Reference

PreviousExamples NextUsing Crosshatch in Cursor

Last updated 5 months ago

Creates a model response for the given chat conversation.

post

/chat/completions

Authorizations

Body

streamboolean | nullable

If set, partial message deltas will be sent. Tokens will be sent as data-only server-sent events as they become available, with the stream terminated by a data: [DONE] message.

messagesone of[]required

A list of messages comprising the conversation so far.

modelany ofrequired

ID of the model to use.

Example: lmsys-coding

Responses

application/json

cURL

JavaScript

Python

HTTP

curl -L \
  --request POST \
  --url 'https://api.crosshatch.app/v1/chat/completions' \
  --header 'Authorization: Bearer YOUR_SECRET_TOKEN' \
  --header 'Content-Type: application/json' \
  --data '{"stream":false,"messages":[{"role":"system"}],"model":"lmsys-coding"}'

200

{
  "id": "text",
  "created": 1,
  "model": "text",
  "usage": {
    "completion_tokens": 1,
    "prompt_tokens": 1,
    "total_tokens": 1
  },
  "object": "chat.completion",
  "choices": [
    {
      "index": 1,
      "message": {
        "content": "text",
        "refusal": "text",
        "role": "assistant"
      },
      "finish_reason": "stop"
    }
  ]
}

Lists the currently available models, and provides basic information about each one such as the owner and availability.

get

/models