diff options
Diffstat (limited to 'models.yaml')
| -rw-r--r-- | models.yaml | 80 |
1 files changed, 54 insertions, 26 deletions
diff --git a/models.yaml b/models.yaml index 5388cb4..20d810f 100644 --- a/models.yaml +++ b/models.yaml @@ -463,6 +463,16 @@ input_price: 3 output_price: 15 supports_function_calling: true + - name: grok-4-fast-non-reasoning + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true + - name: grok-4-fast-reasoning + max_input_tokens: 2000000 + input_price: 0.2 + output_price: 0.5 + supports_function_calling: true - name: grok-code-fast max_input_tokens: 256000 input_price: 0.2 @@ -473,21 +483,11 @@ input_price: 3 output_price: 15 supports_function_calling: true - - name: grok-3-fast - max_input_tokens: 131072 - input_price: 5 - output_price: 25 - supports_function_calling: true - name: grok-3-mini max_input_tokens: 131072 input_price: 0.3 output_price: 0.5 supports_function_calling: true - - name: grok-3-mini-fast - max_input_tokens: 131072 - input_price: 0.6 - output_price: 4 - supports_function_calling: true # Links: # - https://docs.perplexity.ai/getting-started/models @@ -1045,6 +1045,15 @@ input_price: 1.4 output_price: 5.6 supports_function_calling: true + - name: qwen3-next-80b-a3b-instruct + max_input_tokens: 131072 + input_price: 0.14 + output_price: 0.56 + supports_function_calling: true + - name: qwen3-next-80b-a3b-thinking + max_input_tokens: 131072 + input_price: 0.14 + output_price: 1.4 - name: qwen3-235b-a22b-instruct-2507 max_input_tokens: 131072 input_price: 0.28 @@ -1251,7 +1260,7 @@ input_price: 0.112 # Links: -# - https://platform.minimaxi.com/document/Price +# - https://platform.minimaxi.com/document/pricing # - https://platform.minimaxi.com/document/ChatCompletion%20v2 - provider: minimax models: @@ -1604,6 +1613,15 @@ input_price: 1.2 output_price: 6 supports_function_calling: true + - name: qwen/qwen3-next-80b-a3b-instruct + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.8 + supports_function_calling: true + - name: qwen/qwen3-next-80b-a3b-thinking + max_input_tokens: 262144 + input_price: 0.1 + output_price: 0.8 - name: qwen/qwen3-235b-a22b-2507 max_input_tokens: 262144 input_price: 0.12 @@ -1621,10 +1639,15 @@ max_input_tokens: 262144 input_price: 0.071 output_price: 0.285 - - name: qwen/qwen3-coder - max_input_tokens: 262144 + - name: qwen/qwen3-coder-plus + max_input_tokens: 128000 + input_price: 1 + output_price: 5 + supports_function_calling: true + - name: qwen/qwen3-coder-flash + max_input_tokens: 128000 input_price: 0.3 - output_price: 1.2 + output_price: 1.5 supports_function_calling: true - name: qwen/qwen3-coder-30b-a3b-instruct max_input_tokens: 262144 @@ -1660,15 +1683,11 @@ input_price: 3 output_price: 15 supports_function_calling: true - - name: x-ai/grok-3 - max_input_tokens: 131072 - input_price: 3 - output_price: 15 + - name: x-ai/grok-code-fast-1 + max_input_tokens: 256000 + input_price: 0.2 + output_price: 1.5 supports_function_calling: true - - name: x-ai/grok-3-mini - max_input_tokens: 131072 - input_price: 0.3 - output_price: 0.5 - name: amazon/nova-pro-v1 max_input_tokens: 300000 max_output_tokens: 5120 @@ -1932,6 +1951,15 @@ max_input_tokens: 131072 input_price: 0.23 output_price: 0.40 + - name: Qwen/Qwen3-Next-80B-A3B-Instruct + max_input_tokens: 262144 + input_price: 0.14 + output_price: 1.4 + supports_function_calling: true + - name: Qwen/Qwen3-Next-80B-A3B-Thinking + max_input_tokens: 262144 + input_price: 0.14 + output_price: 1.4 - name: Qwen/Qwen3-235B-A22B-Instruct-2507 max_input_tokens: 131072 input_price: 0.13 @@ -1991,10 +2019,10 @@ max_input_tokens: 131072 input_price: 0.07 output_price: 0.28 - - name: moonshotai/Kimi-K2-Instruct - max_input_tokens: 131072 - input_price: 0.55 - output_price: 2.2 + - name: moonshotai/Kimi-K2-Instruct-0905 + max_input_tokens: 262144 + input_price: 0.5 + output_price: 2.0 supports_function_calling: true - name: zai-org/GLM-4.5 max_input_tokens: 131072 |