Google
99.94%Context1M
Max output64K
p50 latency630 ms
Throughput179.0 t/s
Input price$0.5
Output price$3
No trainingCaching
Model directory
Baseer model profileLanguage model
google/gemini-3-flash
Gemini 3 Flash
Google's most intelligent model built for speed, combining frontier intelligence with superior search and grounding.
Input / 1M tokens$0.5
Output / 1M tokens$3
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
99.97%Context1M
Max output65K
p50 latency696 ms
Throughput146.0 t/s
Input price$0.5
Output price$3
Zero retentionNo trainingCaching
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Google | 1M | 64K | 630 ms | 179.0 t/s | 99.938% | $0.5 | $3 | |
Vertex | 1M | 65K | 696 ms | 146.0 t/s | 99.974% | $0.5 | $3 |
What can this model do?
Available modalities and capabilities across inference providers.
TextImageFileAdvanced reasoningFile inputVisionTool useWeb searchAutomatic cachingTools
Reasoning options
MinimalLowMediumHigh
Technical profile
- Model type
- Language model
- Release date
- Dec 17, 2025
- Knowledge cutoff
- 2025-03
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
google/gemini-3-flashModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.