Quickstart

Modellane serves unrestricted language models for red teams, trust and safety, synthetic data, and fiction and character chat, alongside standard models. Models whose ID contains -unrestricted are unrestricted; the others are standard. We add no refusal or moderation layer of our own to any model: you apply your own product policy, and every request is covered by the Acceptable Use Policy.

  1. Get an API key: Create one in the console and keep it in an environment variable.
  2. Set the base URL: Point your SDK at the Modellane endpoint; the table below lists the values.
  3. Send a request: Call the chat API in curl, Python or Node.js.

The API speaks the OpenAI Chat Completions format, so any OpenAI SDK or tool that lets you set a base URL works without code changes. You need three values:

ParamValue
base_urlhttps://usemodellane.com/v1
api_keyA key from API keys in your dashboard
modeldeepseek-v4.1-flash (see Models & pricing for every model)

The same key and models also work in two more request formats. Use the one your SDK or tool speaks; prices and limits are the same in all three.

FormatBase URLEndpoint
OpenAI Chat Completions (default)https://usemodellane.com/v1POST /v1/chat/completions
OpenAI Responseshttps://usemodellane.com/v1POST /v1/responses
Anthropic Messageshttps://usemodellane.comPOST /v1/messages

The Anthropic SDKs add /v1 themselves, so their base URL has no /v1 at the end. See the Anthropic Messages API and Responses API guides for what each format supports.

Coding agents, chat apps and agent frameworks need the same values. Integrations has ready-made settings for Codex, Claude Code, Cline, the OpenAI and Anthropic SDKs, LangChain and more.

Invoke the chat API#

Once you have a key, send a chat completion request. The examples below use the official OpenAI SDKs with only the base URL and key changed. Each one sends a system and a user message and prints the reply.

curl

curl https://usemodellane.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $MODELLANE_API_KEY" \
  -d '{
    "model": "deepseek-v4.1-flash",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Hello!"}
    ],
    "stream": false
  }'

Python

# pip install openai
import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MODELLANE_API_KEY"],
    base_url="https://usemodellane.com/v1",
)

response = client.chat.completions.create(
    model="deepseek-v4.1-flash",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Hello!"},
    ],
    stream=False,
)

print(response.choices[0].message.content)

Node.js

// npm install openai
import OpenAI from "openai"

const client = new OpenAI({
  apiKey: process.env.MODELLANE_API_KEY,
  baseURL: "https://usemodellane.com/v1",
})

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "Hello!" },
  ],
  stream: false,
})

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

Stream the reply#

The examples return the whole reply at once. Set stream to true to receive it token by token as server-sent events instead; the SDKs then return an iterator. Add stream_options: {"include_usage": true} to get the token usage in a final chunk before the done marker. The Streaming responses guide covers the event format.

Next steps#