diff options
| -rw-r--r-- | models.yaml | 587 |
1 files changed, 114 insertions, 473 deletions
diff --git a/models.yaml b/models.yaml index 3f05eaa..2c70877 100644 --- a/models.yaml +++ b/models.yaml @@ -3,18 +3,11 @@ # - https://platform.openai.com/docs/api-reference/chat - provider: openai models: - - name: gpt-5.1 + - name: gpt-5.2 max_input_tokens: 400000 max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - - name: gpt-5.1-chat-latest - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 + input_price: 1.75 + output_price: 14 supports_vision: true supports_function_calling: true - name: gpt-5 @@ -24,13 +17,6 @@ output_price: 10 supports_vision: true supports_function_calling: true - - name: gpt-5-chat-latest - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - name: gpt-5-mini max_input_tokens: 400000 max_output_tokens: 128000 @@ -52,20 +38,6 @@ output_price: 8 supports_vision: true supports_function_calling: true - - name: gpt-4.1-mini - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.4 - output_price: 1.6 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1-nano - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.1 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - name: gpt-4o max_input_tokens: 128000 max_output_tokens: 16384 @@ -73,91 +45,6 @@ output_price: 10 supports_vision: true supports_function_calling: true - - name: gpt-4o-mini - max_input_tokens: 128000 - max_output_tokens: 16384 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - supports_function_calling: true - - name: o4-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o4-mini-high - real_name: o4-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-high - real_name: o3 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-mini-high - real_name: o3-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - name: gpt-4-turbo max_input_tokens: 128000 max_output_tokens: 4096 @@ -211,6 +98,14 @@ output_price: 0 supports_vision: true supports_function_calling: true + - name: gemini-3-pro-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + - name: gemini-3-flash-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true - name: gemini-2.0-flash max_input_tokens: 1048576 max_output_tokens: 8192 @@ -400,6 +295,12 @@ # - https://docs.mistral.ai/api/ - provider: mistral models: + - name: mistral-large-latest + max_output_tokens: 262144 + input_price: 0.5 + output_price: 1.5 + supports_function_calling: true + supports_vision: true - name: mistral-medium-latest max_input_tokens: 131072 input_price: 0.4 @@ -413,28 +314,33 @@ supports_function_calling: true supports_vision: true - name: magistral-medium-latest - max_input_tokens: 40960 + max_input_tokens: 131072 input_price: 2 output_price: 5 - name: magistral-small-latest - max_input_tokens: 40960 + max_input_tokens: 131072 input_price: 0.5 output_price: 1.5 - name: devstral-medium-latest - max_input_tokens: 256000 + max_input_tokens: 262144 input_price: 0.4 output_price: 2 supports_function_calling: true - name: devstral-small-latest - max_input_tokens: 256000 + max_input_tokens: 262144 input_price: 0.1 output_price: 0.3 supports_function_calling: true - name: codestral-latest - max_input_tokens: 256000 + max_input_tokens: 262144 input_price: 0.3 output_price: 0.9 supports_function_calling: true + - name: ministral-14b-latest + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.2 + supports_function_calling: true - name: mistral-embed type: embedding max_input_tokens: 8092 @@ -520,36 +426,21 @@ # - https://docs.x.ai/docs/api-reference#chat-completions - provider: xai models: - - name: grok-4 - max_input_tokens: 256000 - input_price: 3 - output_price: 15 - supports_function_calling: true - - name: grok-4-fast-non-reasoning + - name: grok-4-1-fast-non-reasoning max_input_tokens: 2000000 input_price: 0.2 output_price: 0.5 supports_function_calling: true - - name: grok-4-fast-reasoning + - name: grok-4-1-fast-reasoning max_input_tokens: 2000000 input_price: 0.2 output_price: 0.5 supports_function_calling: true - - name: grok-code-fast + - name: grok-code-fast-1 max_input_tokens: 256000 input_price: 0.2 output_price: 1.5 supports_function_calling: true - - name: grok-3 - max_input_tokens: 131072 - input_price: 3 - output_price: 15 - supports_function_calling: true - - name: grok-3-mini - max_input_tokens: 131072 - input_price: 0.3 - output_price: 0.5 - supports_function_calling: true # Links: # - https://docs.perplexity.ai/getting-started/models @@ -568,10 +459,6 @@ max_input_tokens: 128000 input_price: 2 output_price: 8 - - name: sonar-reasoning - max_input_tokens: 128000 - input_price: 1 - output_price: 5 - name: sonar-deep-research max_input_tokens: 128000 input_price: 2 @@ -654,6 +541,14 @@ output_price: 0.4 supports_vision: true supports_function_calling: true + - name: gemini-3-pro-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true + - name: gemini-3-flash-preview + max_input_tokens: 1048576 + supports_vision: true + supports_function_calling: true - name: gemini-2.0-flash-001 max_input_tokens: 1048576 max_output_tokens: 8192 @@ -814,16 +709,6 @@ output_price: 4 supports_vision: true supports_function_calling: true - - name: mistral-small-2503 - max_input_tokens: 32000 - input_price: 0.1 - output_price: 0.3 - supports_function_calling: true - - name: codestral-2501 - max_input_tokens: 256000 - input_price: 0.3 - output_price: 0.9 - supports_function_calling: true - name: text-embedding-005 type: embedding max_input_tokens: 20000 @@ -1246,27 +1131,20 @@ # - https://cloud.tencent.com/document/product/1729/111007 - provider: hunyuan models: - - name: hunyuan-turbos-latest - max_input_tokens: 28000 + - name: hunyuan-2.0-instruct-20251111 + max_input_tokens: 131072 input_price: 0.112 output_price: 0.28 supports_function_calling: true - - name: hunyuan-t1-latest - max_input_tokens: 28000 + - name: hunyuan-2.0-thinking-20251109 + max_input_tokens: 131072 input_price: 0.14 output_price: 0.56 - - name: hunyuan-lite - max_input_tokens: 250000 - input_price: 0 - output_price: 0 supports_function_calling: true - - name: hunyuan-turbos-vision - max_input_tokens: 6144 + - name: hunyuan-vision-1.5-instruct + max_input_tokens: 24576 input_price: 0.42 - output_price: 0.84 - supports_vision: true - - name: hunyuan-t1-vision - max_input_tokens: 24000 + output_price: 1.26 supports_vision: true - name: hunyuan-embedding type: embedding @@ -1325,54 +1203,27 @@ # - https://open.bigmodel.cn/dev/api#glm-4 - provider: zhipuai models: - - name: glm-4.6 + - name: glm-4.7 max_input_tokens: 202752 - input_price: 0.28 - output_price: 1.12 - supports_function_calling: true - - name: glm-4.5 - max_input_tokens: 131072 - input_price: 0.28 - output_price: 1.12 - - name: glm-4.5-x - max_input_tokens: 131072 - input_price: 1.12 - output_price: 4.48 + input_price: 0.56 + output_price: 2.24 supports_function_calling: true - - name: glm-4.5-air - max_input_tokens: 131072 - input_price: 0.084 - output_price: 0.56 - - name: glm-4.5-airx - max_input_tokens: 131072 + + - name: glm-4.7:instruct + real_name: glm-4.7 + max_input_tokens: 202752 input_price: 0.56 output_price: 2.24 supports_function_calling: true - - name: glm-4.5-flash - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - - name: glm-4.5v + patch: + body: + thinking: + type: disabled + - name: glm-4.6v max_input_tokens: 65536 - input_price: 0.56 - output_price: 1.68 + input_price: 0.28 + output_price: 0.84 supports_vision: true - - name: glm-z1-air - max_input_tokens: 131072 - input_price: 0.07 - output_price: 0.07 - - name: glm-z1-airx - max_input_tokens: 131072 - input_price: 0.7 - output_price: 0.7 - - name: glm-z1-flashx - max_input_tokens: 131072 - input_price: 0.014 - output_price: 0.014 - - name: glm-z1-flash - max_input_tokens: 131072 - input_price: 0 - output_price: 0 - name: embedding-3 type: embedding max_input_tokens: 8192 @@ -1389,29 +1240,27 @@ # - https://platform.minimaxi.com/document/ChatCompletion%20v2 - provider: minimax models: - - name: minimax-m2 + - name: minimax-m2.1 max_input_tokens: 204800 input_price: 0.294 output_price: 1.176 supports_function_calling: true + - name: minimax-m2.1-lightning + max_input_tokens: 204800 + input_price: 0.294 + output_price: 2.352 + supports_function_calling: true # Links: # - https://openrouter.ai/models # - https://openrouter.ai/docs/api-reference/chat-completion - provider: openrouter models: - - name: openai/gpt-5.1 + - name: openai/gpt-5.2 max_input_tokens: 400000 max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-5.1-chat - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 + input_price: 1.75 + output_price: 14 supports_vision: true supports_function_calling: true - name: openai/gpt-5 @@ -1421,13 +1270,6 @@ output_price: 10 supports_vision: true supports_function_calling: true - - name: openai/gpt-5-chat - max_input_tokens: 400000 - max_output_tokens: 128000 - input_price: 1.25 - output_price: 10 - supports_vision: true - supports_function_calling: true - name: openai/gpt-5-mini max_input_tokens: 400000 max_output_tokens: 128000 @@ -1449,104 +1291,12 @@ output_price: 8 supports_vision: true supports_function_calling: true - - name: openai/gpt-4.1-mini - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.4 - output_price: 1.6 - supports_vision: true - supports_function_calling: true - - name: openai/gpt-4.1-nano - max_input_tokens: 1047576 - max_output_tokens: 32768 - input_price: 0.1 - output_price: 0.4 - supports_vision: true - supports_function_calling: true - name: openai/gpt-4o max_input_tokens: 128000 input_price: 2.5 output_price: 10 supports_vision: true supports_function_calling: true - - name: openai/gpt-4o-mini - max_input_tokens: 128000 - input_price: 0.15 - output_price: 0.6 - supports_vision: true - supports_function_calling: true - - name: openai/o4-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: openai/o4-mini-high - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: openai/o3 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: openai/o3-high - real_name: openai/o3 - max_input_tokens: 200000 - input_price: 2 - output_price: 8 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - temperature: null - top_p: null - - name: openai/o3-mini - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - temperature: null - top_p: null - - name: openai/o3-mini-high - max_input_tokens: 200000 - input_price: 1.1 - output_price: 4.4 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - temperature: null - top_p: null - name: openai/gpt-oss-120b max_input_tokens: 131072 input_price: 0.09 @@ -1662,6 +1412,11 @@ max_input_tokens: 131072 input_price: 0.12 output_price: 0.3 + - name: mistralai/mistral-large-2512 + max_input_tokens: 262144 + input_price: 0.5 + output_price: 1.5 + supports_function_calling: true - name: mistralai/mistral-medium-3.1 max_input_tokens: 131072 input_price: 0.4 @@ -1673,22 +1428,10 @@ input_price: 0.1 output_price: 0.3 supports_vision: true - - name: mistralai/magistral-medium-2506 - max_input_tokens: 40960 - input_price: 2 - output_price: 5 - - name: mistralai/magistral-medium-2506:thinking - max_input_tokens: 40960 - input_price: 2 - output_price: 5 - - name: mistralai/magistral-small-2506 - max_input_tokens: 40960 + - name: mistralai/devstral-2512 + max_input_tokens: 262144 input_price: 0.5 - output_price: 1.5 - - name: mistralai/devstral-medium - max_input_tokens: 131072 - input_price: 0.4 - output_price: 2 + output_price: 0.22 supports_function_calling: true - name: mistralai/devstral-small max_input_tokens: 131072 @@ -1700,6 +1443,11 @@ input_price: 0.3 output_price: 0.9 supports_function_calling: true + - name: mistralai/ministral-14b-2512 + max_input_tokens: 262144 + input_price: 0.2 + output_price: 0.2 + supports_function_calling: true - name: ai21/jamba-large-1.7 max_input_tokens: 256000 input_price: 2 @@ -1720,25 +1468,10 @@ max_output_tokens: 4096 input_price: 0.0375 output_price: 0.15 - - name: deepseek/deepseek-v3.2-exp - max_input_tokens: 163840 - input_price: 0.27 - output_price: 0.40 - - name: deepseek/deepseek-v3.1-terminus - max_input_tokens: 163840 - input_price: 0.23 - output_price: 0.90 - - name: deepseek/deepseek-chat-v3.1 + - name: deepseek/deepseek-v3.2 max_input_tokens: 163840 - input_price: 0.2 - output_price: 0.8 - - name: deepseek/deepseek-r1-0528 - max_input_tokens: 128000 - input_price: 0.50 - output_price: 2.15 - patch: - body: - include_reasoning: true + input_price: 0.25 + output_price: 0.38 - name: qwen/qwen3-max max_input_tokens: 262144 input_price: 1.2 @@ -1821,12 +1554,7 @@ input_price: 0.29 output_price: 1.15 supports_function_calling: true - - name: x-ai/grok-4 - max_input_tokens: 256000 - input_price: 3 - output_price: 15 - supports_function_calling: true - - name: x-ai/grok-4-fast + - name: x-ai/grok-4.1-fast max_input_tokens: 2000000 input_price: 0.2 output_price: 0.5 @@ -1873,13 +1601,6 @@ patch: body: include_reasoning: true - - name: perplexity/sonar-reasoning - max_input_tokens: 127000 - input_price: 1 - output_price: 5 - patch: - body: - include_reasoning: true - name: perplexity/sonar-deep-research max_input_tokens: 200000 input_price: 2 @@ -1887,15 +1608,21 @@ patch: body: include_reasoning: true - - name: minimax/minimax-m2 + - name: minimax/minimax-m2.1 max_input_tokens: 196608 - input_price: 0.15 - output_price: 0.45 - - name: z-ai/glm-4.6 + input_price: 0.12 + output_price: 0.48 + supports_function_calling: true + - name: z-ai/glm-4.7 max_input_tokens: 202752 - input_price: 0.5 - output_price: 1.75 + input_price: 0.16 + output_price: 0.80 supports_function_calling: true + - name: z-ai/glm-4.6v + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.9 + supports_vision: true # Links: # - https://github.com/marketplace?type=models @@ -1906,11 +1633,6 @@ max_output_tokens: 128000 supports_vision: true supports_function_calling: true - - name: gpt-5-chat - max_input_tokens: 400000 - max_output_tokens: 128000 - supports_vision: true - supports_function_calling: true - name: gpt-5-mini max_input_tokens: 400000 max_output_tokens: 128000 @@ -1926,90 +1648,10 @@ max_output_tokens: 32768 supports_vision: true supports_function_calling: true - - name: gpt-4.1-mini - max_input_tokens: 1047576 - max_output_tokens: 32768 - supports_vision: true - supports_function_calling: true - - name: gpt-4.1-nano - max_input_tokens: 1047576 - max_output_tokens: 32768 - supports_vision: true - supports_function_calling: true - name: gpt-4o max_input_tokens: 128000 max_output_tokens: 16384 supports_function_calling: true - - name: gpt-4o-mini - max_input_tokens: 128000 - max_output_tokens: 16384 - supports_function_calling: true - - name: o4-mini - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o4-mini-high - real_name: o4-mini - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3 - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-high - real_name: o3 - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - - name: o3-mini - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - max_tokens: null - temperature: null - top_p: null - - name: o3-mini-high - real_name: o3-mini - max_input_tokens: 200000 - supports_vision: true - supports_function_calling: true - system_prompt_prefix: Formatting re-enabled - patch: - body: - reasoning_effort: high - max_tokens: null - temperature: null - top_p: null - name: text-embedding-3-large type: embedding max_tokens_per_chunk: 8191 @@ -2128,22 +1770,11 @@ input_price: 0.18 output_price: 0.69 supports_vision: true - - name: deepseek-ai/DeepSeek-V3.2-Exp - max_input_tokens: 163840 - input_price: 0.27 - output_price: 0.40 - - name: deepseek-ai/DeepSeek-V3.1-Terminus - max_input_tokens: 163840 - input_price: 0.27 - output_price: 1.0 - - name: deepseek-ai/DeepSeek-V3.1 - max_input_tokens: 163840 - input_price: 0.3 - output_price: 1.0 - - name: deepseek-ai/DeepSeek-R1-0528 + - name: deepseek-ai/DeepSeek-V3.2 max_input_tokens: 163840 - input_price: 0.5 - output_price: 2.15 + input_price: 0.26 + output_price: 0.39 + supports_function_calling: true - name: google/gemma-3-27b-it max_input_tokens: 131072 input_price: 0.1 @@ -2162,11 +1793,21 @@ input_price: 0.55 output_price: 2.5 supports_function_calling: true - - name: zai-org/GLM-4.6 + - name: MiniMaxAI/MiniMax-M2.1 + max_input_tokens: 262144 + input_price: 0.28 + output_price: 1.2 + supports_function_calling: true + - name: zai-org/GLM-4.7 max_input_tokens: 202752 - input_price: 0.6 - output_price: 1.9 + input_price: 0.43 + output_price: 1.75 supports_function_calling: true + - name: zai-org/GLM-4.6V + max_input_tokens: 131072 + input_price: 0.3 + output_price: 0.9 + supports_vision: true - name: BAAI/bge-large-en-v1.5 type: embedding input_price: 0.01 |