Models and pricing

The catalog comes from GET /v1/models. No key required — you can call it from your frontend to show users a current list.

curl https://api.mixen.ai/v1/models

The catalog holds around a hundred models across every modality. Both the line-up and the prices change, so read them from the API rather than from this page.

Response shape

{
  "object": "list",
  "data": [
    {
      "id": "anthropic/claude-opus-4.8",
      "object": "model",
      "owned_by": "mixen",
      "type": "text",
      "display_name": "Claude Opus 4.8",
      "pricing": {
        "prompt_rub": 527.6,
        "completion_rub": 2637.8,
        "prompt_usd": 6.0,
        "completion_usd": 30.0,
        "currency_note": "per 1M tokens"
      },
      "capabilities": {
        "vision": true,
        "file": true,
        "reasoning": true,
        "reasoning_efforts": ["low", "medium", "high", "xhigh", "max"],
        "can_disable_reasoning": true
      }
    }
  ]
}

The type field tells you which endpoint accepts the model:

type	Endpoint	Priced per
text	/chat/completions	1M tokens
search	/chat/completions	1M tokens
image	/images/generations, /images/edits	image
video	/videos	second of video
music	/audio/music	request
tts	/audio/speech	1000 input characters
stt	/audio/transcriptions	minute of audio
embeddings	/embeddings	1M input tokens

The unit is always spelled out in pricing.currency_note, so a client never has to infer it from the model type.

Image and video models carry extra fields with the values they accept: aspect_ratios, resolutions, sizes, seconds, and references (how many reference images the model takes). Read them from the catalog instead of guessing — anything else returns 400. Speech models carry a voices list.

Naming a model in a request

The model field accepts:

• the full catalog identifier — openai/gpt-5.6-luna;
• the short suffix — gpt-5.6-luna;
• a familiar name from another vendor — gpt-4o, claude-opus, dall-e-3, gpt-image-1, whisper-1, tts-1, text-embedding-3-small, sora-2.

Those aliases exist so a drop-in swap works: code written for OpenAI runs unchanged and lands on a comparable Mixen model. If nothing matches, the response is a 404 listing similar identifiers.

How prices are calculated

Rouble prices are not static — they are derived from the upstream cost:

price ₽ = upstream $ × USD/RUB rate × (1 + margin)

The exchange rate comes from a live quote and updates on its own, so prompt_rub can differ week to week while prompt_usd stays put. You are charged exactly what the catalog shows at the time of the request — no hidden multipliers.

Charges come off your Mixen balance, the same one the bot and the web account use.

Human-readable catalog

A browsable catalog with filters, descriptions and sample output lives at api.mixen.ai/models. It also shows which models accept images, take files, and support reasoning effort.