Model comparison
Gemini 3.6 Flash vs Gemini 3.5 Flash-Lite
Compare Gemini 3.6 Flash vs Gemini 3.5 Flash-Lite API pricing: input/output token costs, cache pricing, context windows, workload estimates, and routing fit.
Gemini 3.6 Flash
gemini · gemini-3.6-flash
- Input
- $1.5
- Output
- $7.5
- Context
- 1M
Gemini 3.5 Flash-Lite
gemini · gemini-3.5-flash-lite
- Input
- $0.3
- Output
- $2.5
- Context
- 1M
Quick take
Gemini 3.5 Flash-Lite has the lower input price at $0.3 per 1M input tokens. Gemini 3.5 Flash-Lite is cheaper for the example blended workload below. Gemini 3.6 Flash has the larger context window at 1M tokens.
Choose Gemini 3.6 Flash if...
- Gemini 3.6 Flash is a reasonable pick when its provider, latency, or integration path fits your stack better.
Choose Gemini 3.5 Flash-Lite if...
- Gemini 3.5 Flash-Lite is the better default for cost-sensitive traffic and repeated high-volume calls.
Example workload cost
Estimates use input tokens plus 20% output tokens. They exclude provider discounts, cache hits, and tool/search surcharges.
| Workload | Gemini 3.6 Flash | Gemini 3.5 Flash-Lite | Cheaper |
|---|---|---|---|
| 1M input + 200K output | $3.00 | $0.80 | Gemini 3.5 Flash-Lite |
| 10M input + 2M output | $30.00 | $8.00 | Gemini 3.5 Flash-Lite |
| 100M input + 20M output | $300.00 | $80.00 | Gemini 3.5 Flash-Lite |
Context, output, and capability fit
Gemini 3.6 Flash provides the larger context window. Check max output separately when the task needs long reports, code generation, or full-document rewrites.
- Gemini 3.6 Flash max output
- 65.5K
- Gemini 3.5 Flash-Lite max output
- 65.5K
- Gemini 3.6 Flash features
- prompt caching, function calling, vision
- Gemini 3.5 Flash-Lite features
- prompt caching, function calling, vision
Risk notes for Gemini 3.6 Flash
- No major capability risk is flagged in this snapshot, but provider pages should still be verified before production routing.
Risk notes for Gemini 3.5 Flash-Lite
- No major capability risk is flagged in this snapshot, but provider pages should still be verified before production routing.
Routing tags
frontierfastreasoninglong-contextmultimodalcache-friendlystablebudgetraghigh-volume