Google: Gemma 4 31B
The Google model, Gemma 4 31B, is a multi-modal AI that can process image, text, and video inputs. It operates within a context length of 262144 tokens and supports tools for tasks like reasoning. However, its structured output capabilities are not listed. When considering this model, users who need to integrate multiple media types into their workflow may want to shortlist it due to its input modalities. Additionally, those on a budget might find the price point appealing, as it charges $0.09 per million input tokens and $0.34 per million output tokens. However, its benchmark performance, with a blended score of 55.0 across two independent tests, is only average among those available for review, and further testing would be necessary to fully evaluate its capabilities.
Benchmark results
Independent, published benchmarks. Blended score 49.4 across 2 benchmarks, last refreshed 2026-10-13. How scoring works →
| Benchmark | Measures | Score |
|---|---|---|
| AI Index | broad capability composite | 24.2 |
| EQ-Bench | emotional understanding in dialogue | 70.8 |
- Model ID
- google/gemma-4-31b-it
- Vendor
- Released
- April 2026
- Tokenizer
- Gemma
- Input Modalities
- image, text, video
- Output Modalities
- text
- Max Output
- 16,384 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- ✓ supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.09/M input and $0.34/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.06 |
| A month of a busy support chatbot | 5M in / 2M out | $1.13 |
Price & spec history
Tracked daily by PicksByModel since 2026-07-17.
| Date | Input /M | Output /M | Context |
|---|---|---|---|
| 2026-08-26 | $0.09 | $0.34 | 262,144 |
| 2026-08-21 | $0.10 | $0.34 | 262,144 |
| 2026-08-19 | $0.09 | $0.34 | 262,144 |
| 2026-07-30 | $0.10 | $0.34 | 262,144 |
| 2026-07-25 | $0.14 | $0.40 | 262,144 |
| 2026-07-24 | $0.10 | $0.35 | 262,144 |
| 2026-07-23 | $0.12 | $0.35 | 262,144 |
| 2026-07-21 | $0.12 | $0.37 | 262,144 |
| 2026-07-17 | $0.22 | $0.55 | 262,144 |
Category rankings
Where Google: Gemma 4 31B places across the 3 categories it ranks in. How we rank →
| # | Category | Score |
|---|---|---|
| #17 | Real-Time ChatLatency · of 25 ranked | 118 |
| #18 | Self-Hosted / LocalCost · of 25 ranked | 117 |
| #22 | Cheap Bulk InferenceCost · of 25 ranked | 137 |
Similar models
Google: Gemini 3.8 Flash
Google: Gemini 3.8 Flash (batch)
Google: Gemini 3.7 Flash
Google: Gemini 3.7 Flash (batch)
Google: Gemini 3.6 Flash
Google: Gemini 3.6 Flash (batch)
Quick answers
- How much does Google: Gemma 4 31B cost?
- $0.09 per million input tokens and $0.34 per million output tokens.
- What is Google: Gemma 4 31B's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Google: Gemma 4 31B support tool calling?
- It supports tool calling, structured output, a reasoning mode.
- Can Google: Gemma 4 31B process images?
- Yes, it accepts image input.