Gemini 3.8 Flash API pricing and specs
Google's most capable model in the public Gemini API, with function calling, computer use in preview, code execution and grounding in Search and Maps.
Output price includes thinking tokens. Search grounding gives 5,000 free queries a month across Gemini 3.x models, then costs $14 per thousand. The 'minimal' thinking level returns an error.
This is an introductory price. From January 1, 2027 the list price becomes $1.50 input, $0.15 cached and $7.50 output per million tokens.
Spec sheet
- API model string
gemini-3.8-flash- Provider
- Context
- 1.05M tokens
- Max output
- 66K tokens
- Released
- September 2, 2026
- Batch API
- 50% off, results within hours
- Documented agent features
- Tool callingStructured outputComputer useBuilt-in web searchAdjustable reasoning
What a task costs
Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.
| Workload | Per task | Per 1,000 tasks |
|---|---|---|
| Support bot | $0.021 | $21 |
| Coding agent | $0.742 | $742 |
| Browser agent | $0.524 | $524 |
| Research agent | $0.496 | $496 |
Other Google models
Similar cost elsewhere
Models from other providers whose cost on the 30-step coding workload is closest to this one.