Gemini 3.8 Flash
Google's workhorse model for coding and agents, with sharper multi-turn coding, rapid refactoring, code synthesis, and tighter tool-execution logic.
- Input price
- $0.675–$0.825list $0.7510% off
- Output price
- $3.375–$4.125list $3.7510% off
- Context
- 1M
- Max output
- 64K
- Capability
- 159 (#24 of 82)
- Human preference
- 1500
- 30-day uptime
- —
- Released
- 2026-09-02
- Knowledge cutoff
- 2026-03
Providers
Providers that serve this model. With Auto, each request goes to the best available provider. Prices in USD per 1M tokens; stats cover the last 30 days.
Pricing
Prices vary by provider. Showing Google Vertex AI, the lowest. Pick a provider above to see its prices.
| Item | Standard | Standard Discount | Flex | Flex Discount | Price | Price Discount | |||
|---|---|---|---|---|---|---|---|---|---|
| until 2027-01-01 | |||||||||
| Inputper 1M tokens | $0.675 | list $0.75 | 10% off | $0.3375 | list $0.375 | 10% off | — | ||
| Outputper 1M tokens | $3.375 | list $3.75 | 10% off | $1.6875 | list $1.875 | 10% off | — | ||
| Cache readper 1M tokens | $0.0675 | list $0.075 | 10% off | $0.033752 | list $0.0375 | 10% off | — | ||
| Reasoning outputper 1M tokens | $3.375 | list $3.75 | 10% off | $1.6875 | list $1.875 | 10% off | — | ||
| from 2027-01-01 | |||||||||
| Inputper 1M tokens | $1.35 | list $1.50 | 10% off | $0.675 | list $0.75 | 10% off | — | ||
| Outputper 1M tokens | $6.75 | list $7.50 | 10% off | $3.375 | list $3.75 | 10% off | — | ||
| Cache readper 1M tokens | $0.135 | list $0.15 | 10% off | $0.0675 | list $0.075 | 10% off | — | ||
| Reasoning outputper 1M tokens | $6.75 | list $7.50 | 10% off | $3.375 | list $3.75 | 10% off | — | ||
| Web searchper request | — | — | $0.0126 | list $0.014 | 10% off | ||||
| Estimated cost of common use (500 output tokens each) | |||||||||
| One chat message3K input tokens | $0.00372 | $0.00186 | — | ||||||
| Agent first turn100K tokens of context, none cached | $0.0692 | $0.0346 | — | ||||||
| Each later agent turncontext read from cache, plus 2K new tokens | $0.00979 | $0.0049 | — | ||||||
| 20-turn agent taskfirst turn plus 19 more | $0.255 | $0.128 | — | ||||||
Try it
Runs on your balance and is billed like any API request.
Similar models
Other models with the same output types at a similar price.
Human preference ratings are from the LMArena Text Arena (CC BY 4.0, as of 2026-11-18): Elo ratings from blind votes, on a different scale from capability scores. lmarena.ai/leaderboard/text