_price: 0.0 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true - name: stepfun/step-3.5-flash type: chat max_input_tokens: 262144 @@ -9759,9 +9797,9 @@ - name: tencent/hy3 type: chat max_input_tokens: 262144 - input_price: 0.132 - output_price: 0.528 - cache_read_price: 0.033 + input_price: 0.0825 + output_price: 0.33 + cache_read_price: 0.0206 max_output_tokens: 128000 supports_function_calling: true - name: tencent/hy3-preview @@ -10037,7 +10075,7 @@ input_price: 1.4 output_price: 4.4 cache_read_price: 0.14 - max_output_tokens: 128000 + max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-5.2:batch type: chat @@ -10142,16 +10180,16 @@ input_price: 0.15 output_price: 0.6 cache_read_price: 0.015 - max_output_tokens: 943718 + max_output_tokens: 393216 supports_vision: true supports_function_calling: true - name: ~deepseek/deepseek-pro-latest type: chat max_input_tokens: 1048576 - input_price: 0.66 - output_price: 1.98 - cache_read_price: 0.022 - max_output_tokens: 384000 + input_price: 0.5795 + output_price: 1.7384 + cache_read_price: 0.0184 + max_output_tokens: 393216 supports_function_calling: true - name: ~deepseek/deepseek-v4-flash-latest type: chat @@ -10184,9 +10222,9 @@ - name: ~moonshotai/kimi-latest type: chat max_input_tokens: 1048576 - input_price: 2.1 - output_price: 10.95 - cache_read_price: 0.23 + input_price: 2.0 + output_price: 11.2 + cache_read_price: 0.232 max_output_tokens: 943718 supports_vision: true supports_function_calling: true diff --git a/quirks.yaml b/quirks.yaml index 3db303c..fdc65d8 100644 --- a/quirks.yaml +++ b/quirks.yaml @@ -51,6 +51,10 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null - match: "o3" system_prompt_prefix: Formatting re-enabled patch: @@ -58,6 +62,10 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null - match: "o3-mini" system_prompt_prefix: Formatting re-enabled patch: @@ -65,6 +73,10 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null models: - name: text-embedding-3-large type: embedding @@ -94,6 +106,12 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null + reasoning: + effort: high - name: o3-high real_name: o3 max_input_tokens: 200000 @@ -108,6 +126,12 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null + reasoning: + effort: high - name: o3-mini-high max_output_tokens: 100000 real_name: o3-mini @@ -123,6 +147,12 @@ max_tokens: null temperature: null top_p: null + responses: + body: + temperature: null + top_p: null + reasoning: + effort: high - name: chat-latest max_input_tokens: 400000 max_output_tokens: 128000