mistralai
Gemma 4 31B vs Mistral Large 4
43.9 overall · $1.05 / 1M
Gemma 4 31B
google/gemma-4-31b-it
reasoningtool callingimage inputvideo input
Gemma 4 31B costs $0.200 per 1M input tokens and $0.400 per 1M output tokens with a 262K-token context window.
A reasoning, tool-calling model from google, released Apr 2, 2026. On LiveBench it scores 38.7 overall — #28 of 28 benchmarked models — and ranks highest in long-horizon agentic (#26).
- Input / 1M
- $0.200
- Output / 1M
- $0.400
- Context
- 262K
- LiveBench overall
- 38.7 · #28
Specs and pricing
| Input price USD per 1M prompt tokens | $0.200 |
|---|---|
| Output price USD per 1M completion tokens, reasoning included | $0.400 |
| Blended price 3:1 input:output — #93 cheapest of 350 listed models | $0.250 |
| Cached input read Blank means not priced separately — not free | — |
| Cache write | — |
| Context window | 262,144 tokens |
| Max output | 16,384 tokens |
| Input modalities | image, text, video |
| Tool calling | Yes |
| Extended reasoning | Yes |
| Knowledge cutoff | — |
| Listed | Apr 2, 2026 |
Also listed as google/gemma-4-31b-it:free (Free blended)— the same model at a different price or rate limit.
Benchmarks by category
LiveBench scores out of 100, with Gemma 4 31B's rank among the 28 benchmarked models listed here. Run: gemma-4-31b.
Browser#28 of 28
0.0
What Gemma 4 31B costs to run
Monthly list cost across five workload shapes, using the published cached-input rate where there is one. A floor, not a quote — batch discounts and cache writes aren't included.
| Workload | Per month |
|---|---|
| Support chatbot 1.2K in / 400 out × 200K requests | $80.00/mo |
| RAG assistant 8K in / 600 out × 100K requests | $184.00/mo |
| Coding agent 40K in / 4K out × 20K requests | $192.00/mo |
| Document extraction 20K in / 1.5K out × 50K requests | $230.00/mo |
| Bulk classification 500 in / 20 out × 5M requests | $540.00/mo |
Compare Gemma 4 31B with
The benchmarked models closest to it on overall score.
thinkingmachines
Gemma 4 31B vs Inkling
47.0 overall · $1.76 / 1M
nvidia
Gemma 4 31B vs Nemotron 3.5 Super VL
50.2 overall · $0.237 / 1M
meta
Gemma 4 31B vs Muse Spark Open
51.6 overall · $2.00 / 1M
qwen
Gemma 4 31B vs Qwen3.8 27B
58.4 overall · $0.581 / 1M
stepfun
Gemma 4 31B vs Step 5 Preview
58.6 overall · $1.43 / 1M
Gemma 4 31B FAQ
How much does Gemma 4 31B cost?
Gemma 4 31B lists at $0.200 per 1M input tokens and $0.400 per 1M output tokens. A RAG assistant handling 100K requests a month (8K tokens in, 600 out) comes to about $184.00 at list price.
What is the context window of Gemma 4 31B?
Gemma 4 31B accepts up to 262,144 tokens of context and can return up to 16,384 output tokens per response.
Does Gemma 4 31B support tool calling?
Yes — Gemma 4 31B supports tool (function) calling and exposes extended reasoning. It accepts image, text, video input.
How does Gemma 4 31B score on benchmarks?
On LiveBench release 2026-10-25 (run: gemma-4-31b), Gemma 4 31B scores 38.7 overall, ranking #28 of 28 benchmarked models.
What is the API model ID for Gemma 4 31B?
On OpenRouter the model ID is "google/gemma-4-31b-it". It was listed on Apr 2, 2026.
More from google
How these numbers are produced
- Price and specs — provider list data from OpenRouter, refreshed every 15 minutes. “Blended” is a 3:1 input:output mix.
- Scores and ranks — LiveBench release 2026-10-25. Ranks count only models that have a published run; a blank means “not evaluated”, never “bad”.
- Cost per point — the measured dollars LiveBench spent on the run, divided by the score it earned.
Published benchmarks rank models on someone else's tasks. Before committing, see LLM & agent evaluation for building an eval on your own.