Google model product
Gemini 3.5 Flash Lite
5 Flash-Lite is Google's low-latency, cost-effective multimodal reasoning model for high-throughput agentic workflows, document processing, data extraction, translation, and classification.
Updated Aug 12, 2026. Default version: Gemini 3.5 Flash-Lite
LLMBoard score57.0Gemini 3.5 Flash-Lite
Coverage20%5 benchmark families
Context window1MTokens
Official input price$0.30Google API
Gemini 3.5 Flash Lite Specifications
Technical details for the model's default version.
- Version
- Gemini 3.5 Flash-Lite
- Released
- Jul 21, 2026
- Knowledge cutoff
- Mar 31, 2026
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- audio, image, pdf, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.5 Flash Lite Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 3.5 Flash Lite Benchmark Results
Benchmark scores for Gemini 3.5 Flash-Lite.
| MLE-Bench | 39.2% | 02 | 2 | 0.0% | C | |
| OSWorld-Verified | 74.0% | 12 | 23 | 50.0% | C | |
| MRCR v2 (8-needle) | 21.3% | 18 | 21 | 15.0% | C | |
| Terminal-Bench 2.1 | 54.0% | 18 | 19 | 5.6% | C | |
| CharXiv-R | 76.5% | 30 | 48 | 38.3% | C | |
| SWE-Bench Pro | 54.2% | 35 | 45 | 22.7% | C |
Gemini 3.5 Flash Lite Arena Results
Preference and agent-evaluation results for the default version.
| vision style control | overall | 32 | 1259.8 | 1,207 | N/A | |
| vision | overall | 37 | 1263.5 | 1,207 | N/A | |
| agent bash recovery steps | overall | 40 | -0.1 | N/A | 15.3K | |
| agent tool hallucination | overall | 40 | -0.0 | N/A | 228.1K | |
| agent praise complaint | overall | 41 | -0.1 | N/A | 2.3K | |
| agent | overall | 42 | -0.1 | N/A | 260.6K | |
| agent steerability | overall | 42 | -0.1 | N/A | 8.8K | |
| webdev | overall | 42 | 1449.9 | 227 | N/A | |
| agent task outcome explicit | overall | 45 | -0.1 | N/A | 6.1K | |
| text style control | overall | 48 | 1458.2 | 13,090 | N/A | |
| text factuality | overall | 55 | 1448.5 | 13,090 | N/A | |
| text | overall | 65 | 1437.0 | 13,090 | N/A |
Gemini 3.5 Flash Lite Runtime Performance
Provider-specific output speed and catalog latency for Gemini 3.5 Flash-Lite. Runtime does not affect the capability score.
| 101.091 tok/s | 3.907 s | 1M | 65.5K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 3.5 Flash Lite Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.30 input, $2.5 output per 1M
- Official provider
- Lowest third-party
- From $0.30 input, $2.5 output per 1M via Impossibl
- Tracked offerings
- 16
| Impossibl | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| CrossModel | gemini/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | ||
| NanoGPT | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| LLM Gateway | gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| OpenCode Zen | gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Neon | gemini-3-5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Pioneer | gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Vertex | gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Requesty | gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Kilo Gateway | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Merge Gateway | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Vercel AI Gateway | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| OpenRouter | google/gemini-3.5-flash-lite | global | $0.30 | $2.5 | 1M | |
| Cortecs | gemini-3.5-flash-lite | global | $0.33 | $2.75 | 1M | |
| Venice AI | gemini-3-5-flash-lite | global | $0.375 | $3.13 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini 3.5 Flash Lite Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemini 3.5 Flash-Lite | 57.0 | N/A | 1M | 65.5K | No | Proprietary |
What is Gemini 3.5 Flash Lite?
Key information about Gemini 3.5 Flash Lite and its available data.
5 Flash-Lite is Google's low-latency, cost-effective multimodal reasoning model for high-throughput agentic workflows, document processing, data extraction, translation, and classification. It supports text, image, video, audio, and PDF inputs, a 1 million-token context window, and a 65,536-token text output.
Data as of 2026-08-11.
Gemini 3.5 Flash Lite vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemini 3.5 Flash Lite
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemma 4 31B
GOGoogle
Gemma 4 26B A4B
GOGoogle
Gemini 3.1 Flash Lite
GOGoogle
Gemini 2.5 Pro
GOGoogle
Gemini 3 Flash
GOGoogle
Gemini 3 Pro
FAQ
Common questions about Gemini 3.5 Flash Lite.
When was Gemini 3.5 Flash Lite released?
Gemini 3.5 Flash Lite's default version was released on Jul 21, 2026.
How much does Gemini 3.5 Flash Lite cost?
Gemini 3.5 Flash Lite's official API price is $0.30 per million input tokens and $2.5 per million output tokens via Google. The lowest tracked third-party offer starts at $0.30 input and $2.5 output via Impossibl.
Who created Gemini 3.5 Flash Lite?
Gemini 3.5 Flash Lite was created by Google.
What is the context window for Gemini 3.5 Flash Lite?
The default version has a 1M token context window.
Is Gemini 3.5 Flash Lite open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemini 3.5 Flash Lite?
16 provider offerings are linked to the default version.
What models should I compare Gemini 3.5 Flash Lite with?
Nearby ranked alternatives include Qwen3.5 27B, Grok 4.20 Beta Reasoning, GLM 5V Turbo.