Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite by Google DeepMind: League Score, pricing, context window and sourced benchmarks — the full tracked record.
70 Closed $0.30 / $2.50 per 1M 1M context
League positions: #14 overall · #5 Value Division. Score coverage: 25% of components measured. Count tokens & cost for Gemini 3.5 Flash-Lite · Estimate a workload cost
Agent-ready: this model is tracked with agentic strengths. See the AI Agents section for the products and frameworks that put models like this to work.
Specifications & pricing
| Maker | Google DeepMind — lab profile |
| Family | Gemini 3 Flash |
| Released | Jul 21, 2026 |
| Status | Current |
| Weights | Closed / proprietary API |
| License | Proprietary |
| Knowledge cutoff | Not published |
| Context window | 1,000,000 tokens |
| Max output | — |
| Modalities in | text, image, audio, video |
| Modalities out | text |
| API price (input) | $0.30 per 1M tokens |
| API price (output) | $2.50 per 1M tokens |
| Cached input | $0.030 per 1M |
| Blended (3:1 in:out) | $0.85 per 1M |
| Pricing source | Official pricing page (checked Oct 14, 2026) |
| API access | Google AI Studio, Gemini API |
Benchmark results
| Benchmark | Score | Source | Date | Link |
|---|---|---|---|---|
| LMArena Elo | 1418 | LMArena | Oct 14, 2026 | Source |
| MMLU-Pro | 85.8 / 100 | BenchLM MMLU-Pro (Vals AI mirror) | Oct 14, 2026 | Source |
How its League Score is built
| Component | Raw | Normalised | Weight | Date | Link |
|---|---|---|---|---|---|
| MMLU-Pro | 85.8 | 72.8 | 10% | Oct 14, 2026 | Source |
| LMArena Elo | 1418 | 68.0 | 15% | Oct 14, 2026 | Source |
Normalised 0–100 against the tracked field; missing components redistribute their weight. Full rules on the methodology page.
Closest rivals
- Gemini 3.5 Flash-Lite vs Kimi K2.6 — full comparison or compare any pair
- Gemini 3.5 Flash-Lite vs Muse Spark 1.3 — full comparison or compare any pair
- Gemini 3.5 Flash-Lite vs Claude Haiku 5.5 — full comparison or compare any pair
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 on the first-party API (checked Oct 14, 2026).
What is the context window of Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash-Lite accepts up to 1,000,000 tokens of context.
Is Gemini 3.5 Flash-Lite open source?
No — Gemini 3.5 Flash-Lite is a closed model available through Google DeepMind’s API and products.
Data verified Oct 14, 2026. Spotted an error? Every figure above links to its source.