Google: Gemini 3.7 Flash
google/gemini-3.7-flash
Gemini 3.7 Flash (Google) is one of the best deals on the board: #12 of 271 on the TryAii Score at $0.75/$3.75 per million input/output tokens, with nothing cheaper scoring higher. It's strongest on knowledge (#4 on GPQA). It's reasonably quick at roughly 73-78 tokens/sec.
Prompt $/1M
$0.750
Completion $/1M
$3.750
Context
1,048,576 tok
Best provider
81 tok/s · Google
Specs
- Model id
- google/gemini-3.7-flash
- Display name
- Google: Gemini 3.7 Flash
- Modality
- text+image+file+audio+video->text
- Tokenizer
- Gemini
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 65,536
- Prompt $/1M
- $0.750
- Completion $/1M
- $3.750
- 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 |
|---|---|
| 81 | |
| Google AI Studio | 70 |
Prompt caching by provider
All models →| Platform | Caches? | Min tokens | Lifetimes | Resets | Read $/1M | Write $/1M |
|---|---|---|---|---|---|---|
| Yes, automatic or on request | 4,096 | explicit— | unknown | $0.165 | — |
- exact
- the provider promises this lifetime
- at least
- promised for at least this long
- not promised
- no guarantee from the provider
We measure these daily and do our best to keep them accurate. Always confirm with the provider’s official documentation.
Official docs: Vertex AI
Spot a wrong number? Message our support.