Chat Completions

Use POST /chat/completions to send OpenAI-compatible chat requests through OpenModels.

Base URL:

https://api.getopenmodels.com/v1

Endpoint:

POST /chat/completions

Request

{
  "model": "qwen3.5-flash",
  "route": { "provider": "<provider-for-this-model>" },
  "route_mode": "balanced",
  "messages": [
    {
      "role": "system",
      "content": "You are a concise assistant."
    },
    {
      "role": "user",
      "content": "Explain OpenModels in one sentence."
    }
  ],
  "max_tokens": 256,
  "temperature": 0.7
}

Required fields:

Common optional fields:

Parameter support can vary by model and upstream provider. If a parameter is not supported by the selected model, choose a different model or remove the parameter.

Route selection

The examples on this page include optional route and route_mode fields so you can see where request-time routing controls belong. Remove both fields to use the default available route for the selected model.

To pin a request to a specific provider route, pass route.provider with a provider name you have confirmed in the Models table or OpenModels dashboard:

{
  "model": "qwen3.5-flash",
  "route": { "provider": "<provider-for-this-model>" },
  "route_mode": "balanced",
  "messages": [
    {
      "role": "user",
      "content": "Hello!"
    }
  ],
  "max_tokens": 256
}

Fixed provider routes are only sent to the selected provider. If the provider route is unavailable for that model, remove route or choose another provider route.

For application-level route groups created in the dashboard, pass the route:* ID as model instead. See Model Routes.

cURL

curl https://api.getopenmodels.com/v1/chat/completions \
  -H "Authorization: Bearer $OM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen3.5-flash",
    "route": { "provider": "<provider-for-this-model>" },
    "route_mode": "balanced",
    "messages": [
      {
        "role": "system",
        "content": "You are a concise assistant."
      },
      {
        "role": "user",
        "content": "Explain OpenModels in one sentence."
      }
    ],
    "max_tokens": 256,
    "temperature": 0.7
  }'

Python

import os
from openai import OpenAI
client = OpenAI(
    base_url="https://api.getopenmodels.com/v1",
    api_key=os.environ["OM_API_KEY"],
)
response = client.chat.completions.create(
    model="qwen3.5-flash",
    messages=[
        {
            "role": "system",
            "content": "You are a concise assistant.",
        },
        {
            "role": "user",
            "content": "Explain OpenModels in one sentence.",
        },
    ],
    max_tokens=256,
    temperature=0.7,
    extra_body={
        "route": {"provider": "<provider-for-this-model>"},
        "route_mode": "balanced",
    },
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";
const client = new OpenAI({
  baseURL: "https://api.getopenmodels.com/v1",
  apiKey: process.env.OM_API_KEY,
});
const response = await client.chat.completions.create({
  model: "qwen3.5-flash",
  route: { provider: "<provider-for-this-model>" },
  route_mode: "balanced",
  messages: [
    {
      role: "system",
      content: "You are a concise assistant.",
    },
    {
      role: "user",
      content: "Explain OpenModels in one sentence.",
    },
  ],
  max_tokens: 256,
  temperature: 0.7,
});
console.log(response.choices[0].message.content);

Response

Responses follow the OpenAI-compatible chat completions shape:

{
  "id": "chatcmpl_123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "OpenModels provides low-cost access to supported models through one OpenAI-compatible API key."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 18,
    "completion_tokens": 20,
    "total_tokens": 38
  }
}

Use the usage object to understand token consumption for the request. Credit spend is based on actual input and output token usage.