← All models
Gemini 3.8 Flash
gemini-3.8-flashgoogleAvailableReleased 2026-09-02Google's latest fast Gemini tier. 1M context window with reasoning support. Served through Antigravity credentials. Antigravity is a subscription product with no metered API price; the listed rate is a reference from Google's direct Gemini API and OpenRouter.
TextToolsThinkingThinking: low, medium, high
Pricing comparison
Each route's consumer price, and what multiple of the official list price it charges. Requests start at the cheapest route and only move to the next one when it fails, so you normally pay the top rate here. Lowest ready quote is marked. USD per million tokens.
| Route | Rate | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| Official | 1x | $0.750/M | $3.75/M | $0.075/M | $0.750/M(Same as Input) |
| MeridianLowest | 0.25x | $0.188/M | $0.938/M | $0.019/M | $0.188/M |
/v1/chat/completionsAvailableGuides and comparisons
- Choosing a Gemini model: five ids on one price ladder
- Gemini 3.1 Pro vs Gemini Flash: the price gap depends on which Flash
- Gemini 3.8 Flash vs 3.7 Flash: same rate, twice the multiplier
- Is grok-composer-2.5-fast cheap? What 0.2x of $3/$15 actually costs
- Largest context models: who reaches 1M, and what it costs to use it