← Model list
Gemma 4 31B
google·google/gemma-4-31b·GA·Open weights·gemma series
Open Gemma instruction model for efficient chat and self-hosted deployments
At a glance
Reference price$0.40 / $1.00 per 1M
Cache read $0.40 · NanoGPT
Lowest paid$0.10 / $0.34
Weights & Biases Cloud · 4× spread
1 more $0 channels
Context262,144
⚠ Providers report 262,128–262,144; the table below is authoritative
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff2025-01
Released / updated2026-04-02 / 2026-04-08
Quality & performanceArtificial Analysis · Intelligence Index v4.1 · rep. tier Reasoning
Intelligence29.7
Value186
Coding43.4
Agentic14.4
Output speed36 tok/s
TTFT1.11 s
Cost per task$0
Value formulaIQ 29.7 ÷ min blended $0.160 = 186
Reasoning tier → intelligence / speed (higher tier = stronger but slower)
Non-reasoningIQ 22.3 · 82 tok/s
ReasoningIQ 29.7 · 36 tok/s
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 7 providers5 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Poe | Gateway | Free | — | — | 262,144 | 8,192 | ||
| Weights & Biases google/gemma-4-31B-it | Cloud | $0.10 | $0.34 | $0.10 | — | 262,144 | 262,144 | |
| NanoGPT google/gemma-4-31b-it | Gateway | $0.10 | $0.35 | $0.05 | — | 262,144 | 131,072 | |
| NovitaAI google/gemma-4-31b-it | Gateway | $0.14 | $0.40 | — | — | 262,144 | 131,072 | |
| Neuralwatt | Gateway | $0.144 | $0.42 | $0.036 | — | 262,128 ⚠ | 16,384 | |
| NanoGPT TEE/gemma4-31b | Gateway | $0.40 | $1.00 | $0.40 | — | 262,144 | 131,072 | |
| Ollama Cloud gemma4:31b | Cloud | — | — | — | — | 262,144 | 262,144 | hostTable.undisclosed |
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
1NanoGPT$31.50
2Neuralwatt$36.84
3Weights & Biases$37.00
4NovitaAI$48.00
5NanoGPT$130.00
1 more channels offer $0 (Poe); free tiers usually have rate limits and no SLA, excluded from ranking.
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
Toggle (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 Flashcheaper alternative$0.14 / $0.28GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0MiMo-V2.5cheaper alternative$0.14 / $0.28
Price historyone sample accumulated per data sync
Input listOutput listMin blended