Google: Gemma 3 12B
google/gemma-3-12b-it
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
According to its OpenRouter catalog entry, google/gemma-3-12b-it is an instruction-tuned Google model that accepts text and image input and produces text output. The catalog lists a 128k-token context window, coverage of more than 140 languages, and an August 2024 knowledge cutoff, along with parameters for structured outputs and tool calling. No independent model card was included in this source pack, so these capabilities are provider-reported rather than verified, and real-world behavior should be validated on your own workloads.[1]
Strengths
Limitations
- Evidence is catalog-only; no independent model card was available in this source pack, so claims require workload validation.[1]
- The catalog lists no dedicated reasoning mode, and its benchmark fields indicate very weak measured agentic performance.[1]
- Reported knowledge cutoff is August 2024, so recent events may not be covered.[1]
Where to use it
Sources
- [1] OpenRouter catalog · Google: Gemma 3 12BSources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
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,...
Specifications
- Model ID
- google/gemma-3-12b-it
- Creator
- Added to OpenRouter
- 13.03.2025
- Context length
- 131,072
- Modality
- text+image->text
- Input modalities
- text, image
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.050 / out $0.150
- Knowledge cutoff
- 31.08.2024
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 5.8 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 0.1 | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| DeepInfrabf16 | 131,072 | $0.040 | $0.120 | — | — | — |
| DeepInfrabf16 | 131,072 | $0.050 | $0.150 | — | — | 85.71% |
| NextBitint4 | 131,072 | $0.075 | $0.150 | — | — | 100% |
| DeepInfrabf16 | 131,072 | $0.075 | $0.225 | — | — | 65.52% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.