Quickstart

Mixen API is an OpenAI-compatible gateway to models for text, images, video, music, speech and embeddings. You pay from your Mixen balance in roubles, with no OpenAI, Google or Anthropic account needed.

If you already have code written against the OpenAI SDK, exactly two lines change — they are highlighted in the example below.

1. Get a key

Keys are issued in your account: mixen.ai/account/profile/api. The key is shown once, at creation — save it right away, only a hash is stored.

A key looks like mxn- followed by a random string.

2. Make your first call

The base URL is https://api.mixen.ai/v1.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.mixen.ai/v1",
    api_key="mxn-...",
)

resp = client.chat.completions.create(
    model="gpt-5.6-luna",
    messages=[{"role": "user", "content": "Explain recursion in one paragraph"}],
)
print(resp.choices[0].message.content)

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://api.mixen.ai/v1',
  apiKey: process.env.MIXEN_API_KEY,
})

const resp = await client.chat.completions.create({
  model: 'gpt-5.6-luna',
  messages: [{ role: 'user', content: 'Explain recursion in one paragraph' }],
})
console.log(resp.choices[0].message.content)

curl https://api.mixen.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.6-luna",
    "messages": [{"role": "user", "content": "Explain recursion in one paragraph"}]
  }'

3. See what else is available

GET /v1/models returns the live catalog: identifiers, prices in roubles and dollars, and what each model can do. No key required for this call.

curl https://api.mixen.ai/v1/models | jq '.data[0]'

Where to next

• Keys and authentication — scopes, rotation, safe storage.
• Models and pricing — picking a model and knowing what it costs.
• Chat and streaming — SSE, image input, files, reasoning effort.
• Integrations — Cursor, Cline, Open WebUI, LangChain with no code changes.

All endpoints

Endpoint	Purpose
GET /models	Model catalog with prices
POST /chat/completions	Chat, streaming, vision, files, web search
POST /images/generations	Image generation
POST /images/edits	Edit an image from a reference
POST /videos · GET /videos/{id} · GET /videos/{id}/content	Video (async job)
POST /videos/upscale	Video upscaling
POST /audio/music · GET /audio/music/{id} · GET /audio/music/{id}/content	Music (async job)
POST /audio/speech	Text to speech
POST /audio/transcriptions	Speech to text
POST /embeddings	Text embeddings

For an interactive reference with a request form, see the API Reference.