Gemma 4 12B IT
Compact Gemma 4 instruction model for open, self-hosted chat and reasoning.
- Capability
- —No ECI score yet
- Input
- $0.05per 1M tokens
- Output
- $0.25per 1M tokens
- Context
- 262K33K max output
What it costs
- Input
- $0.05per million tokens
- Output
- $0.25per million tokens
- Blended (3:1)
- $0.10cheaper than 89% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $0.225 |
| Team assistant25M input + 5M output tokens | $2.50 |
| Production app250M input + 50M output tokens | $25.00 |
Median of 3 paid API providers on models.dev.
Independent benchmarks
Epoch AI has not published a Capabilities Index score for Gemma 4 12B IT yet.
The details
- Lab
- Released
- Jun 9, 2026
- Context window
- 262,144 tokens
- Max output
- 32,768 tokens
- Inputs
- Text, Images
- Output
- Text
- Reasoning
- Always on
- Tool calling
- Yes
- Structured output
- No
- Weights
- Open weights
- Availability
- 3 API providerslisted on models.dev
More from Google
About Gemma 4 12B IT
How much does Gemma 4 12B IT cost?
Gemma 4 12B IT costs $0.05 input / $0.25 output per million tokens (median across 3 API providers). At a 3:1 input-to-output mix that is $0.10 per million tokens, cheaper than 89% of the 469 priced models we track.
What is the context window of Gemma 4 12B IT?
Gemma 4 12B IT accepts up to 262,144 tokens per request and can write up to 32,768 tokens in one response.
How good is Gemma 4 12B IT?
Epoch AI has not published a Capabilities Index score for Gemma 4 12B IT yet.
Is Gemma 4 12B IT open source?
Yes. Google publishes the weights, so it can be downloaded and self-hosted.
What inputs does Gemma 4 12B IT support?
Gemma 4 12B IT accepts text and images and replies in text. It is a reasoning model, supports tool calling.
When was Gemma 4 12B IT released?
Google released Gemma 4 12B IT on Jun 9, 2026.
What are the best alternatives to Gemma 4 12B IT?
The closest current models from other labs on capability, price and release date are Schematron V2 Small (Inference.net, $0.05 / $0.23), Laguna S 2.1 (Poolside, $0.09 / $0.18), Nemotron 3.5 Lightning 30B A3B (NVIDIA, $0.06 / $0.20) and Ling 3.0 Flash (inclusionAI, $0.075 / $0.224).