Text model
google/gemma-4-31B-it pricing
DeepInfra charges $0.13 per million input tokens and $0.38 per million output tokens for google/gemma-4-31B-it. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.13/ 1M
- Output
- $0.38/ 1M
- Context
- 262.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.13 | $0.38 | — | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000347 | 100,000 | $34.70 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00097 | 100,000 | $97.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.00186 | 250,000 | $466.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with google/gemma-4-31B-it, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| deepinfra/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B | $0.000287 | 17% |
| deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo | $0.000278 | 20% |
| watsonx/mistralai/mistral-small-3-1-24b-instruct-2503 | $0.000286 | 18% |
| mistral/ministral-3-8b-2512 | $0.000285 | 18% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: DeepInfra pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.