Google
99.79%Context1M
Max output64K
p50 latency1,849 ms
Throughput145.5 t/s
Input price$0.75
Output price$3.75
No trainingCaching
Model directory
Baseer model profileLanguage model
google/gemini-3.6-flash
Gemini 3.6 Flash
Gemini 3.6 Flash delivers higher quality across coding, agentic workflows, and web development with reduced token consumption and fewer model calls compared to previous model iterations.
Input / 1M tokens$0.75
Output / 1M tokens$3.75
Maximum context1M
Inference providers2
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Vertex
99.98%Context1M
Max output64K
p50 latency1,591 ms
Throughput159.0 t/s
Input price$0.75
Output price$3.75
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Google | 1M | 64K | 1,849 ms | 145.5 t/s | 99.787% | $0.75 | $3.75 | |
Vertex | 1M | 64K | 1,591 ms | 159.0 t/s | 99.983% | $0.75 | $3.75 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageFileVideoAdvanced reasoningFile inputTool useVisionAutomatic cachingWeb searchVideo inputTools
Reasoning options
MinimalLowMediumHigh
Technical profile
- Model type
- Language model
- Release date
- Jul 21, 2026
- Knowledge cutoff
- 2026-03
- Regions
- EU, US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
google/gemini-3.6-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.