Gemini 3.5 Flash-Lite benchmarks, pricing and specs
Gemini 3.5 Flash-Lite is a Google model released on July 21, 2026 that takes text, image, audio and video input and produces text. It costs $0.30 per 1M input tokens and $2.50 per 1M output tokens and accepts up to 1,048,576 tokens of context. It scores 1455 Elo on Arena Text, #27 of 39 current models (Arena, measured October 8, 2026).
- Per 1M input tokens
- $0.30
- Per 1M output tokens
- $2.50
- Context window
- 1.05M
- Arena Text
- 1455 Elo · #27/39
Data verified October 12, 2026 · Dataset 2026-10-12
Key facts
- Provider
- Model family
- Gemini 3.5
- Release date
- July 21, 2026
- Status
- Current
- Access
- API only
- API model id
- Not reported
- Context window
- 1,048,576 tokens
- Max output
- 65,536 tokens
- Input
- text, image, audio, video
- Output
- text
- Task families
- text, multimodal
- Declared capabilities
- reasoning
Gemini 3.5 Flash-Lite pricing
It is the #6 cheapest of 37 current text models priced per 1M input tokens.
Independent benchmark results
Scores come from independent evaluators that ran the model themselves, pinned to a dated snapshot. Rank is among current models in the same snapshot. Google's own launch figures are listed under strengths with the publisher named, because they are not measured the same way.
| Benchmark | Score | Rank | Measured | Source |
|---|---|---|---|---|
| Arena Text | 1455 Elo | #27 of 39 | October 8, 2026 | Arena · 2026-10-12 |
| GPQA Diamond | 83.3% | #32 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
| FrontierMath Tiers 1-3 (v2) | 26% | #34 of 37 | October 12, 2026 | Epoch AI · 2026-10-12 |
Strengths, cautions and best uses
Strengths
- Gemini 3.5 Flash-Lite is optimized for high-throughput, low-cost execution of subagent tasks and document parsing
- Reads text, images, video, audio and PDF in a 1,048,576-token window with 65,536 output tokens, and supports thinking, function calling, code execution, search grounding and caching
Cautions
- The represented prices are standard API rates; batch, flex, and priority consumption use different rates
Best for
- High-volume extraction, structured parsing, and cost-sensitive subagent trials
Alternatives to Gemini 3.5 Flash-Lite
The closest current textmodels by price. The cheapest model that scores as well or better is listed first; failing that, the cheapest one within 3% of the benchmark's scale.
Cheaper, similar score
GPT-6 Luna
- 67% cheaper per 1M input tokens, $0.10 vs $0.30
- 12 points lower on Arena Text, 1443 vs 1455
- From OpenAI
DeepSeek-V4.1-Flash
- Same price per 1M input tokens, $0.30
- 20 points higher on Arena Text, 1475 vs 1455
- From DeepSeek
Gemini 3.1 Flash-Lite
- 17% cheaper per 1M input tokens, $0.25 vs $0.30
- 1.5 points lower on GPQA Diamond, 81.8 vs 83.3
GPT-4.1 mini
- 33% more per 1M input tokens, $0.40 vs $0.30
- 72 points lower on Arena Text, 1383 vs 1455
- From OpenAI
Compare Gemini 3.5 Flash-Lite with
Other Gemini 3.5 models
Gemini 3.5 Flash-Lite FAQ
How much does Gemini 3.5 Flash-Lite cost?
Gemini 3.5 Flash-Lite costs $0.30 per 1M input tokens and $2.50 per 1M output tokens at the standard tier. It is the #6 cheapest of 37 current text models priced per 1M input tokens. Source: Google, verified August 7, 2026.
What is the context window of Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash-Lite accepts up to 1,048,576 tokens of context. It can return up to 65,536 tokens in one response. That ranks #10 of 44 current text models by context length.
How does Gemini 3.5 Flash-Lite score on independent benchmarks?
Gemini 3.5 Flash-Lite scores 1455 Elo on Arena Text, #27 of 39 current models (Arena, measured October 8, 2026), 83.3% on GPQA Diamond, #32 of 37 current models (Epoch AI, measured October 12, 2026) and 26% on FrontierMath Tiers 1-3 (v2), #34 of 37 current models (Epoch AI, measured October 12, 2026). These are independent evaluations, not Google's own launch figures.
Is Gemini 3.5 Flash-Lite open source or API only?
Gemini 3.5 Flash-Lite is available through Google's API only; its weights are not published.
What are the best alternatives to Gemini 3.5 Flash-Lite?
The closest current alternatives by price and measured performance are GPT-6 Luna (67% cheaper per 1M input tokens, $0.10 vs $0.30), DeepSeek-V4.1-Flash (same price per 1M input tokens, $0.30), Gemini 3.1 Flash-Lite (17% cheaper per 1M input tokens, $0.25 vs $0.30) and GPT-4.1 mini (33% more per 1M input tokens, $0.40 vs $0.30).
Sources
- Gemini 3.5 Flash-Lite model · Google · official · verified August 7, 2026 · CC-BY-4.0
- Gemini 3.5 Flash-Lite pricing · Google · official · verified August 7, 2026 · CC-BY-4.0
- Gemini API release notes · Google · official · verified August 18, 2026 · CC-BY-4.0
- Epoch AI Benchmarking Hub data (benchmark_data.zip) · Epoch AI · independent · verified October 12, 2026 · CC-BY-4.0
- Arena leaderboard dataset (lmarena-ai/leaderboard-dataset) · Arena · independent · verified October 12, 2026 · CC-BY-4.0
Cite this page
Van Data Team. "Gemini 3.5 Flash-Lite Benchmarks, Pricing and Specs." AI Model Benchmark Dataset 2026-10-12. https://vandatateam.com/ai-model-benchmarks/gemini-3-5-flash-lite
Reuse the data: JSON · CSV · or explore every model in the AI model benchmark comparison.
Production evaluation
Deciding whether Gemini 3.5 Flash-Lite fits your workload?
Public benchmarks narrow the shortlist. We test the finalists on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- Evaluation cases and acceptance thresholds tied to real work
- Model routing, fallbacks and cost controls