Gemini 3.1 Flash-Lite: API Pricing, Context Window & Benchmarks
Gemini 3.1 Flash-Lite is a language model from Google, released in March 2026, with multimodal input, a 1M-token context window, and pricing from $0.250/M input and $1.50/M output.
Gemini 3.1 Flash-Lite is the first Flash-Lite model in the Gemini 3 series. It is optimized for high-volume, latency-sensitive tasks like translation, content moderation, and classification. It delivers enhanced performance at a fraction
Gemini 3.1 Flash-Lite benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Gemini 3.1 Flash-Lite across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Gemini 3.1 Flash-Lite holds up as conversations get longer.
Quality Tracker
Gemini 3.1 Flash-Lite Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Sep 02 2026Gemini 3.1 Flash-Lite pricing
Providers
Gemini 3.1 Flash-Lite starts at $0.250 per million input tokens and $1.50 per million output tokens via Google.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Google | $0.250 | — | $1.50 | 1.0M/65.5K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Gemini 3.1 Flash-Lite context window
Input and output token limits for Gemini 3.1 Flash-Lite, plus how it ranks on long-context understanding.
Gemini 3.1 Flash-Lite API
Available from the model provider
Gemini 3.1 Flash-Lite is available from Google. It is not currently routed through the LLM Stats gateway.
Read the official API documentationGemini 3.1 Flash-Lite latency
Gemini 3.1 Flash-Lite time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Gemini 3.1 Flash-Lite examples
Recent arena outputs from Gemini 3.1 Flash-Lite, picked from the highest-ranked matchups.
Gemini 3.1 Flash-Lite license
Gemini 3.1 Flash-Lite is a proprietary model available under its provider's product and API terms, has a knowledge cutoff of January 2025.
- License
- Proprietary
- Hosted access
- Knowledge cutoff
- January 2025
Proprietary license - usage restrictions apply
Gemini 3.1 Flash-Lite resources
Official sources for Gemini 3.1 Flash-Lite: api documentation, official playground, official launch post.
Gemini 3.1 Flash-Lite vs other models
The most-compared alternatives to Gemini 3.1 Flash-Lite are Gemma 4 31B, Claude Opus 4.5, Gemma 4 26B-A4B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Gemini 3.1 Flash-Lite
Models ranked just above and below Gemini 3.1 Flash-Lite by LLM Stats score.
FAQ
Common questions about Gemini 3.1 Flash-Lite.