Google model product
Gemini 3.5 Flash Lite
5 Flash Lite is Google's low-latency, cost-effective multimodal reasoning model for agentic workflows, document processing, data extraction, translation, and classification.
Updated Sep 8, 2026. Default version: Gemini 3.5 Flash-Lite
LLMBoard Score53.7Gemini 3.5 Flash-Lite
Coverage0%5 benchmark families
Context window1MTokens
Official input price$0.30Google API
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.
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkMLE-Bench | Score39.20% | Rank02 | Participants2 | Percentile0.00% | EvidenceC | Evaluated |
| BenchmarkOSWorld-Verified | Score74.00% | Rank13 | Participants24 | Percentile47.83% | EvidenceC | Evaluated |
| BenchmarkMRCR v2 (8-needle) | Score21.30% | Rank21 | Participants24 | Percentile13.04% | EvidenceC | Evaluated |
| BenchmarkLM Arena Vision Style Control | Score1,266.42 rating | Rank24 | Participants107 | Percentile78.30% | EvidenceA | Evaluated |
| BenchmarkLM Arena Vision | Score1,268.89 rating | Rank28 | Participants107 | Percentile74.53% | EvidenceA | Evaluated |
| BenchmarkTerminal-Bench 2.1 | Score54.00% | Rank31 | Participants35 | Percentile11.76% | EvidenceC | Evaluated |
| BenchmarkCharXiv-R | Score76.50% | Rank37 | Participants55 | Percentile33.33% | EvidenceC | Evaluated |
| BenchmarkSWE-Bench Pro | Score54.20% | Rank41 | Participants55 | Percentile25.93% | EvidenceC | Evaluated |
| BenchmarkLM Arena Text Style Control | Score1,456.93 rating | Rank42 | Participants210 | Percentile80.38% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Bash Recovery Steps | Score-16.30% | Rank43 | Participants49 | Percentile12.50% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Tool Hallucination | Score-0.87% | Rank44 | Participants49 | Percentile10.42% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text Factuality | Score1,449.51 rating | Rank44 | Participants121 | Percentile64.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Leaderboard | Score-11.64% | Rank45 | Participants49 | Percentile8.33% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Steerability | Score-9.15% | Rank45 | Participants49 | Percentile8.33% | EvidenceA | Evaluated |
| BenchmarkLM Arena Webdev | Score1,449.01 rating | Rank45 | Participants97 | Percentile54.17% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Praise Complaint | Score-15.43% | Rank48 | Participants49 | Percentile2.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Agent Task Outcome Explicit | Score-16.44% | Rank48 | Participants49 | Percentile2.08% | EvidenceA | Evaluated |
| BenchmarkLM Arena Text | Score1,436.42 rating | Rank59 | Participants210 | Percentile72.25% | EvidenceA | Evaluated |
Gemini 3.5 Flash Lite Arena Results
Preference and agent-evaluation results for the default version.
Sort by
Arena | Category | Rank | Rating / score | Votes | Observations | Result date |
|---|
| Arenavision | Categorydiagram | Rank23 | Rating / score1,291.72 | Votes987 | ObservationsN/A | Result date |
| Arenavision style control | Categorydiagram | Rank23 | Rating / score1,299.86 | Votes987 | ObservationsN/A | Result date |
| Arenavision style control | Categoryoverall | Rank24 | Rating / score1,266.42 | Votes3,886 | ObservationsN/A | Result date |
| Arenavision style control | Categoryenglish | Rank25 | Rating / score1,263.16 | Votes1,335 | ObservationsN/A | Result date |
| Arenavision style control | Categoryocr | Rank25 | Rating / score1,278.61 | Votes2,608 | ObservationsN/A | Result date |
| Arenavision style control | Categorycreative writing vision | Rank26 | Rating / score1,251.93 | Votes344 | ObservationsN/A | Result date |
| Arenawebdev | Categoryimage to webdev | Rank27 | Rating / score1,443.79 | Votes1,269 | ObservationsN/A | Result date |
| Arenatext | Categoryjapanese | Rank28 | Rating / score1,420.78 | Votes348 | ObservationsN/A | Result date |
| Arenavision | Categoryocr | Rank28 | Rating / score1,277.33 | Votes2,608 | ObservationsN/A | Result date |
| Arenavision | Categoryoverall | Rank28 | Rating / score1,268.89 | Votes3,886 | ObservationsN/A | Result date |
| Arenatext style control | Categoryfrench | Rank29 | Rating / score1,486.72 | Votes746 | ObservationsN/A | Result date |
| Arenatext style control | Categoryjapanese | Rank29 | Rating / score1,439.55 | Votes348 | ObservationsN/A | Result date |
| Arenavision style control | Categoryhomework | Rank30 | Rating / score1,280.95 | Votes299 | ObservationsN/A | Result date |
| Arenatext style control | Categorypolish | Rank31 | Rating / score1,467.59 | Votes317 | ObservationsN/A | Result date |
| Arenavision | Categorycreative writing vision | Rank31 | Rating / score1,254.92 | Votes344 | ObservationsN/A | Result date |
| Arenavision | Categoryhomework | Rank31 | Rating / score1,282.15 | Votes299 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryfrench | Rank32 | Rating / score1,475.18 | Votes468 | ObservationsN/A | Result date |
| Arenatext | Categorypolish | Rank33 | Rating / score1,446.03 | Votes317 | ObservationsN/A | Result date |
| Arenatext style control | Categorygerman | Rank33 | Rating / score1,463.81 | Votes411 | ObservationsN/A | Result date |
| Arenatext style control | Categorykorean | Rank34 | Rating / score1,420.48 | Votes430 | ObservationsN/A | Result date |
| Arenatext style control | Categoryrussian | Rank34 | Rating / score1,466.85 | Votes2,213 | ObservationsN/A | Result date |
| Arenavision | Categoryenglish | Rank34 | Rating / score1,264.87 | Votes1,335 | ObservationsN/A | Result date |
| Arenatext | Categorygerman | Rank35 | Rating / score1,449.94 | Votes411 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry life and physical and social science | Rank35 | Rating / score1,482.31 | Votes3,636 | ObservationsN/A | Result date |
| Arenavision style control | Categorychinese | Rank35 | Rating / score1,286.71 | Votes169 | ObservationsN/A | Result date |
| Arenatext | Categorykorean | Rank37 | Rating / score1,405.45 | Votes430 | ObservationsN/A | Result date |
| Arenatext factuality | Categoryrussian | Rank37 | Rating / score1,459.18 | Votes1,891 | ObservationsN/A | Result date |
| Arenavision | Categorychinese | Rank37 | Rating / score1,293.28 | Votes169 | ObservationsN/A | Result date |
| Arenatext style control | Categoryindustry business and management and financial operations | Rank38 | Rating / score1,460.61 | Votes4,144 | ObservationsN/A | Result date |
| Arenatext style control | Categorynon english | Rank38 | Rating / score1,448.76 | Votes12,907 | ObservationsN/A | Result date |
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 $0.15 input, $1.25 output per 1M via Kilo Gateway
- Tracked offerings
- 21
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderKilo Gateway | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.15 | Output / 1M$1.25 | Context1M | Updated |
| ProviderOrcaRouter | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderNanoGPT | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderVertex | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderGoogle | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderImpossibl | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderOpenRouter | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderCrossModel | Provider model IDgemini/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderOpper | Provider model IDgemini/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderMerge Gateway | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderOfox | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderNeon | Provider model IDgemini-3-5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderOpenCode Zen | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderRequesty | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderVercel AI Gateway | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderEden AI | Provider model IDgoogle/gemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderDevPass (LLM Gateway) | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderPioneer | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderAbacus | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.30 | Output / 1M$2.5 | Context1M | Updated |
| ProviderCortecs | Provider model IDgemini-3.5-flash-lite | Regionglobal | Input / 1M$0.33 | Output / 1M$2.75 | Context1M | Updated |
| ProviderVenice AI | Provider model IDgemini-3-5-flash-lite | Regionglobal | Input / 1M$0.375 | Output / 1M$3.13 | Context1M | Updated |
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.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderGoogle | Output Speed21.45 tok/s | Catalog Latency2.04 s | Max Input1M | Max Output65.5K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
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, text, video
- Outputs
- text
- Open weights
- No
- License
- Proprietary
Gemini 3.5 Flash Lite Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionGemini 3.5 Flash-Lite | Released | LLMBoard53.71 | ParametersN/A | Context1M | Max output65.5K | Open weightsNo | LicenseProprietary |
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 26B A4B
GOGoogle
Gemini 3.1 Flash Lite
GOGoogle
Gemini 2.5 Pro
GOGoogle
Gemma 4 31B
GOGoogle
Gemini 3.5 Flash Cyber
GOGoogle
Gemini 3 Flash
What is Gemini 3.5 Flash Lite?
Key information about Gemini 3.5 Flash Lite and its available data.
5 Flash Lite is a Google large language model that supports text, image, video, audio, and PDF inputs. It has a 1 million-token context window and supports up to 65,536 output tokens.
Data as of 2026-09-08.
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 $0.15 input and $1.25 output via Kilo Gateway.
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.