Provider
Google through one endpoint
5 Google models, billed at Google's own list price with nothing added - alongside every other provider on the same key, with routing and fallback between them.
Where your requests go, and what happens to them
The Gemini API endpoint we call is global, which in practice means processing outside the EU. Vertex AI offers European regions; that is a different integration and not this one.
Read on Google's own terms, last checked 2026-08-21 - their published policy. Recorded as a published position rather than a commitment we can make on their behalf, which is why the date is here.
The models, and what they cost
Gemini 4 Argon
google/gemini-4-argon$2 in · $10 out · 1,048,576 ctx
Reasoning · Huge context · Multimodal
Gemini 3.8 Flash
google/gemini-3.8-flash$0.75 in · $3.75 out · 1,048,576 ctx
Fast · Huge context · Multimodal
Gemini 3.5 Flash-Lite
google/gemini-3.5-flash-lite$0.3 in · $2.5 out · 1,048,576 ctx
Very fast · Cheap · Summarization
Gemini 2.5 Pro
Off by defaultgoogle/gemini-2.5-pro$1.25 in · $10 out · 1,048,576 ctx
Huge context · Multimodal
Gemini 2.5 Flash
Off by defaultgoogle/gemini-2.5-flash$0.3 in · $2.5 out · 1,048,576 ctx
Very fast · Long context · Summarization
You do not have to choose Google for everything
That is the point of a gateway: route the cheap work elsewhere, keep Google for what it is best at, and fall through to another provider when this one has a bad day - on one key, with one bill and one log.