Gemma 3 12B
Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B
Model card on Hugging Face- Input / output price
- $0.05 / $0.10 per 1M
- Context
- 131K tokens
- Released
- Mar 12, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
7 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Novita novita/gemma-3-12b-it | $0.05/M | $0.10/M |
DeepInfra deepinfra/gemma-3-12b-it | $0.05/M | $0.15/M |
Featherless featherless/gemma-3-12b-it | $0.05/M | $0.15/M |
Bedrock bedrock/gemma-3-12b-it | $0.09/M | $0.29/M |
Concentrate concentrate/gemma-3-12b | $0.09/M | $0.29/M |
Nextbit256 nextbit256/gemma-3-12b-it | $0.35/M | $0.45/M |
OpenRouter openrouter/gemma-3-12b-it | $0.05/M | $0.15/M |
Is a provider down? AWS Bedrock status, OpenRouter status
Pricing
Averaged across 7 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.10 per 1M
- Average output
- $0.23 per 1M
- Average cache read
- $0.17 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better12tokens/sacross providers
Response latency
Lower is better1.7sacross providers
Benchmarks
5 published scores from 1 source, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBenchGoogle | 24.6% | Mar 12, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondGoogle | 40.9% | Mar 12, 2025 |
Apps
Use Gemma 3 12B in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Gemma 3 12B FAQ
Short answers, built from the data on this page.
Gemma 3 12B is a model from Google Gemini AI, released on Mar 12, 2025. Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 12B is the second largest in the family of Gemma 3 models after Gemma 3 27B.
On the Respan gateway, input starts at $0.05 per 1M tokens on Novita, DeepInfra, Featherless, and 1 more, and output starts at $0.10 per 1M tokens on Novita, after gateway discounts. Averaged across its 7 providers, it costs $0.10 per 1M input tokens and $0.23 per 1M output tokens.
Gemma 3 12B is available through 7 providers: Novita, DeepInfra, Featherless, Bedrock, Concentrate, Nextbit256, and 1 more.
Gemma 3 12B accepts up to 131K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "gemma-3-12b-it". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemma 3 12B has 5 published benchmark scores, including LiveCodeBench 24.6%, GPQA Diamond 40.9%, and IFEval 88.9%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.