Open multimodal Gemma instruction model for efficient text generation and image understanding
Gemma 3 4B IT by google is offered by 9 providers on this page. Public prices are shown for 8 of them. Its reference price is $0.201 per 1M tokens. The lowest paid channel is Amazon Bedrock at $0.04 / $0.08 per 1M, about 5.0× below the reference price. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
The context window is 128,000 tokens at the reference host, but hosts report different limits, from 128,000 to 131,072, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-08.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Nvidia | Cloud | Free | — | — | 131,072 ⚠ | 16,384 | ||
| Amazon Bedrock google.gemma-3-4b-it | Cloud | $0.04 | $0.08 | — | — | 131,072 ⚠ | 4,096 | |
| Merge Gateway | Gateway | $0.04 | $0.08 | — | — | 128,000 | 8,192 | |
| Deep Infra | Cloud | $0.05 | $0.10 | — | — | 131,072 ⚠ | 131,072 | |
| Kilo Gateway | Gateway | $0.05 | $0.10 | — | — | 131,072 ⚠ | 16,384 | |
| OpenRouter | Gateway | $0.05 | $0.10 | — | — | 131,072 ⚠ | 16,384 | |
| Hugging Face | Cloud | $0.05 | $0.10 | — | — | 131,072 ⚠ | 131,072 | |
| Eden AI | Gateway | $0.05 | $0.10 | — | — | 131,072 ⚠ | 131,072 | |
| NanoGPT | Gateway | $0.20 | $0.20 | $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.
1 more channels offer $0 (Nvidia); free tiers usually have rate limits and no SLA, excluded from ranking.