Gemini 3.5 Flash
- In Input modalities: TextImageVideoAudioPDF Out Output modalities: Text
- Reasoning· minimal, low, medium, high
- Tool use
- Structured output
Prices
3 offerings · prices as listedgemini-3.5-flash| Conditions/ 1M tokens | Input | Cache read | Output |
|---|---|---|---|
| Standard no longer listed since Oct 10, 2026 | $1.50 | $0.15 | $9.00 |
| Flex tier no longer listed since Oct 10, 2026 | $0.75 | $0.080 | $4.50 |
| Priority tier no longer listed since Oct 10, 2026 | $2.70 | $0.27 | $16.20 |
| Batch no longer listed since Oct 10, 2026 | $0.75 | $0.075 | $4.50 |
Prices from Gemini API pricing (opens in a new tab) (checked Oct 9, 2026)
Standard: the price a request with no conditions pays (the headline price elsewhere on the site).
Details
- Built-in tools
- Web search, Web fetch, Code execution, Computer use
- Knowledge cutoff
- Jan 2025
- Open weights
- —
- Family
- gemini-flash
- Model ID
Not stated on Google’s pages: max input, reasoning can be off, max thinking budget, aliases.
Cited scores
From third-party leaderboards, not measured by us- Epoch Capabilities Index 155.2
#40 of 118 listed models · CI 153.4–157.2
- LMArena Text 1,478
#25 of 163 listed models · high effort · CI 1,474–1,482 · 47,646 votes
Also listed: medium effort 1,476
- Epoch AI · Chess Puzzles 45%
#28 of 85 listed models · high effort · ±5
Also listed: low effort 42% · minimal effort 27%
- Epoch AI · EBR-bench 4.8%
#26 of 28 listed models · high effort
- Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks'. Licensed CC BY 4.0. · License · as of Oct 7 – Nov 5, 2026
- LMArena (Arena), leaderboard-dataset on Hugging Face, licensed CC BY 4.0 · License · as of Nov 8, 2026
- EQ-Bench by Samuel J. Paech (eqbench.com; EQ-bench/EQ-bench-site on GitHub), MIT License. · License · as of Oct 24 – 28, 2026
- LiveBench (White et al.), release 2026-06-25, livebench.ai, licensed CC BY-SA 4.0. This board, adapted from it, is shared under CC BY-SA 4.0. · License · as of Jun 25, 2026
- changes we made
Provider-reported scores
Published by Google, under the conditions it states| Benchmark | Setting | Score |
|---|---|---|
| Terminal-Bench 2.1 | Terminus-2 harness, pass@1 | 76.2% |
| OSWorld-Verified | average of 5 runs, single attempt, max 100 steps | 78.4% |
| CharXiv Reasoning | no tools | 84.2% |
| MMMU-Pro | no tools, average of Standard (10 options) and Vision | 83.6% |
| Humanity's Last Exam | full set, text + MM | 40.2% |
News
All news →- Oct 8, 2026Retirement Google deprecates Gemini 3.5 Flash Google deprecated gemini-3.5-flash and replaced it with gemini-3.6-flash. Requests to the deprecated model are automatically routed to the replacement.
Changes
All changes →- Available → Deprecated
Sources
- Gemini 3.5 Flash model card (opens in a new tab) deepmind.google · checked Sep 26, 2026
- Gemini API pricing (opens in a new tab) ai.google.dev · checked Oct 9, 2026
- Gemini 3.5 Flash model (opens in a new tab) ai.google.dev · checked Nov 8, 2026
- Gemini API changelog (opens in a new tab) ai.google.dev · checked Nov 8, 2026
- models.dev: gemini-3.5-flash (community data, MIT) (opens in a new tab) github.com · checked Sep 30, 2026
- What's new in Gemini 3.5 Flash | Gemini API | Google AI for Developers (opens in a new tab) ai.google.dev · checked Nov 6, 2026
- Gemini API deprecations (opens in a new tab) ai.google.dev · checked Nov 4, 2026
- Gemini 3.5 Flash | Gemini Enterprise Agent Platform | Google Cloud Documentation (opens in a new tab) docs.cloud.google.com · checked Nov 10, 2026
- Vertex AI generative AI pricing (opens in a new tab) cloud.google.com · checked Nov 5, 2026
Google’s official policies: data use, privacy, terms →
Some values on this page are still waiting to be checked against official pages: a filled dot is verified, a hollow one is not yet (with or without a source on file). How we verify data
Google · United States · ai.google.dev
Related models
Snapshots, the same family and other models from this provider