Gemma 4 31B
Google · google/gemma-4-31b-it
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Gemma 4 31B ranks #33 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.21 blended per million tokens, it is cheaper than 80% of models with published API pricing. Its 262,144-token context window is about the catalog median (262,144 tokens). A quality index of 76.4 places it at #33 of 59 models with an Arena Elo signal.
Context
Max output: 16384
Pricing
Output / 1M: 0.34
Blend / 1M: 0.21
Quality
Provider
Moderated: no
Monthly cost at this blended rate
Estimated API spend if every token is billed at $0.21per 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 | $0.21 |
| 10,000,000 | $2.15 |
| 100,000,000 | $21.50 |
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 3.8 Flash$2.25 / 1M · Q 85.5
- Gemini 3.6 Flash$2.25 / 1M · Q 83.7
- Gemini 3.5 Flash$5.25 / 1M · Q 81.2
- Gemini 3.1 Pro Preview$7.00 / 1M · Q 80.4
Closest API price
- DeepSeek V4 Flash 0731$0.21 / 1M · Q 86.3
- MiMo-V2.5$0.21 / 1M
- Llama 3.3 70B Instruct$0.21 / 1M
- Gemma 4 26B A4B$0.20 / 1M · Q 72.5
- GPT-5 Nano$0.22 / 1M
Closest quality index
- Claude Haiku 4.5$3.00 / 1M · Q 76.4
- Gemini 2.5 Pro$5.63 / 1M · Q 76.2
- Gemini 2.5 Pro Preview 06-05$5.63 / 1M · Q 76.2
- GPT-5$5.63 / 1M · Q 76.1
- GPT-5.2 Chat$7.88 / 1M · Q 76.0