Gemma 3 4B
Google · google/gemma-3-4b-it
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities,...
Gemma 3 4B ranks #59 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.07 blended per million tokens, it is cheaper than 95% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).
Context
Max output: 16384
Pricing
Output / 1M: 0.10
Blend / 1M: 0.07
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.07per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.
| Tokens / month | Est. cost (USD) |
|---|---|
| 1,000,000 | $0.07 |
| 10,000,000 | $0.75 |
| 100,000,000 | $7.50 |
Related models
Same lab, similar price, or similar quality — useful next comparisons.
More from Google
- Gemini 3.7 Flash$2.25 / 1M · Q 86.7
- Gemini 3.6 Flash$2.25 / 1M · Q 83.7
- Gemini 3.5 Flash$5.25 / 1M · Q 81.3
- Gemini 3.8 Flash$2.25 / 1M · Q 80.8
- Gemini 3.1 Pro Preview$7.00 / 1M · Q 80.4
Closest API price
- Solar Pro 4$0.07 / 1M
- Qwen3.7 Flash$0.08 / 1M
- gpt-oss-20b$0.08 / 1M
- Mistral Small 3$0.07 / 1M
- Llama 3.1 8B Instruct$0.07 / 1M