Google Gemini models in ClawAI

What the Gemini lineup covers

Google’s current lineup has three tiers: Gemini 2.5 Pro for the most demanding requests, Gemini 2.5 Flash as the general-purpose middle tier, and Gemini 2.5 Flash-Lite as the fast, lower-cost option. ClawAI’s router can move between them per request.

When a task suits a Gemini model

Gemini models are commonly reached for for tasks with a large amount of source material to work through, since the family is built around long-context handling. Whether a given tier is the right fit for your specific workload is worth checking yourself — see how to evaluate AI models below for a repeatable method rather than a one-line claim.

How ClawAI routes to it

ClawAI’s router can send a request to a Gemini model automatically under Auto or Cost Saver routing, or you can pin one under Manual Model mode. Gemini’s published pricing rises above a long-context threshold that this page’s cost band does not attempt to model — a single qualitative band is not precise enough to express a tiered rate, so treat it as a starting point, not a bill.

Questions people ask

Does ClawAI have a direct partnership with Google?

No. ClawAI connects to the Gemini API the same way any application with an API key would.

Which Gemini model handles long documents best?

The family is generally built for long-context handling across the tiers; the exact limit and cost depend on the specific model and request. Check the live catalog rather than assume a fixed number.

Is Gemini 2.5 Pro available on every plan?

Model availability is enforced by your plan and the live catalog, not by this page. Confirm the current lineup on the pricing page before choosing a plan for a specific model.