Chat completions

POST /v1/chat/completions with OpenAI-compatible messages, tools, and streaming.

http

POST https://api.webway.sh/v1/chat/completions

Use this endpoint with OpenAI SDKs and clients that speak the Chat Completions protocol.

Request

bash

curl https://api.webway.sh/v1/chat/completions \
  -H "Authorization: Bearer $WEBWAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5.6-terra",
    "messages": [{"role": "user", "content": "Say hello."}],
    "max_tokens": 128
  }'

Field	Type	Notes
`model`	string	Required provider-qualified model ID
`messages`	array	Required `system`, `user`, and `assistant` messages
`max_tokens`	integer	Maximum generated tokens
`temperature`	number	Sampling temperature
`tools`	array	OpenAI-compatible function definitions
`tool_choice`	string or object	Controls tool selection
`stream`	boolean	Streams server-sent events when `true`

Provider-specific fields are passed through when the selected model supports them.

Response

json

{
  "id": "chatcmpl_01…",
  "object": "chat.completion",
  "model": "openai/gpt-5.6-terra",
  "choices": [
    {
      "index": 0,
      "message": {"role": "assistant", "content": "Hello!"},
      "finish_reason": "stop"
    }
  ],
  "usage": {"prompt_tokens": 9, "completion_tokens": 2, "total_tokens": 11}
}

With stream: true, each SSE data: line contains a chat.completion.chunk; the stream ends with data: [DONE].