Models

Models

The LivRouter catalog groups models by provider family — currently including Claude, GPT, Grok, DeepSeek, GLM, Kimi, Gemini, Qwen, Mimo, and MiniMax — all behind one endpoint. Model IDs are kebab-case strings such as claude-opus-5, gpt-6-sol, glm-5.3, and deepseek-v4-flash; the live model catalog and each model's pricing page always show the exact current ID to use.

You choose a model per request with the model parameter — the endpoint and API key stay the same, so switching models is a one-line change. If your workflow needs vision, audio, embeddings, or moderation, pick a model that the current catalog explicitly marks as supporting the requested endpoint; capability support varies by model.

Most models are billed per token, with rates published per 1M input tokens on each model page; some catalog entries bill per request instead. Every request draws from your prepaid credits — see plans and billing for credits, subscriptions, and how plan rates apply.

List the model IDs available to your key at any time:

python
from openai import OpenAI client = OpenAI(    base_url="https://api.livrouter.com/v1") models = client.models.list() for model in models.data:    print(model.id)