API Reference

Models

ProviderModelIDSpecDescription
OpenAIgpt-3.5-turboopenai/gpt-3.5-turbochatCurrently points to gpt-3.5-turbo-0125
gpt-3.5-turbo-16kopenai/gpt-3.5-turbo-16kchatCurrently points to gpt-3.5-turbo-16k-0613
gpt-3.5-turbo-0613openai/gpt-3.5-turbo-0613chat
gpt-3.5-turbo-1106openai/gpt-3.5-turbo-1106chat
gpt-3.5-turbo-0125openai/gpt-3.5-turbo-0125chat
gpt-3.5-turbo-instructopenai/gpt-3.5-turbo-instructcompletion
gpt-4openai/gpt-4chatCurrently points to gpt-4-0613
gpt-4-0613openai/gpt-4-0613chat
gpt-4-32k-0613openai/gpt-4-32k-0613chat
gpt-4-1106-previewopenai/gpt-4-1106-previewchat
gpt-4-turbo-2024-04-09openai/gpt-4-turbo-2024-04-09chat
gpt-4o-2024-05-13openai/gpt-4o-2024-05-13chat or responses
gpt-4o-2024-08-06openai/gpt-4o-2024-08-06chat or responses
gpt-4o-2024-11-20openai/gpt-4o-2024-11-20chat or responses
gpt-4o-mini-2024-07-18openai/gpt-4o-mini-2024-07-18chat or responses
o1-preview-2024-09-12openai/o1-preview-2024-09-12chat
o1-mini-2024-09-12openai/o1-mini-2024-09-12chat
o3-mini-2025-01-31openai/o3-mini-2025-01-31chat or responses
text-embedding-ada-002openai/text-embedding-ada-002embedding
text-embedding-3-largeopenai/text-embedding-3-largeembedding
text-embedding-3-smallopenai/text-embedding-3-smallembedding
text-moderation-stableopenai/text-moderation-stablesafety
omni-moderation-2024-09-26openai/omni-moderation-2024-09-26safety
dall-e-2openai/dall-e-2image generation
dall-e-3openai/dall-e-3image generation
gpt-4o-realtime-preview-2024-12-17openai/gpt-4o-realtime-preview-2024-12-17realtimeBeta
gpt-4o-realtime-preview-2024-10-01openai/gpt-4o-realtime-preview-2024-10-01realtimeBeta
gpt-4o-mini-realtime-preview-2024-12-17openai/gpt-4o-mini-realtime-preview-2024-12-17realtimeBeta
gpt-4o-search-preview-2025-03-11openai/gpt-4o-search-preview-2025-03-11chat
gpt-4o-mini-search-preview-2025-03-11openai/gpt-4o-mini-search-preview-2025-03-11chat
gpt-4.1-2025-04-14openai/gpt-4.1-2025-04-14chat or responses
gpt-4.1-mini-2025-04-14openai/gpt-4.1-mini-2025-04-14chat or responses
gpt-4.1-nano-2025-04-14openai/gpt-4.1-nano-2025-04-14chat or responses
o3-2025-04-16openai/o3-2025-04-16chat or responses
o4-mini-2025-04-16openai/o4-mini-2025-04-16chat or responses
Azure OpenAIgpt-3.5-turbo-0125azure/openai/gpt-3.5-turbo-0125chat
gpt-3.5-turbo-1106azure/openai/gpt-3.5-turbo-1106chat
gpt-3.5-turbo-0613azure/openai/gpt-3.5-turbo-0613chat
gpt-4-0613azure/openai/gpt-4-0613chat
gpt-4-32k-0613azure/openai/gpt-4-32k-0613chat
gpt-4-1106azure/openai/gpt-4-1106chat
gpt-4-turbo-2024-04-09azure/openai/gpt-4-turbo-2024-04-09chat
gpt-4o-2024-05-13azure/openai/gpt-4o-2024-05-13chat
gpt-4o-2024-08-06azure/openai/gpt-4o-2024-08-06chat
gpt-4o-2024-11-20-gsazure/openai/gpt-4o-2024-11-20-gschatGlobal Standard
gpt-4o-mini-2024-07-18azure/openai/gpt-4o-mini-2024-07-18chat
o1-2024-12-17-gsazure/openai/o1-2024-12-17-gschatGlobal Standard
o3-mini-2025-01-31-gsazure/openai/o3-mini-2025-01-31-gschatGlobal Standard
gpt-4.1-2025-04-14-gsazure/openai/gpt-4.1-2025-04-14-gschatGlobal Standard
gpt-4.1-mini-2025-04-14-gsazure/openai/gpt-4.1-mini-2025-04-14-gschatGlobal Standard
gpt-4.1-nano-2025-04-14-gsazure/openai/gpt-4.1-nano-2025-04-14-gschatGlobal Standard
o3-2025-04-16-gsazure/openai/o3-2025-04-16-gschatGlobal Standard
o4-mini-2025-04-16-gsazure/openai/o4-mini-2025-04-16-gschatGlobal Standard
text-embedding-ada-002azure/openai/text-embedding-ada-002embedding
text-embedding-3-largeazure/openai/text-embedding-3-largeembedding
text-embedding-3-smallazure/openai/text-embedding-3-smallembedding
Anthropicclaude-instant-1anthropic/claude-instant-1chat or completion
claude-2anthropic/claude-2chat or completionCurrently points to claude-2.1
claude-2.0anthropic/claude-2.0chat or completion
claude-2.1anthropic/claude-2.1chat or completion
claude-3-opus-20240229anthropic/claude-3-opus-20240229chat
claude-3-sonnet-20240229anthropic/claude-3-sonnet-20240229chat
claude-3-haiku-20240307anthropic/claude-3-haiku-20240307chat
claude-3-5-sonnet-20240620anthropic/claude-3-5-sonnet-20240620chat
claude-3-5-haiku-20241022anthropic/claude-3-5-haiku-20241022chat
claude-3-5-sonnet-20241022anthropic/claude-3-5-sonnet-20241022chat
claude-3-7-sonnet-20250219anthropic/claude-3-7-sonnet-20250219chat
Gcpgemini-1.5-pro-002gcp/gemini-1.5-pro-002chat
gemini-1.5-flash-002gcp/gemini-1.5-flash-002chat
gemini-2.0-flash-001gcp/gemini-2.0-flash-001chat
Amazontitan-embed-image-v1amazon/titan-embed-image-v1embedding
titan-embed-text-v2:0amazon/titan-embed-text-v2:0embedding
titan-embed-text-v1amazon/titan-embed-text-v1embedding
stable-image-core-v1:1amazon/stability/stable-image-core-v1:1image generation
stable-image-ultra-v1:1amazon/stability/stable-image-ultra-v1:1image generation
sd3.5-large-v1amazon/stability/sd3.5-large-v1image generation
SKTa.x-3-smskt/a.x-3-smchat
a.x-3-lgskt/a.x-3-lgchat
a.x-3-lg-q8skt/a.x-3-lg-q8chat
safety-v2skt/safety-v2text safety
safety-image-v1-stgskt/safety-image-v1-stgimage safety
axtts-2-6skt/axtts-2-6ttsAvailable voices
axtts-2-6-ainewsskt/axtts-2-6-ainewsttsAvailable voices
axtts-2-1skt/axtts-2-1ttsAvailable voices
axtts-2-1-dialectskt/axtts-2-1-dialectttsAvailable voices
Perplexitysonarperplexity/sonarchat
sonar-properplexity/sonar-prochat
sonar-reasoningperplexity/sonar-reasoningchat
sonar-reasoning-properplexity/sonar-reasoning-prochat
r1-1776perplexity/r1-1776chatOffline model