Google: Gemini 3.5 Flash
google/gemini-3.5-flash
Gemini 3.5 Flash (Google) ranks #36 of 263 on the TryAii Score at $1.5/$9 per million input/output tokens — about the going rate for its score class, though Ling 3.1 Flash matches it for $0.225 per million output tokens. It's strongest on knowledge (#9 on MMLU-Pro). It's among the fastest models we track, at roughly 150-191 tokens/sec.
Prompt $/1M
$1.500
Completion $/1M
$9.000
Context
1,048,576 tok
Best provider
212 tok/s · Google AI Studio
Specs
- Model id
- google/gemini-3.5-flash
- Display name
- Google: Gemini 3.5 Flash
- Modality
- text+image+file+audio+video->text
- Tokenizer
- Gemini
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 65,536
- Prompt $/1M
- $1.500
- Completion $/1M
- $9.000
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- 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 |
|---|---|
| Google AI Studiofastest | 212 |
| 129 |
Prompt caching by provider
| Provider | Min tokens to cache |
|---|---|
| Google AI Studio | 4,096 tokens |
| Google Vertex | 4,096 tokens |