Models
19 models from 5 providers, on one OpenAI-compatible endpoint.
Google: Gemini 3.1 Flash Lite
FlashfastbudgetFlashLightest Gemini. Classification, extraction, bulk transforms.
eaon/gemini-3.1-flash-lite1M contextFree, Go, Plus, Pro, MaxGoogle: Gemini 3 Flash
Flashlong contextfastFlashGemini 3 generation Flash. Long context, flash pricing.
eaon/gemini-3-flash1M contextFree, Go, Plus, Pro, MaxGoogle: Gemini 3.7 Flash
Flashlong contextfastFlash3.7 Flash for tools that pin that revision. Same economics.
eaon/gemini-3.7-flash1M contextFree, Go, Plus, Pro, MaxGoogle: Gemini 3.8 Flash
Flashlong contextfastFlashA million tokens of context for the price of a rounding error.
eaon/gemini-3.8-flash1M contextFree, Go, Plus, Pro, MaxGoogle: Gemini 3.1 Pro Preview
Standardreasoninglong contextStandardPreview Pro. Strong multimodal reasoning before it hardens.
eaon/gemini-3.1-pro-preview1M contextGo, Plus, Pro, Max
Showing 5 of 19 models. Every call bills its real token cost against your plan's usage grant.