Compact Gemma 4 instruction model for open, self-hosted chat and reasoning
Gemma 4 12B IT by google is offered by 3 providers on this page. Its reference price is $0.25 per 1M tokens. The lowest paid channel is NanoGPT at $0.05 / $0.25 per 1M, about 5.0× below the reference price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.
The context window is 32,768 tokens at the reference host, but hosts report different limits, from 32,768 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, and Audio. 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.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT | Gateway | $0.05 | $0.25 | $0.025 | — | 131,072 ⚠ | 32,768 | |
| SiliconFlow google/gemma-4-12B-it | Cloud | $0.10 | $0.30 | — | — | 262,144 ⚠ | 262,144 | |
| Pioneer google/gemma-4-12B-it | Gateway | $0.25 | $0.25 | $0.25 | $0.25 | 32,768 | 32,768 |
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.
Interleaved thinking (reasoning between tool calls) is declared by 1 of 3 providers.