Chat Completions

The main endpoint for interacting with language models.

POST /v1/chat/completions

Request Parameters

Parameter	Type	Description
model	string	Required. Model ID (e.g., gpt-4o).
messages	array	Required. Array of conversation messages. Each message contains role (user, assistant, system) and content.
stream	boolean	Whether to send the response in chunks as it's generated (Server-Sent Events).

The gateway automatically detects the need for streaming by the presence of the stream: true flag in the JSON.

Basic Request Example

{
  "model": "gpt-4o-mini",
  "messages": [
    { "role": "system", "content": "You are a helpful assistant." },
    { "role": "user", "content": "Tell me a joke." }
  ],
  "stream": false
}

---

Streaming Mode (SSE)

For interactive real-time output, set "stream": true. The gateway automatically injects stream_options: {"include_usage": true} so that the final chunk contains accurate token usage statistics.

Python (Streaming)

from openai import OpenAI

client = OpenAI(
    api_key="sk-or-your-key",
    base_url="https://api.rawrter.com/v1",
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Write a short poem."}],
    stream=True,
    stream_options={"include_usage": True},
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
    
    if chunk.usage:
        print(f"\n\n[Tokens Used: {chunk.usage.total_tokens}]")

Node.js (Streaming)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-or-your-key",
  baseURL: "https://api.rawrter.com/v1",
});

async function main() {
  const stream = await client.chat.completions.create({
    model: "gpt-4o",
    messages: [{ role: "user", content: "Write a short poem." }],
    stream: true,
    stream_options: { include_usage: true },
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || "");
    if (chunk.usage) {
      console.log(`\n\n[Tokens Used: ${chunk.usage.total_tokens}]`);
    }
  }
}

main();

---

Retry and Failover

The Rawrter gateway includes a built-in failover mechanism. If the selected node returns a network error or a status >= 400 before data transmission begins (the first byte of the response), the gateway will automatically exclude the problematic node and retry the request on another available node without interrupting your request execution.