← Model list
Gemma 3 4B IT
google·google/gemma-3-4b-it·GA·Open weights·gemma series
Open Gemma instruction model for efficient chat and self-hosted deployments
At a glance
Reference price$0.201 / $0.201 per 1M
Cache read $0.10 · NanoGPT
Lowest paid$0.04 / $0.08
Amazon Bedrock Cloud · 5× spread
1 more $0 channels
Context128,000
⚠ Providers report 128,000–131,072; the table below is authoritative
Output limit8,192
Capabilities
Reasoning✓ Tool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff—
Released / updated2025-03-12 / 2025-03-12
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 providers2 with public prices · 1 free
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | First-party | Free | — | — | 131,072 ⚠ | 16,384 | ||
| Amazon Bedrock google.gemma-3-4b-it | Cloud | $0.04 | $0.08 | — | — | 128,000 | 4,096 | |
| NanoGPT | Gateway | $0.201 | $0.201 | $0.10 | — | 128,000 | 8,192 |
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
1Amazon Bedrock$12.00
2NanoGPT$38.11
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.
The cheapest paid channel is the only channel.
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 / $0.20Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Ministral 3Bcheaper alternative$0.10 / $0.10Lyria 3 Clip Previewcheaper alternative$0 / $0Command R7Bcheaper alternative$0.037 / $0.15
Price historyone sample accumulated per data sync
Input listOutput listMin blended