Google: Gemini 3 Flash Preview
google/gemini-3-flash-preview
Gemini 3 Flash Preview (Google) ranks #36 of 235 on the TryAii Score at $0.5/$3 per million input/output tokens — about a third of what models at its level usually charge, though GLM 5.3 Flash matches it for $0.25 per million output tokens. It's strongest on math (#8 on AIME-2025). It's among the fastest models we track, at roughly 68-75 tokens/sec.
Prompt $/1M
$0.500
Completion $/1M
$3.000
Context
1,048,576 tok
Best provider
79 tok/s · Google
Specs
- Model id
- google/gemini-3-flash-preview
- Display name
- Google: Gemini 3 Flash Preview
- Modality
- text+image+file+audio+video->text
- Tokenizer
- Gemini
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 65,536
- Prompt $/1M
- $0.500
- Completion $/1M
- $3.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionno
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| 79 | |
| Google AI Studio | 64 |
| googlefastest | — |
Prompt caching by provider
| Provider | Min tokens to cache |
|---|---|
| Google AI Studio | 4,096 tokens |
| Google Vertex | 6,144 tokens |