POST

/api/v1/chat/completions

Create a chat completion using any text model. Fully OpenAI-compatible.

Request Body

Parameter	Type	Description
`model` required	string	Model slug, e.g. "gpt-4o", "claude-sonnet-4-5-20250929"
`messages` required	object[]	Array of {role, content} message objects.
`temperature`	number	Sampling temperature (0-2).Default: `1`
`max_tokens`	number	Maximum output tokens.
`top_p`	number	Nucleus sampling (0-1).Default: `1`
`frequency_penalty`	number	Repeated token penalty (-2 to 2).Default: `0`
`presence_penalty`	number	Token presence penalty (-2 to 2).Default: `0`
`stop`	string \| string[]	Stop sequences.

Examples

javascript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "rw_live_xxxxx",
  baseURL: "https://railwail.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "gpt-4o",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
  temperature: 0.7,
  max_tokens: 500,
});

console.log(response.choices[0].message.content);

Response

JSON

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1700000000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello! How can I help you today?"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 20,
    "completion_tokens": 9,
    "total_tokens": 29
  }
}

Compatible Models

gpt-4o

gpt-4o-mini

claude-sonnet-4-5-20250929

claude-3-haiku

gemini-pro

gemini-1.5-flash

llama-3.1-70b

llama-3.1-8b

deepseek-chat

mistral-large

+ many more

Browse all available text models at /models.

PreviousConfiguration NextImage Generation