Gemini 3.8 Flash pricing

Model id gemini-3.8-flash. Verified against the provider's published price; registry row retrieved 2026-09-11 from ai.google.dev.

USD per 1M tokens. A dash means the provider publishes no rate for that dimension, so the proxy declines to price it.

• Endpoint classes: global.
• on_demand: the standard rate.
• batch: 50% below the standard rate.
• No long-context tier: the standard rate applies at any prompt size.

What does a cache read cost on Gemini 3.8 Flash?

A cache-read token on Gemini Developer API costs $0.075 per 1M tokens, against $0.75 for an ordinary input token. An ordinary input token costs 10 times as much. No cache-write rate is published for this model.

Does Gemini 3.8 Flash have a batch price?

Yes: batch: 50% below the standard rate. The batch rate applies to the whole request; the proxy prices a batch call from the same row with that factor applied.

• AI token calculator — every priced model, with cache writes and monthly volume
• Gemini API proxy — route Gemini 3.8 Flash calls through Vigil
• LLM token cost — LLM token cost is a function, not a number
• prompt caching providers — Prompt caching providers: inject, steer or observe
• LLM model aliases — LLM model aliases, and the rates that don't resolve
• LLM observability pricing — what Vigil itself costs