Gemma 3 12B IT
by GoogleChat
Open Gemma instruction model for efficient chat and self-hosted deployments
- Context
- 131K tokens
- Max output
- 16,384 tokens
- Parameters
- 12.2B total
- Released
- 2025-03-12
- Weights
- Open
- Licence
- gemma
google/gemma-3-12b-it · also seen as amazon/google.gemma-3-12b-it@us, amazon/google.gemma-3-12b-it, deepinfra/google/gemma-3-12b-it
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-03-12
- Weights
- Opengated
- License
- gemma
- Input
- Text, Image
- Output
- Text
- Context window
- 131,072 max across endpoints
- Max output
- 16,384
- Providers
- 7 + 6 gateways, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.05–$0.10 in · $0.10–$0.29 out per 1M tokens · 6 of 7 providers have a comparable price
More details
- Last updated
- 2025-03-12
- Knowledge cutoff
- 2024-08
- Weights link
- Hugging Face · google/gemma-3-12b-it
- Parameters
- 12.2B total
- Base model
- google/gemma-3-12b-pt
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel tools
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messages
- Assistant prefillunknown
- Temperature
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Price history
Atom feedNo change since 19 Oct 2026. The cheapest direct price has been $0.05 in / $0.10 out per 1M tokens at Novita AI on every data refresh since then.
Tracked from 19 Oct 2026. Headline-eligible direct prices only, so a price the sanity check flags never draws a spike. Series as JSON
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs Gemma 3 12B IT |
|---|---|---|---|---|---|
| Qwen3-VL FlashAlibaba (Qwen) | $0.0542 | $0.022 | $0.215 | 262K | +2% |
| Nova MicroAmazon | $0.0525 | $0.035 | $0.14 | 128K | −2% cheaper |
| Qwen FlashAlibaba (Qwen) | $0.0543 | $0.022 | $0.216 | 1M | +2% |
| AutoGLM Phone 9B MultilingualZ.ai (Zhipu AI) | $0.0522 | $0.035 | $0.138 | 65.5K | −2% cheaper |
| GLM-4.6V-FlashZ.ai (Zhipu AI) | $0.0546 | $0.0218 | $0.218 | 128K | +2% |
| Llama 3.1 8B InstructMeta | $0.055 | $0.05 | $0.08 | 200K | +3% |
| llama-3-8bMeta | $0.055 | $0.05 | $0.08 | 8.2K | +3% |
| Mistral Small 3Mistral AI | $0.055 | $0.05 | $0.08 | 32.8K | +3% |
More from Google
Newest Google models in the catalogue. All Google models
| Model | Released | Context | Listed price |
|---|---|---|---|
| Gemini 4 Argon | 2026-10-13 | 1.05M | from $2.00 |
| Gemma 4 31B Scarlet | 2026-10-08 | 262K | $0.10 via NanoGPT |
| Gemma 4 26B A4B Chimera X Heretic | 2026-10-08 | 262K | $0.12 via NanoGPT |
| Gemini Nano Banana 2.1 | 2026-10-06 | 131K | from $1.50 |
| Gemini 3.8 Flash TTS | 2026-09-23 | 8.2K | unpriced |
| Gemini 3.8 Flash-Lite TTS | 2026-09-23 | 8.2K | unpriced |
| DiffusionGemma | 2026-09-19 | 262K | $0.05 via NanoGPT |
| Gemma 4 26B A4B Cybersecurity | 2026-09-19 | 262K | $0.106 via NanoGPT |