Gemma 3 12B: Benchmarks, Pricing & Context Window
Gemma 3 12B is a language model from Google, released in March 2025, with multimodal input, a 131K-token context window, and pricing from $0.050/M input and $0.150/M output.
Gemma 3 12B is a 12-billion-parameter vision-language model from Google, handling text and image input and generating text output. It features a 128K context window, multilingual support, and open weights. Suitable for question answering,
Gemma 3 12B benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Gemma 3 12B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Gemma 3 12B holds up as conversations get longer.
Quality Tracker
Gemma 3 12B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Fri Oct 02 2026Gemma 3 12B pricing
Providers
Gemma 3 12B starts at $0.0500 per million input tokens and $0.150 per million output tokens via DeepInfra.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.0500 | — | $0.150 | 131.1K/131.1K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Gemma 3 12B model size
Gemma 3 12B has 12 billion parameters and was trained on 12 trillion tokens. See how it compares to other models in the same parameter range.
Gemma 3 12B context window
Input and output token limits for Gemma 3 12B, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Gemma 3 12B.
Gemma 3 12B latency
Gemma 3 12B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Gemma 3 12B examples
Recent arena outputs from Gemma 3 12B, picked from the highest-ranked matchups.
Gemma 3 12B license
Gemma 3 12B is released under the Gemma license, which permits commercial use, has 12.0B parameters.
- License
- Gemma
- Commercial use allowed
- Parameters
- 12.0B
Google Gemma Terms of Use
Gemma 3 12B resources
Official sources for Gemma 3 12B: paper or system card, official launch post, model weights.
Gemma 3 12B vs other models
The most-compared alternatives to Gemma 3 12B are Llama 3.1 70B Instruct, Claude 3 Sonnet, GPT-5. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Gemma 3 12B
Models ranked just above and below Gemma 3 12B by LLM Stats score.
FAQ
Common questions about Gemma 3 12B.