All modelsGoogle
Gemma 4 31B fastruns locally
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...
Input / 1M
$0.20
USD per million tokens
Output / 1M
$0.40
USD per million tokens
Est. cost / token
$0.00000025
$0.25 per 1M, 3:1 mix
Context window
262K
max output 16K
Major features
VisionOpen weightsReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 16.3 GB |
| Q3_K_M | fair | 18.6 GB |
| Q4_K_Mrecommended | good | 22.6 GB |
| Q5_K_M | very good | 25.9 GB |
| Q6_K | excellent | 29.5 GB |
| Q8_0 | near-lossless | 37.4 GB |
| F16 | lossless | 68.2 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.20 | $0.40 | — | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.20
- Output
- $0.40
- Blended (3:1)
- $0.25
Details
- Company
- Version
- 4
- Family
- Gemma
- Released
- 2026-04-02
- Parameters
- 31.3B
- Max output
- 16K
- Open weights
- Yes
- Inputs
- image, text, video
- Last synced
- 29 min ago