diff --git a/models.yaml b/models.yaml index 450d057..efafb1b 100644 --- a/models.yaml +++ b/models.yaml @@ -5513,6 +5513,7 @@ 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 @@ -6018,12 +6019,26 @@ 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: 0.075 - output_price: 0.25 - cache_read_price: 0.015 + 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 @@ -7018,9 +7033,9 @@ - name: deepseek/deepseek-v4-flash-0731 type: chat max_input_tokens: 1310720 - input_price: 0.06 - output_price: 0.12 - cache_read_price: 0.012 + input_price: 0.04 + output_price: 0.16 + cache_read_price: 0.016 max_output_tokens: 943718 supports_function_calling: true - name: deepseek/deepseek-v4-flash-0731:batch @@ -7031,20 +7046,13 @@ cache_read_price: 0.0035 max_output_tokens: 943718 supports_function_calling: true - - name: deepseek/deepseek-v4-flash-0731:free - type: chat - max_input_tokens: 1048576 - input_price: 0.0 - output_price: 0.0 - max_output_tokens: 393216 - supports_function_calling: true - name: deepseek/deepseek-v4-flash-vision-exp type: chat max_input_tokens: 1048576 - input_price: 0.2156 - output_price: 0.6468 - cache_read_price: 0.0069 - max_output_tokens: 262144 + 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-flash-vision-exp:batch @@ -7059,10 +7067,10 @@ - name: deepseek/deepseek-v4-pro type: chat max_input_tokens: 1048576 - input_price: 1.6 - output_price: 3.2 - cache_read_price: 0.135 - max_output_tokens: 393216 + input_price: 0.9553 + output_price: 1.9105 + cache_read_price: 0.0796 + max_output_tokens: 384000 supports_function_calling: true - name: deepseek/deepseek-v4-pro-0813 type: chat @@ -7512,9 +7520,9 @@ - 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 + input_price: 0.1 + output_price: 0.15 + cache_read_price: 0.05 max_output_tokens: 117964 supports_function_calling: true - name: inception/mercury-2 @@ -7634,9 +7642,9 @@ - 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 + input_price: 0.72 + output_price: 0.72 + max_output_tokens: 8192 supports_function_calling: true - name: meta-llama/llama-3.1-8b-instruct type: chat @@ -7668,8 +7676,8 @@ - name: meta-llama/llama-4-maverick type: chat max_input_tokens: 1048576 - input_price: 0.1875 - output_price: 0.6525 + input_price: 0.2 + output_price: 0.8 max_output_tokens: 16384 supports_vision: true supports_function_calling: true @@ -7692,9 +7700,9 @@ type: chat max_input_tokens: 131072 input_price: 0.3 - output_price: 1.1 + output_price: 1.2 cache_read_price: 0.04 - max_output_tokens: 117964 + max_output_tokens: 16384 supports_vision: true supports_function_calling: true - name: meta/muse-glimmer-30b:batch @@ -8007,6 +8015,7 @@ 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 @@ -8083,9 +8092,9 @@ - name: moonshotai/kimi-k3 type: chat max_input_tokens: 1048576 - input_price: 2.1 - output_price: 10.95 - cache_read_price: 0.23 + input_price: 1.7 + output_price: 8.5 + cache_read_price: 0.17 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -8176,10 +8185,10 @@ - name: nvidia/nemotron-3-ultra-550b-a55b type: chat max_input_tokens: 262144 - input_price: 0.625 - output_price: 3.125 - cache_read_price: 0.1875 - max_output_tokens: 32768 + 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 @@ -8205,10 +8214,10 @@ - name: nvidia/nemotron-3.5-lightning type: chat max_input_tokens: 262144 - input_price: 0.08 + input_price: 0.07 output_price: 0.2 cache_read_price: 0.04 - max_output_tokens: 131072 + max_output_tokens: 235929 supports_function_calling: true - name: nvidia/nemotron-3.5-lightning:free type: chat @@ -9267,6 +9276,14 @@ 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 @@ -9522,9 +9539,10 @@ - name: qwen/qwen3.5-35b-a3b type: chat max_input_tokens: 262144 - input_price: 0.1625 - output_price: 1.3 - max_output_tokens: 65536 + 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 @@ -9541,7 +9559,7 @@ max_input_tokens: 262144 input_price: 0.1 output_price: 0.15 - max_output_tokens: 235929 + max_output_tokens: 32768 supports_vision: true supports_function_calling: true - name: qwen/qwen3.5-9b:batch @@ -9589,8 +9607,8 @@ - name: qwen/qwen3.6-35b-a3b type: chat max_input_tokens: 262144 - input_price: 0.1 - output_price: 0.9 + input_price: 0.15 + output_price: 1.0 cache_read_price: 0.05 max_output_tokens: 235929 supports_vision: true @@ -9669,9 +9687,9 @@ - name: qwen/qwen3.8-27b type: chat max_input_tokens: 1000000 - input_price: 0.214 - output_price: 2.55 - cache_read_price: 0.15 + input_price: 0.2 + output_price: 2.5 + cache_read_price: 0.05 max_output_tokens: 131072 supports_vision: true supports_function_calling: true @@ -10112,10 +10130,10 @@ - name: z-ai/glm-5.2 type: chat max_input_tokens: 1048576 - input_price: 0.5625 - output_price: 1.8 - cache_read_price: 0.105 - max_output_tokens: 163840 + 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-5.2:batch type: chat @@ -10134,10 +10152,10 @@ - name: z-ai/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: 943717 + input_price: 0.91 + output_price: 2.86 + cache_read_price: 0.169 + max_output_tokens: 131072 supports_function_calling: true - name: z-ai/glm-5.3-flash type: chat @@ -10157,6 +10175,15 @@ max_output_tokens: 943718 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: 0.075 + max_output_tokens: 131072 + supports_vision: true + supports_function_calling: true - name: z-ai/glm-5.3:batch type: chat max_input_tokens: 1048576 @@ -10217,9 +10244,9 @@ - name: ~deepseek/deepseek-flash-latest type: chat max_input_tokens: 1048576 - input_price: 0.15 - output_price: 0.6 - cache_read_price: 0.015 + input_price: 0.12 + output_price: 0.48 + cache_read_price: 0.0036 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -10234,9 +10261,9 @@ - name: ~deepseek/deepseek-v4-flash-latest type: chat max_input_tokens: 1310720 - input_price: 0.0558 - output_price: 0.1767 - cache_read_price: 0.0088 + input_price: 0.04 + output_price: 0.16 + cache_read_price: 0.016 max_output_tokens: 943718 supports_function_calling: true - name: ~google/gemini-flash-latest @@ -10262,9 +10289,9 @@ - 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: 1.7 + output_price: 8.5 + cache_read_price: 0.17 max_output_tokens: 943718 supports_vision: true supports_function_calling: true @@ -10332,16 +10359,16 @@ input_price: 0.075 output_price: 0.25 cache_read_price: 0.015 - max_output_tokens: 131072 + max_output_tokens: 943718 supports_vision: true supports_function_calling: true - name: ~z-ai/glm-latest type: chat max_input_tokens: 1310720 - input_price: 0.8775 - output_price: 2.97 - cache_read_price: 0.1755 - max_output_tokens: 235929 + input_price: 0.7735 + output_price: 2.431 + cache_read_price: 0.1271 + max_output_tokens: 943718 supports_function_calling: true - provider: github models: