v55

latestOpenAPI 3.1.0raw.githubusercontent.com2026-08-06107288545.4 KB

chat_completions

OpenAI-compatible chat completions

Creates a chat completion using the OpenAI wire format, proxying to the selected provider with credentials resolved on the server (secret store first, environment second) — callers never handle provider API keys. Model must be '{provider}:{model_name}' for a built-in provider (one of anthropic, aws, azure_openai, cerebras, deepseek, fireworks, google, groq, moonshot, ollama, openai, perplexity, together, xai) or 'custom:{provider_id}:{model_name}' for a stored custom provider, e.g. 'openai:gpt-4o' or 'anthropic:claude-sonnet-4-5'. Set stream: true for server-sent events of chat.completion.chunk payloads terminated by data: [DONE]. Tool calling is not supported.

Phoenix is not an AI gateway. The same server also takes on trace ingestion traffic, so routing production LLM calls through it competes with ingestion. Use this endpoint only to quickly try out different models in non-production environments.

post/v1/chat/completions

Request body

modelstring required

Model must be '{provider}:{model_name}' for a built-in provider (one of anthropic, aws, azure_openai, cerebras, deepseek, fireworks, google, groq, moonshot, ollama, openai, perplexity, together, xai) or 'custom:{provider_id}:{model_name}' for a stored custom provider, e.g. 'openai:gpt-4o' or 'anthropic:claude-sonnet-4-5'.

streamboolean

temperaturenumber nullable

top_pnumber nullable

max_tokensinteger nullable

max_completion_tokensinteger nullable

frequency_penaltynumber nullable

presence_penaltynumber nullable

seedinteger nullable

ninteger nullable

{"stackTrail":"components:schemas:CreateChatCompletionRequestBody:properties:tool_choice:anyOf","oasType":"schema","type":"unknown","title":"Tool Choice","nullable":true}

response_formatobject nullable

Example request

{
  "messages": [
    {
      "content": "You are a helpful assistant.",
      "role": "system"
    },
    {
      "content": "Say hello.",
      "role": "user"
    }
  ],
  "model": "openai:gpt-4o"
}

Response

Successful Response

idstring required

object'chat.completion'

createdinteger required

modelstring required