# Links: # - https://platform.openai.com/docs/models # - https://openai.com/api/pricing/ # - https://platform.openai.com/docs/api-reference/chat - provider: openai models: - name: gpt-4o max_input_tokens: 128000 max_output_tokens: 16384 input_price: 2.5 output_price: 10 supports_vision: true supports_function_calling: true - name: chatgpt-4o-latest max_input_tokens: 128000 max_output_tokens: 16384 input_price: 5 output_price: 15 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: gpt-4-turbo max_input_tokens: 128000 max_output_tokens: 4096 input_price: 10 output_price: 30 supports_vision: true supports_function_calling: true - 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: o1 max_input_tokens: 200000 input_price: 15 output_price: 60 supports_vision: true supports_function_calling: true system_prompt_prefix: Formatting re-enabled patch: body: max_tokens: null temperature: null top_p: null - name: o1-preview max_input_tokens: 128000 max_output_tokens: 32768 input_price: 15 output_price: 60 no_system_message: true patch: body: max_tokens: null temperature: null top_p: null - name: o1-mini max_input_tokens: 128000 max_output_tokens: 65536 input_price: 3 output_price: 12 no_system_message: true patch: body: max_tokens: null temperature: null top_p: null - name: gpt-3.5-turbo max_input_tokens: 16385 max_output_tokens: 4096 input_price: 0.5 output_price: 1.5 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 # Links: # - https://ai.google.dev/models/gemini # - https://ai.google.dev/pricing # - https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent - provider: gemini models: - name: gemini-2.0-flash max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: gemini-2.0-flash-lite-preview max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: gemini-2.0-flash-thinking-exp max_input_tokens: 32767 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true - name: gemini-2.0-pro-exp max_input_tokens: 2097152 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: gemini-1.5-pro-latest max_input_tokens: 2097152 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: gemini-1.5-flash-latest max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: gemini-1.5-flash-8b-latest max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true supports_function_calling: true - name: text-embedding-004 type: embedding input_price: 0 max_tokens_per_chunk: 2048 default_chunk_size: 1500 max_batch_size: 100 # Links: # - https://docs.anthropic.com/en/docs/about-claude/models # - https://docs.anthropic.com/en/api/messages - provider: claude models: - name: claude-3-5-sonnet-latest max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-5-sonnet-20241022 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-5-haiku-latest max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 0.8 output_price: 4 supports_vision: true supports_function_calling: true - name: claude-3-5-haiku-20241022 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 0.8 output_price: 4 supports_vision: true supports_function_calling: true - name: claude-3-opus-20240229 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 15 output_price: 75 supports_vision: true supports_function_calling: true - name: claude-3-sonnet-20240229 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-haiku-20240307 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 0.25 output_price: 1.25 supports_vision: true supports_function_calling: true # Links: # - https://docs.mistral.ai/getting-started/models/models_overview/ # - https://mistral.ai/en/products/la-plateforme#pricing # - https://docs.mistral.ai/api/ - provider: mistral models: - name: mistral-large-latest max_input_tokens: 128000 input_price: 2 output_price: 6 supports_function_calling: true - name: mistral-small-latest max_input_tokens: 32000 input_price: 0.1 output_price: 0.3 supports_function_calling: true - name: codestral-latest max_input_tokens: 256000 input_price: 0.3 output_price: 0.9 supports_function_calling: true - name: ministral-8b-latest max_input_tokens: 128000 input_price: 0.1 output_price: 0.1 supports_function_calling: true - name: open-mistral-nemo max_input_tokens: 128000 input_price: 0.15 output_price: 0.15 supports_function_calling: true - name: pixtral-large-latest max_input_tokens: 128000 input_price: 2 output_price: 6 supports_vision: true - name: pixtral-12b-latest max_input_tokens: 128000 input_price: 0.15 output_price: 0.15 supports_vision: true - name: mistral-embed type: embedding max_input_tokens: 8092 input_price: 0.1 max_tokens_per_chunk: 8092 default_chunk_size: 2000 # Links: # - https://docs.ai21.com/docs/jamba-15-models # - https://www.ai21.com/pricing # - https://docs.ai21.com/reference/jamba-15-api-ref - provider: ai21 models: - name: jamba-1.5-large max_input_tokens: 256000 input_price: 2 output_price: 8 supports_function_calling: true - name: jamba-1.5-mini max_input_tokens: 256000 input_price: 0.2 output_price: 0.4 supports_function_calling: true # Links: # - https://docs.cohere.com/docs/command-r-plus # - https://cohere.com/pricing # - https://docs.cohere.com/reference/chat - provider: cohere models: - name: command-r-plus-08-2024 max_input_tokens: 128000 max_output_tokens: 4096 input_price: 2.5 output_price: 10 supports_function_calling: true - name: command-r-08-2024 max_input_tokens: 128000 max_output_tokens: 4096 input_price: 0.15 output_price: 0.6 supports_function_calling: true - name: command-r7b-12-2024 max_input_tokens: 128000 max_output_tokens: 4096 input_price: 0.0375 output_price: 0.15 - 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-english-light-v3.0 type: embedding input_price: 0.1 max_tokens_per_chunk: 512 default_chunk_size: 700 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: embed-multilingual-light-v3.0 type: embedding input_price: 0.1 max_tokens_per_chunk: 512 default_chunk_size: 700 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 # Links: # - https://docs.x.ai/docs/models # - https://docs.x.ai/docs/api-reference#chat-completions - provider: xai models: - name: grok-2-latest max_input_tokens: 131072 input_price: 2 output_price: 10 supports_function_calling: true - name: grok-2-1212 max_input_tokens: 131072 input_price: 2 output_price: 10 supports_function_calling: true - name: grok-beta max_input_tokens: 131072 input_price: 5 output_price: 15 supports_function_calling: true - name: grok-2-vision-latest max_input_tokens: 32768 input_price: 2 output_price: 10 supports_vision: true supports_function_calling: true - name: grok-2-vision-1212 max_input_tokens: 32768 input_price: 2 output_price: 10 supports_vision: true supports_function_calling: true - name: grok-vision-beta max_input_tokens: 8192 input_price: 5 output_price: 15 supports_vision: true # Links: # - https://docs.perplexity.ai/guides/model-cards # - https://docs.perplexity.ai/guides/pricing # - https://docs.perplexity.ai/api-reference/chat-completions - provider: perplexity models: - name: sonar-pro max_input_tokens: 200000 input_price: 3 output_price: 15 - name: sonar max_input_tokens: 127000 input_price: 1 output_price: 1 - name: sonar-reasoning-pro max_input_tokens: 127000 input_price: 2 output_price: 8 - name: sonar-reasoning max_input_tokens: 127000 input_price: 1 output_price: 5 # Links: # - https://console.groq.com/docs/models # - https://console.groq.com/docs/api-reference#chat - provider: groq models: - name: llama-3.3-70b-versatile max_input_tokens: 131072 input_price: 0 output_price: 0 supports_function_calling: true - name: llama-3.1-8b-instant max_input_tokens: 131072 input_price: 0 output_price: 0 supports_function_calling: true - name: llama-3.2-90b-vision-preview max_input_tokens: 131072 input_price: 0 output_price: 0 supports_vision: true - name: llama-3.2-11b-vision-preview max_input_tokens: 131072 input_price: 0 output_price: 0 supports_vision: true - name: deepseek-r1-distill-llama-70b max_input_tokens: 131072 input_price: 0 output_price: 0 - name: deepseek-r1-distill-qwen-32b max_input_tokens: 131072 input_price: 0 output_price: 0 - name: qwen-2.5-32b max_input_tokens: 131072 input_price: 0 output_price: 0 - name: qwen-2.5-coder-32b max_input_tokens: 131072 input_price: 0 output_price: 0 # Links: # - https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models # - https://cloud.google.com/vertex-ai/generative-ai/pricing # - https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini - provider: vertexai models: - name: gemini-2.0-flash-001 max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0.15 output_price: 0.6 supports_vision: true supports_function_calling: true - name: gemini-2.0-flash-lite-preview-02-05 max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0.075 output_price: 0.3 supports_vision: true supports_function_calling: true - name: gemini-2.0-flash-thinking-exp-01-21 max_input_tokens: 32760 max_output_tokens: 8192 supports_vision: true - name: gemini-2.0-pro-exp-02-05 max_input_tokens: 2097152 max_output_tokens: 8192 supports_vision: true supports_function_calling: true - name: gemini-1.5-pro-002 max_input_tokens: 2097152 max_output_tokens: 8192 input_price: 1.25 output_price: 3.75 supports_vision: true supports_function_calling: true - name: gemini-1.5-flash-002 max_input_tokens: 1048576 max_output_tokens: 8192 input_price: 0.019 output_price: 0.075 supports_vision: true supports_function_calling: true - name: claude-3-5-sonnet-v2@20241022 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-5-sonnet@20240620 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-5-haiku@20241022 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 0.8 output_price: 4 supports_vision: true supports_function_calling: true - name: claude-3-opus@20240229 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 15 output_price: 75 supports_vision: true supports_function_calling: true - name: claude-3-sonnet@20240229 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: claude-3-haiku@20240307 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 0.25 output_price: 1.25 supports_vision: true supports_function_calling: true - name: mistral-large-2411 max_input_tokens: 128000 input_price: 2 output_price: 6 supports_function_calling: true - name: codestral-2501 max_input_tokens: 256000 input_price: 0.3 output_price: 0.9 supports_function_calling: true - name: mistral-nemo@2407 max_input_tokens: 128000 input_price: 0.15 output_price: 0.15 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 # Links: # - https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns # - https://aws.amazon.com/bedrock/pricing/ # - https://docs.aws.amazon.com/bedrock/latest/userguide/cross-region-inference-support.html - provider: bedrock models: - name: anthropic.claude-3-5-sonnet-20241022-v2:0 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: anthropic.claude-3-5-sonnet-20240620-v1:0 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: anthropic.claude-3-5-haiku-20241022-v1:0 max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 0.8 output_price: 4 supports_vision: true supports_function_calling: true - name: anthropic.claude-3-opus-20240229-v1:0 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 15 output_price: 75 supports_vision: true supports_function_calling: true - name: anthropic.claude-3-sonnet-20240229-v1:0 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: anthropic.claude-3-haiku-20240307-v1:0 max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 0.25 output_price: 1.25 supports_vision: true supports_function_calling: true - name: us.meta.llama3-3-70b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 8192 require_max_tokens: true input_price: 0.72 output_price: 0.72 supports_function_calling: true - name: meta.llama3-1-405b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 4096 require_max_tokens: true input_price: 2.4 output_price: 2.4 supports_function_calling: true - name: meta.llama3-1-70b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 8192 require_max_tokens: true input_price: 0.72 output_price: 0.72 supports_function_calling: true - name: meta.llama3-1-8b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 8192 require_max_tokens: true input_price: 0.22 output_price: 0.22 supports_function_calling: true - name: us.meta.llama3-2-90b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 8192 require_max_tokens: true input_price: 0.72 output_price: 0.72 supports_function_calling: true supports_vision: true - name: us.meta.llama3-2-11b-instruct-v1:0 max_input_tokens: 131072 max_output_tokens: 8192 require_max_tokens: true input_price: 0.16 output_price: 0.16 supports_function_calling: true supports_vision: true - name: us.amazon.nova-pro-v1:0 max_input_tokens: 300000 max_output_tokens: 5120 input_price: 0.8 output_price: 3.2 supports_vision: true - name: us.amazon.nova-lite-v1:0 max_input_tokens: 300000 max_output_tokens: 5120 input_price: 0.06 output_price: 0.24 supports_vision: true - name: us.amazon.nova-micro-v1:0 max_input_tokens: 128000 max_output_tokens: 5120 input_price: 0.035 output_price: 0.14 - name: mistral.mistral-large-2407-v1:0 max_input_tokens: 128000 input_price: 2 output_price: 6 supports_function_calling: true - name: cohere.command-r-plus-v1:0 max_input_tokens: 128000 input_price: 3 output_price: 15 supports_function_calling: true - name: cohere.command-r-v1:0 max_input_tokens: 128000 input_price: 0.5 output_price: 1.5 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 - name: ai21.jamba-1-5-large-v1:0 max_input_tokens: 256000 input_price: 2 output_price: 8 supports_function_calling: true - name: ai21.jamba-1-5-mini-v1:0 max_input_tokens: 256000 input_price: 0.2 output_price: 0.4 supports_function_calling: true # Links: # - https://developers.cloudflare.com/workers-ai/models/ # - https://developers.cloudflare.com/workers-ai/configuration/open-ai-compatibility/ - provider: cloudflare models: - name: '@cf/meta/llama-3.3-70b-instruct-fp8-fast' max_input_tokens: 131072 max_output_tokens: 2048 require_max_tokens: true input_price: 0 output_price: 0 - name: '@cf/meta/llama-3.1-70b-instruct' max_input_tokens: 131072 max_output_tokens: 2048 require_max_tokens: true input_price: 0 output_price: 0 - name: '@cf/meta/llama-3.1-8b-instruct' max_input_tokens: 131072 max_output_tokens: 2048 require_max_tokens: true input_price: 0 output_price: 0 - name: '@cf/deepseek-ai/deepseek-r1-distill-qwen-32b' max_input_tokens: 131072 max_output_tokens: 2048 require_max_tokens: true input_price: 0 output_price: 0 - name: '@cf/baai/bge-large-en-v1.5' type: embedding input_price: 0 max_tokens_per_chunk: 512 default_chunk_size: 1000 max_batch_size: 100 # Links: # - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Fm2vrveyu # - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7 - provider: ernie models: - name: ernie-4.0-turbo-8k-latest max_input_tokens: 8192 input_price: 2.8 output_price: 8.4 supports_function_calling: true - name: ernie-4.0-turbo-128k max_input_tokens: 128000 input_price: 2.8 output_price: 8.4 supports_function_calling: true - name: ernie-4.0-8k-latest max_input_tokens: 8192 input_price: 4.2 output_price: 12.6 supports_function_calling: true - name: ernie-3.5-128k max_input_tokens: 128000 input_price: 0.112 output_price: 0.28 supports_function_calling: true - name: ernie-speed-pro-128k max_input_tokens: 128000 input_price: 0.042 output_price: 0.084 - name: deepseek-v3 max_input_tokens: 131072 input_price: 0.112 output_price: 0.224 - name: deepseek-r1 max_input_tokens: 131072 input_price: 0.28 output_price: 1.12 - 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 # Links: # - https://help.aliyun.com/zh/model-studio/getting-started/models # - https://help.aliyun.com/zh/model-studio/developer-reference/use-qwen-by-calling-api - provider: qianwen models: - name: qwen-max-latest max_input_tokens: 32678 max_output_tokens: 8192 input_price: 1.6 output_price: 6.4 supports_function_calling: true - name: qwen-plus-latest max_input_tokens: 131072 max_output_tokens: 8192 input_price: 0.112 output_price: 0.28 supports_function_calling: true - name: qwen-turbo-latest max_input_tokens: 1000000 max_output_tokens: 8192 input_price: 0.042 output_price: 0.084 supports_function_calling: true - name: qwen-coder-plus-latest max_input_tokens: 129024 max_output_tokens: 8192 input_price: 0.49 output_price: 0.98 supports_function_calling: true - name: qwen-coder-turbo-latest max_input_tokens: 129024 max_output_tokens: 8192 input_price: 0.28 output_price: 0.84 supports_function_calling: true - name: qwen-long max_input_tokens: 1000000 input_price: 0.07 output_price: 0.28 - name: qvq-72b-preview max_input_tokens: 16384 max_output_tokens: 16384 supports_vision: true - name: qwq-32b-preview max_input_tokens: 30720 max_output_tokens: 16384 input_price: 0.49 output_price: 0.98 supports_function_calling: true - name: qwen-vl-max-latest max_input_tokens: 30720 max_output_tokens: 2048 input_price: 0.42 output_price: 1.26 supports_vision: true - name: qwen-vl-plus-latest max_input_tokens: 30000 max_output_tokens: 2048 input_price: 0.21 output_price: 0.63 supports_vision: true - name: qwen2.5-72b-instruct max_input_tokens: 129024 max_output_tokens: 8192 input_price: 0.56 output_price: 1.68 supports_function_calling: true - name: qwen2.5-coder-32b-instruct max_input_tokens: 129024 max_output_tokens: 8192 input_price: 0.49 output_price: 0.98 supports_function_calling: true - name: deepseek-v3 max_input_tokens: 65792 input_price: 0.14 output_price: 0.56 - name: deepseek-r1 max_input_tokens: 65792 input_price: 0.28 output_price: 1.12 - name: text-embedding-v3 type: embedding input_price: 0.1 max_tokens_per_chunk: 8192 default_chunk_size: 2000 max_batch_size: 6 - name: text-embedding-v2 type: embedding input_price: 0.1 max_tokens_per_chunk: 2048 default_chunk_size: 2000 max_batch_size: 25 # links: # - https://cloud.tencent.com/document/product/1729/104753 # - https://cloud.tencent.com/document/product/1729/97731 # - https://cloud.tencent.com/document/product/1729/111007 - provider: hunyuan models: - name: hunyuan-turbo-latest max_input_tokens: 28000 max_output_tokens: 4096 input_price: 2.1 output_price: 7.0 supports_function_calling: true - name: hunyuan-large max_input_tokens: 28000 max_output_tokens: 4096 input_price: 0.56 output_price: 1.68 supports_function_calling: true - name: hunyuan-large-longcontext max_input_tokens: 128000 max_output_tokens: 6144 input_price: 0.84 output_price: 2.52 supports_function_calling: true - name: hunyuan-standard max_input_tokens: 30000 max_output_tokens: 2048 input_price: 0.112 output_price: 0.28 supports_function_calling: true - name: hunyuan-standard-256K max_input_tokens: 250000 max_output_tokens: 6144 input_price: 0.07 output_price: 0.28 supports_function_calling: true - name: hunyuan-lite max_input_tokens: 250000 max_output_tokens: 6144 input_price: 0 output_price: 0 supports_function_calling: true - name: hunyuan-functioncall max_input_tokens: 28000 max_output_tokens: 4096 input_price: 0.56 output_price: 1.12 supports_function_calling: true - name: hunyuan-turbo-vision max_input_tokens: 6144 max_output_tokens: 2048 input_price: 11.2 output_price: 11.2 supports_vision: true - name: hunyuan-vision max_input_tokens: 6144 max_output_tokens: 2048 input_price: 2.52 output_price: 2.52 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 # Links: # - https://platform.moonshot.cn/docs/pricing/chat#%E8%AE%A1%E8%B4%B9%E5%9F%BA%E6%9C%AC%E6%A6%82%E5%BF%B5 # - https://platform.moonshot.cn/docs/api/chat#%E5%85%AC%E5%BC%80%E7%9A%84%E6%9C%8D%E5%8A%A1%E5%9C%B0%E5%9D%80 - provider: moonshot models: - name: kimi-latest supports_vision: true supports_function_calling: true - name: moonshot-v1-8k max_input_tokens: 8192 input_price: 1.68 output_price: 1.68 supports_function_calling: true - name: moonshot-v1-32k max_input_tokens: 32768 input_price: 3.36 output_price: 3.36 supports_function_calling: true - name: moonshot-v1-128k max_input_tokens: 131072 input_price: 8.4 output_price: 8.4 supports_function_calling: true - name: moonshot-v1-8k-vision-preview max_input_tokens: 8192 input_price: 1.68 output_price: 1.68 supports_vision: true - name: moonshot-v1-32k-vision-preview max_input_tokens: 32768 input_price: 3.36 output_price: 3.36 supports_vision: true - name: moonshot-v1-128k-vision-preview max_input_tokens: 131072 input_price: 8.4 output_price: 8.4 supports_vision: true # Links: # - https://api-docs.deepseek.com/quick_start/pricing # - https://platform.deepseek.com/api-docs/api/create-chat-completion - provider: deepseek models: - name: deepseek-chat max_input_tokens: 64000 max_output_tokens: 8192 input_price: 0.27 output_price: 1.1 supports_function_calling: true - name: deepseek-reasoner max_input_tokens: 64000 max_output_tokens: 8192 input_price: 0.55 output_price: 2.19 # Links: # - https://open.bigmodel.cn/pricing # - https://open.bigmodel.cn/dev/api#glm-4 - provider: zhipuai models: - name: glm-4-plus max_input_tokens: 128000 max_output_tokens: 4096 input_price: 7 output_price: 7 supports_function_calling: true - name: glm-4-alltools max_input_tokens: 128000 max_output_tokens: 4096 input_price: 14 output_price: 14 supports_function_calling: true - name: glm-4-long max_input_tokens: 1000000 max_output_tokens: 4096 input_price: 0.14 output_price: 0.14 supports_function_calling: true - name: glm-4-flash max_input_tokens: 128000 max_output_tokens: 4096 input_price: 0 output_price: 0 supports_function_calling: true - name: glm-4v-plus max_input_tokens: 8192 input_price: 0.56 output_price: 0.56 supports_vision: true - name: glm-4v-flash max_input_tokens: 8192 input_price: 0 output_price: 0 supports_vision: true - name: glm-zero-preview max_input_tokens: 16384 input_price: 1.4 output_price: 1.4 - 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 # Links: # - https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B%E4%B8%8E%E8%AE%A1%E8%B4%B9 # - https://platform.lingyiwanwu.com/docs/api-reference#create-chat-completion - provider: lingyiwanwu models: - name: yi-lightning max_input_tokens: 16384 input_price: 0.14 output_price: 0.14 - name: yi-vision-v2 max_input_tokens: 16384 input_price: 0.84 output_price: 0.84 supports_vision: true # Links: # - https://platform.minimaxi.com/document/Price # - https://platform.minimaxi.com/document/ChatCompletion%20v2 - provider: minimax models: - name: minimax-text-01 max_input_tokens: 1000192 input_price: 0.14 output_price: 1.12 supports_vision: true - name: abab6.5s-chat max_input_tokens: 245760 input_price: 0.14 output_price: 0.14 supports_vision: true - name: deepseek-r1 max_input_tokens: 131072 input_price: 0.56 output_price: 2.24 # Links: # - https://openrouter.ai/models # - https://openrouter.ai/docs/api-reference/chat-completion - provider: openrouter models: - 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-2024-11-20 max_input_tokens: 128000 input_price: 2.5 output_price: 10 supports_vision: true supports_function_calling: true - name: openai/gpt-4o-2024-08-06 max_input_tokens: 128000 input_price: 2.5 output_price: 10 supports_vision: true supports_function_calling: true - name: openai/chatgpt-4o-latest max_input_tokens: 128000 input_price: 5 output_price: 15 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/gpt-4-turbo max_input_tokens: 128000 input_price: 10 output_price: 30 supports_vision: true supports_function_calling: true - 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/o1 max_input_tokens: 128000 input_price: 15 output_price: 60 supports_vision: true supports_function_calling: true system_prompt_prefix: Formatting re-enabled patch: body: temperature: null top_p: null - name: openai/o1-preview max_input_tokens: 128000 input_price: 15 output_price: 60 no_system_message: true patch: body: temperature: null top_p: null - name: openai/o1-mini max_input_tokens: 128000 input_price: 3 output_price: 12 no_system_message: true patch: body: temperature: null top_p: null - name: openai/gpt-3.5-turbo max_input_tokens: 16385 input_price: 0.5 output_price: 1.5 supports_function_calling: true - name: google/gemini-pro-1.5 max_input_tokens: 2000000 input_price: 1.25 output_price: 5 supports_vision: true supports_function_calling: true - name: google/gemini-flash-1.5 max_input_tokens: 1000000 input_price: 0.075 output_price: 0.3 supports_vision: true supports_function_calling: true - name: google/gemini-flash-1.5-8b max_input_tokens: 1000000 input_price: 0.0375 output_price: 0.15 supports_vision: true supports_function_calling: true - name: google/gemini-2.0-flash-001 max_input_tokens: 1000000 input_price: 0.1 output_price: 0.4 supports_vision: true supports_function_calling: true - name: anthropic/claude-3.5-sonnet max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: anthropic/claude-3-5-haiku max_input_tokens: 200000 max_output_tokens: 8192 require_max_tokens: true input_price: 0.8 output_price: 4 supports_vision: true supports_function_calling: true - name: anthropic/claude-3-opus max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 15 output_price: 75 supports_vision: true supports_function_calling: true - name: anthropic/claude-3-sonnet max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 3 output_price: 15 supports_vision: true supports_function_calling: true - name: anthropic/claude-3-haiku max_input_tokens: 200000 max_output_tokens: 4096 require_max_tokens: true input_price: 0.25 output_price: 1.25 supports_vision: true supports_function_calling: true - name: meta-llama/llama-3.3-70b-instruct max_input_tokens: 131072 input_price: 0.12 output_price: 0.3 - name: meta-llama/llama-3.1-405b-instruct max_input_tokens: 32768 input_price: 0.8 output_price: 0.8 supports_function_calling: true - name: meta-llama/llama-3.1-70b-instruct max_input_tokens: 131072 input_price: 0.12 output_price: 0.3 supports_function_calling: true - name: meta-llama/llama-3.1-8b-instruct max_input_tokens: 131072 input_price: 0.02 output_price: 0.05 - name: meta-llama/llama-3.2-90b-vision-instruct max_input_tokens: 131072 input_price: 0.9 output_price: 0.9 supports_vision: true - name: meta-llama/llama-3.2-11b-vision-instruct max_input_tokens: 131072 input_price: 0.055 output_price: 0.055 supports_vision: true - name: mistralai/mistral-large-2411 max_input_tokens: 128000 input_price: 2 output_price: 6 supports_function_calling: true - name: mistralai/mistral-small-24b-instruct-2501 max_input_tokens: 32768 input_price: 0.1 output_price: 0.3 - name: mistralai/codestral-2501 max_input_tokens: 256000 input_price: 0.3 output_price: 0.9 supports_function_calling: true - name: mistralai/ministral-8b max_input_tokens: 128000 input_price: 0.1 output_price: 0.1 supports_function_calling: true - name: mistralai/mistral-nemo max_input_tokens: 128000 input_price: 0.035 output_price: 0.08 supports_function_calling: true - name: mistralai/pixtral-large-2411 max_input_tokens: 128000 input_price: 2 output_price: 6 supports_vision: true - name: mistralai/pixtral-12b max_input_tokens: 128000 input_price: 0.1 output_price: 0.1 supports_vision: true - name: ai21/jamba-1-5-large max_input_tokens: 256000 input_price: 2 output_price: 8 supports_function_calling: true - name: ai21/jamba-1-5-mini max_input_tokens: 256000 input_price: 0.2 output_price: 0.4 supports_function_calling: true - name: cohere/command-r-plus-08-2024 max_input_tokens: 128000 input_price: 2.5 output_price: 10 supports_function_calling: true - name: cohere/command-r-08-2024 max_input_tokens: 128000 input_price: 0.15 output_price: 0.6 supports_function_calling: true - name: cohere/command-r7b-12-2024 max_input_tokens: 128000 max_output_tokens: 4096 input_price: 0.0375 output_price: 0.15 - name: deepseek/deepseek-chat max_input_tokens: 64000 input_price: 0.14 output_price: 0.28 supports_function_calling: true - name: deepseek/deepseek-r1 max_input_tokens: 163840 input_price: 0.55 output_price: 2.19 patch: body: include_reasoning: true - name: deepseek/deepseek-r1-distill-llama-70b max_input_tokens: 131072 input_price: 0.23 output_price: 0.69 patch: body: include_reasoning: true - name: deepseek/deepseek-r1-distill-qwen-32b max_input_tokens: 131072 input_price: 0.12 output_price: 0.18 patch: body: include_reasoning: true - name: qwen/qwen-max max_input_tokens: 32768 max_output_tokens: 8192 input_price: 1.6 output_price: 6.4 supports_function_calling: true - name: qwen/qwen-plus max_input_tokens: 131072 max_output_tokens: 8192 input_price: 0.4 output_price: 1.2 supports_function_calling: true - name: qwen/qwen-turbo max_input_tokens: 1000000 max_output_tokens: 8192 input_price: 0.05 output_price: 0.2 supports_function_calling: true - name: qwen/qwen-2.5-72b-instruct max_input_tokens: 131072 input_price: 0.35 output_price: 0.4 supports_function_calling: true - name: qwen/qwen-2.5-coder-32b-instruct max_input_tokens: 32768 input_price: 0.18 output_price: 0.18 - name: qwen/qwen-2-vl-72b-instruct max_input_tokens: 32768 input_price: 0.4 output_price: 0.4 - name: x-ai/grok-2-1212 max_input_tokens: 131072 input_price: 2 output_price: 10 supports_function_calling: true - name: x-ai/grok-beta max_input_tokens: 32768 input_price: 5 output_price: 15 supports_function_calling: true - name: x-ai/grok-2-vision-1212 max_input_tokens: 32768 input_price: 2 output_price: 10 supports_vision: true supports_function_calling: true - name: x-ai/grok-vision-beta max_input_tokens: 8192 input_price: 5 output_price: 15 supports_vision: true - name: amazon/nova-pro-v1 max_input_tokens: 300000 max_output_tokens: 5120 input_price: 0.8 output_price: 3.2 supports_vision: true - name: amazon/nova-lite-v1 max_input_tokens: 300000 max_output_tokens: 5120 input_price: 0.06 output_price: 0.24 supports_vision: true - name: amazon/nova-micro-v1 max_input_tokens: 128000 max_output_tokens: 5120 input_price: 0.035 output_price: 0.14 - name: perplexity/sonar-reasoning max_input_tokens: 127000 input_price: 1 output_price: 5 patch: body: include_reasoning: true - name: perplexity/sonar max_input_tokens: 127000 input_price: 1 output_price: 1 - name: minimax/minimax-01 max_input_tokens: 1000192 input_price: 0.2 output_price: 1.1 # Links: # - https://github.com/marketplace/models - provider: github models: - name: gpt-4o max_input_tokens: 128000 supports_function_calling: true - name: gpt-4o-mini max_input_tokens: 128000 supports_function_calling: true - name: o3-mini max_input_tokens: 200000 supports_function_calling: true supports_vision: 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_function_calling: true supports_vision: true system_prompt_prefix: Formatting re-enabled patch: body: reasoning_effort: high max_tokens: null temperature: null top_p: null - name: o1 max_input_tokens: 200000 supports_function_calling: true supports_vision: true system_prompt_prefix: Formatting re-enabled patch: body: max_tokens: null temperature: null top_p: null - name: o1-preview max_input_tokens: 128000 no_stream: true no_system_message: true patch: body: max_tokens: null temperature: null top_p: null - name: o1-mini max_input_tokens: 128000 no_stream: true no_system_message: true patch: body: max_tokens: null temperature: null top_p: null - 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-3.3-70b-instruct max_input_tokens: 131072 - name: meta-llama-3.1-405b-instruct max_input_tokens: 131072 - name: meta-llama-3.1-70b-instruct max_input_tokens: 131072 - name: meta-llama-3.1-8b-instruct max_input_tokens: 131072 - name: llama-3.2-90b-vision-instruct max_input_tokens: 131072 supports_vision: true - name: llama-3.2-11b-vision-instruct max_input_tokens: 131072 supports_vision: true - name: mistral-large-2411 max_input_tokens: 128000 supports_function_calling: true - name: codestral-2501 max_input_tokens: 256000 supports_function_calling: true - name: mistral-nemo max_input_tokens: 128000 supports_function_calling: true - name: cohere-command-r-plus-08-2024 max_input_tokens: 128000 supports_function_calling: true - name: cohere-command-r-08-2024 max_input_tokens: 128000 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: ai21-jamba-1.5-large max_input_tokens: 256000 supports_function_calling: true - name: ai21-jamba-1.5-mini max_input_tokens: 256000 supports_function_calling: true - name: deepseek-r1 max_input_tokens: 163840 - name: phi-4 max_input_tokens: 16384 - name: phi-3.5-moe-instruct max_input_tokens: 128000 - name: phi-3.5-mini-instruct max_input_tokens: 128000 - name: phi-3.5-vision-instruct max_input_tokens: 128000 supports_vision: true # Links: # - https://deepinfra.com/models # - https://deepinfra.com/docs/openai_api - provider: deepinfra models: - name: meta-llama/Llama-3.3-70B-Instruct max_input_tokens: 131072 input_price: 0.23 output_price: 0.40 - name: meta-llama/Meta-Llama-3.1-405B-Instruct max_input_tokens: 32768 input_price: 0.8 output_price: 0.8 supports_function_calling: true - name: meta-llama/Meta-Llama-3.1-70B-Instruct max_input_tokens: 131072 input_price: 0.23 output_price: 0.4 supports_function_calling: true - name: meta-llama/Meta-Llama-3.1-8B-Instruct max_input_tokens: 131072 input_price: 0.03 output_price: 0.05 supports_function_calling: true - name: meta-llama/Llama-3.2-90B-Vision-Instruct max_input_tokens: 131072 input_price: 0.35 output_price: 0.4 - name: meta-llama/Llama-3.2-11B-Vision-Instruct max_input_tokens: 131072 input_price: 0.055 output_price: 0.055 - name: Qwen/Qwen2.5-72B-Instruct max_input_tokens: 32768 input_price: 0.23 output_price: 0.40 supports_function_calling: true - name: Qwen/Qwen2.5-Coder-32B-Instruct max_input_tokens: 32768 input_price: 0.07 output_price: 0.16 - name: deepseek-ai/DeepSeek-V3 max_input_tokens: 65536 input_price: 0.49 output_price: 0.89 - name: deepseek-ai/DeepSeek-R1 max_input_tokens: 65536 input_price: 0.75 output_price: 2.4 - name: deepseek-ai/DeepSeek-R1-Distill-Llama-70B max_input_tokens: 131072 input_price: 0.23 output_price: 0.69 - name: deepseek-ai/DeepSeek-R1-Distill-Qwen-32B max_input_tokens: 131072 input_price: 0.12 output_price: 0.18 - name: mistralai/Mistral-Small-24B-Instruct-2501 max_input_tokens: 32768 input_price: 0.07 output_price: 0.14 - name: mistralai/Mistral-Nemo-Instruct-2407 max_input_tokens: 131072 input_price: 0.035 output_price: 0.08 - 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 # Links: # - https://jina.ai/models # - https://api.jina.ai/redoc - provider: jina models: - name: jina-embeddings-v3 type: embedding input_price: 0 max_tokens_per_chunk: 8192 default_chunk_size: 2000 max_batch_size: 100 - name: jina-colbert-v2 type: embedding input_price: 0 max_tokens_per_chunk: 8192 default_chunk_size: 1500 max_batch_size: 100 - name: jina-clip-v2 type: embedding input_price: 0 max_tokens_per_chunk: 8192 default_chunk_size: 1500 max_batch_size: 100 - name: jina-colbert-v2 type: reranker max_input_tokens: 8192 input_price: 0 - name: jina-reranker-v2-base-multilingual type: reranker max_input_tokens: 8192 input_price: 0 # Links: # - https://docs.voyageai.com/docs/embeddings # - https://docs.voyageai.com/docs/pricing # - https://docs.voyageai.com/reference/ - 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