Google: Gemma 4 31B IT
Open Gemma instruction model for efficient chat and self-hosted deployments
Cheapest input
$0
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
262K
tokens
Offers
5
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number. Showing free/$0 offers. Hide them.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestgoogle/gemma-4-31b | Poe | $0 | $0 | $0 | 262K |
| LiteLLMbedrock_mantle/google.gemma-4-31b | — | $0.14 | $0.4 | $0.014 | — |
| LiteLLMgoogle.gemma-4-31b | — | $0.14 | $0.4 | $0.014 | — |
| models.devgemma-4-31b | Neuralwatt | $0.144 | $0.42 | $0.036 | 262K |
| models.devgemma-4-31b | Cerebras | $0.99 | $1.49 | $0 | 131K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Released: 2026-04-02Family: gemma
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence29.4
- AA coding43.4
- AA agentic14.4
Sources: Arena AI, Artificial Analysis. See /benchmarks.