Chat Completions

Create Chat Completion

Generate a model response for the given conversation.

POST /v1/chat/completions

Request Headers

Header	Required	Description
`Authorization`	Yes	`Bearer sk-r9k-your-key`
`Content-Type`	Yes	`application/json`

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID — a provider-prefixed slug from `GET /v1/models` (e.g. `anthropic/claude-opus-5`), not a short name like `gpt-4o`
`messages`	array	Yes	Conversation messages
`stream`	boolean	No	Enable streaming (default: `false`)
`temperature`	number	No	Sampling temperature (0-2)
`max_tokens`	number	No	Maximum tokens to generate

Model ids are provider-prefixed slugs, not short aliases. gpt-4o or claude-3-sonnet return 404 model_not_found unless your deployment has configured a matching route — see Models.

Messages Format

{
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Hello!" }
  ]
}

Example Request

curl https://api.router9.com/v1/chat/completions \
  -H "Authorization: Bearer sk-r9k-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5",
    "messages": [
      { "role": "user", "content": "Explain quantum computing in one sentence." }
    ]
  }'

Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1714000000,
  "model": "anthropic/claude-opus-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Quantum computing uses quantum mechanical phenomena like superposition and entanglement to process information in ways classical computers cannot."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 15,
    "completion_tokens": 28,
    "total_tokens": 43
  }
}

Streaming

Set stream: true to receive responses as Server-Sent Events (SSE).

curl https://api.router9.com/v1/chat/completions \
  -H "Authorization: Bearer sk-r9k-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-5",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'

The response is a stream of data: lines:

data: {"id":"chatcmpl-abc","choices":[{"delta":{"role":"assistant"},"index":0}]}

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"id":"chatcmpl-abc","choices":[{"delta":{"content":"!"},"index":0}]}

data: [DONE]

Token usage is included in the final chunk before [DONE].

If your administrator has configured an auto route, setting model to "auto" lets Router9 pick a model for you. auto is not a built-in alias — on a deployment with no auto route, this returns 404 model_not_found. See Models for how to check whether it's available.

{
  "model": "auto",
  "messages": [{ "role": "user", "content": "Hello!" }]
}