Google model product
Gemini 2.5 Flash Lite
5 Flash-Lite is a model developed by Google DeepMind, designed to handle various tasks including reasoning, science, mathematics, code generation, and more.
Updated Aug 12, 2026. Default version: Gemini 2.5 Flash-Lite
LLMBoard score19.1Gemini 2.5 Flash-Lite
Coverage100%12 benchmark families
Context window1MTokens
Official input price$0.10Google API
Gemini 2.5 Flash Lite Specifications
Technical details for the model's default version.
- Version
- Gemini 2.5 Flash-Lite
- Released
- Jun 17, 2025
- Knowledge cutoff
- Jan 1, 2025
- Parameters
- N/A
- Context window
- 1M
- Max output
- 65.5K
- Inputs
- audio, image, pdf, text, video
- Outputs
- text
- Open weights
- No
- License
- Creative Commons Attribution 4.0 License
Gemini 2.5 Flash Lite Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Gemini 2.5 Flash Lite Benchmark Results
Benchmark scores for Gemini 2.5 Flash-Lite.
| Arc | 2.5% | 01 | 1 | 100.0% | C | |
| FACTS Grounding | 84.1% | 03 | 13 | 83.3% | C | |
| MRCR v2 | 16.6% | 03 | 3 | 0.0% | C | |
| Global-MMLU-Lite | 81.1% | 04 | 14 | 76.9% | C | |
| Vibe-Eval | 51.3% | 06 | 8 | 28.6% | C | |
| Aider-Polyglot | 26.7% | 21 | 22 | 4.8% | C | |
| MMMU | 72.9% | 26 | 63 | 59.7% | C | |
| SimpleQA | 10.7% | 39 | 46 | 15.6% | C | |
| LiveCodeBench | 33.7% | 58 | 73 | 20.8% | C | |
| Humanity's Last Exam | 5.1% | 90 | 93 | 3.3% | C | |
| AIME 2025 | 49.8% | 101 | 114 | 11.5% | C | |
| SWE-Bench Verified | 31.6% | 101 | 105 | 3.9% | C | |
| GPQA | 64.6% | 152 | 234 | 35.2% | C |
Gemini 2.5 Flash Lite Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Gemini 2.5 Flash Lite Runtime Performance
Provider-specific output speed and catalog latency for Gemini 2.5 Flash-Lite. Runtime does not affect the capability score.
| 5.69 tok/s | 0.44 s | 1M | 65.5K |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Gemini 2.5 Flash Lite Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.10 input, $0.40 output per 1M
- Official provider
- Lowest third-party
- From $0.07 input, $0.28 output per 1M via Poe
- Tracked offerings
- 21
| Kenari | gemini-2-5-flash-lite | global | N/A | N/A | 1M | |
| Poe | google/gemini-2.5-flash-lite | global | $0.07 | $0.28 | 1M | |
| Jiekou.AI | gemini-2.5-flash-lite | global | $0.09 | $0.36 | 1M | |
| Helicone | gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Impossibl | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| CrossModel | gemini/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | ||
| NanoGPT | gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| NEAR AI Cloud | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| LLM Gateway | gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| SAP AI Core | gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| ZenMux | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Ofox | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| OrcaRouter | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Vertex | gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Kilo Gateway | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Merge Gateway | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| Vercel AI Gateway | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M | |
| OpenRouter | google/gemini-2.5-flash-lite | global | $0.10 | $0.40 | 1M |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Gemini 2.5 Flash Lite Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
| Gemini 2.5 Flash-Lite | 19.1 | N/A | 1M | 65.5K | No | Creative Commons Attribution 4.0 License |
What is Gemini 2.5 Flash Lite?
Key information about Gemini 2.5 Flash Lite and its available data.
5 Flash-Lite is a model developed by Google DeepMind, designed to handle various tasks including reasoning, science, mathematics, code generation, and more. It features advanced capabilities in multilingual performance and long context understanding.
It is optimized for low latency use cases, supporting multimodal input with a 1 million-token context length.
Data as of 2026-08-11.
Gemini 2.5 Flash Lite vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Gemini 2.5 Flash Lite
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
GO
Google
Gemini 1.5 Pro
GOGoogle
Gemini 2.0 Flash Lite
GOGoogle
Gemma 3 27B
GOGoogle
Gemma 4 E4B
GOGoogle
Gemma 4 E2B
GOGoogle
Gemma 3 12B
FAQ
Common questions about Gemini 2.5 Flash Lite.
When was Gemini 2.5 Flash Lite released?
Gemini 2.5 Flash Lite's default version was released on Jun 17, 2025.
How much does Gemini 2.5 Flash Lite cost?
Gemini 2.5 Flash Lite's official API price is $0.10 per million input tokens and $0.40 per million output tokens via Google. The lowest tracked third-party offer starts at $0.07 input and $0.28 output via Poe.
Who created Gemini 2.5 Flash Lite?
Gemini 2.5 Flash Lite was created by Google.
What is the context window for Gemini 2.5 Flash Lite?
The default version has a 1M token context window.
Is Gemini 2.5 Flash Lite open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Gemini 2.5 Flash Lite?
21 provider offerings are linked to the default version.
What models should I compare Gemini 2.5 Flash Lite with?
Nearby ranked alternatives include Magistral Small, Magistral Medium, Qwen3 VL 4B.