← Model list
Gemma 4
google·google/gemma4·GA·Open weights·gemma series
Open Gemma instruction model for efficient chat and self-hosted deployments
At a glance
Reference price$2.00 / $5.00 per 1M
Cache read $0.50 · LLMTR
Lowest paid$0.18 / $0.50
DigitalOcean Cloud · 11.1× spread
Context131,072
⚠ Providers report 131,072–262,144; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideo
Knowledge cutoff—
Released / updated2026-04-02 / 2026-04-30
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 3 providers3 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| DigitalOcean gemma-4-31B-it | Cloud | $0.18 | $0.50 | $0.036 | — | 256,000 ⚠ | 8,192 | |
| GreenPT | Gateway | $0.57 | $1.71 | — | — | 262,144 ⚠ | 32,768 | |
| LLMTR gemma-4 | Gateway | $2.00 | $5.00 | $0.50 | — | 131,072 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1DigitalOcean$43.72
2GreenPT$199.50
3LLMTR$470.00
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = noneeffort = minimaleffort = loweffort = mediumeffort = highToggle (on / off)
Related models
Gemma 4 12B Instructsame series$0.06 / $0.30Gemma 4 26B A4Bsame series$0.13 / $0.40Google Gemma 3 27B Instructsame series$0.12 / $0.20DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28MiniMax-M2.7cheaper alternative$0.30 / $1.20DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44
Price historyone sample accumulated per data sync
Input listOutput listMin blended