All available models on the Lyumen API. No auth required — just send requests.
| Model ID | Provider | Context |
|---|---|---|
| gemini-3-flash | 1M tokens | |
| minimax-m2.7 | MiniMax | 1M tokens |
Google's Gemini 3 Flash model — fast and capable. Great for general-purpose chat, code generation, and reasoning tasks. Supports a 1M token context window.
MiniMax's M2.7 model — strong multilingual performance with a massive context window. Suitable for long-form content and complex multi-turn conversations.