Google: Gemma 3 4B
google/gemma-3-4b-it
Gemma 3 4B (Google) is a compact 4B open-weight model priced near the bottom of the board, at $0.04/$0.05 per million input/output tokens, served by 2 independent hosts. For the money it delivers #247 of 263 on the TryAii Score. It's among the fastest models we track, at roughly 62-140 tokens/sec.
Prompt $/1M
$0.040
Completion $/1M
$0.050
Context
131,072 tok
Best provider
178 tok/s · Parasail
Specs
- Model id
- google/gemma-3-4b-it
- Display name
- Google: Gemma 3 4B
- Modality
- text+image->text
- Tokenizer
- Gemini
- Instruct type
- gemma
- Context length
- 131,072
- Max completion
- 117,964
- Prompt $/1M
- $0.040
- Completion $/1M
- $0.050
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptyes
- 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 |
|---|---|
| Parasailfastest | 178 |
| DeepInfra | 24 |