Docs / LLM / Chat

LLM / Chat

RelayRouter serves chat models through a fully OpenAI-compatible API. If you already use the OpenAI SDK, change the base URL and API key; no other code changes are needed.

#Base URL

https://relayrouter.io/v1

#Example models

Model ID	Provider
claude-opus-4-8	Anthropic
gpt-5-5	OpenAI
deepseek-v4-flash	DeepSeek

Browse the full catalog on the Models page or via GET /v1/models.

#Python

main.pypython

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["RELAYROUTER_API_KEY"],
    base_url="https://relayrouter.io/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user",   "content": "Explain quantum computing in simple terms."},
    ],
    temperature=0.7,
    max_tokens=1024,
)
print(response.choices[0].message.content)

#Python: streaming

stream.pypython

stream = client.chat.completions.create(
    model="deepseek-v4-flash",
    messages=[{"role": "user", "content": "Write a short story about a robot."}],
    stream=True,
)
for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

#Node.js / TypeScript

index.tstypescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.RELAYROUTER_API_KEY,
  baseURL: "https://relayrouter.io/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user",   content: "Explain quantum computing in simple terms." },
  ],
});
console.log(response.choices[0].message.content);

#cURL

terminalbash

curl https://relayrouter.io/v1/chat/completions \
  -H "Authorization: Bearer $RELAYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-v4-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user",   "content": "Explain quantum computing in simple terms."}
    ],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

#Common parameters

Parameter	Type	Description
`model`	string	Model ID from your key's model list
`messages`	array	Chat messages with role (system \| user \| assistant) and content
`temperature`	number	Sampling temperature 0 to 2. Higher means more random
`max_tokens`	integer	Maximum tokens to generate
`stream`	boolean	If true, tokens are sent as SSE chunks
`top_p`	number	Nucleus sampling, alternative to temperature
`stop`	string \| array	Up to 4 stop sequences
`tools`	array	Tools the model may call (OpenAI tool-use schema)

Parameter support varies by model; unsupported parameters are ignored upstream. See the Chat Completions reference for request and response shapes.

←Overview Image Generation→