Google: Gemma 4 31B (free)
google/gemma-4-31b-it:free
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
google/gemma-4-31b-it:free is OpenRouter's free listing for Google's instruction-tuned Gemma 4 31B model. Google's model card describes a 30.7B-parameter dense architecture with text output, a 256K-token context window, configurable thinking, function calling, and multilingual support. OpenRouter lists text, image, and video inputs, while the card's 31B table lists only text and image. Reported benchmark coverage includes reasoning, coding, vision, multilingual, and long-context tasks, but this evidence does not establish performance on a specific workload.[1][2]
Strengths
- Google reports a 256K-token context window for this 31B dense variant, a source-reported capability that may help with lengthy documents and prompts.[2]
- The model card reports configurable thinking, native function calling, and system-role support; OpenRouter also exposes reasoning and tool-related request parameters.[1][2]
- Google reports image understanding for OCR, document and PDF parsing, charts, screens, and handwriting; OpenRouter additionally lists video input for this endpoint.[1][2]
Limitations
- Modality evidence is inconsistent: OpenRouter lists text, image, and video input, whereas the model card's 31B table lists only text and image; verify video support on the actual endpoint.[1][2]
- The model card's 31B table lists no audio support; audio capabilities documented for smaller Gemma 4 variants should not be attributed to this model.[2]
- Detailed benchmark results are source-reported rather than independently reproduced, so teams should validate quality, latency, reliability, and endpoint behavior on their own workloads.[1][2]
Where to use it
- Worth evaluating for long-context document analysis that combines text with images, such as OCR, PDF parsing, or chart and UI question answering.[2]
- Worth evaluating for coding assistance and agent-style workflows that need structured tool calls, subject to endpoint validation.[1][2]
- Worth evaluating for multilingual assistants or drafting workflows that benefit from configurable reasoning and system-role control.[2]
Sources
- [1] OpenRouter catalog · Google: Gemma 4 31B (free)Sources checked: Nov 13, 2026
- [2] Model documentation · Google: Gemma 4 31B (free)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Specifications
- Model ID
- google/gemma-4-31b-it:free
- Canonical ID
- google/gemma-4-31b-it-20260402
- Creator
- Added to OpenRouter
- 02.04.2026
- Context length
- 262,144
- Modality
- text+image+video->text
- Input modalities
- image, text, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0 / out $0
- Knowledge cutoff
- —
- 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 | CC — below the B band | reasoning: optional · parameters: include_reasoning, reasoning |
| Coding | BB — next 30% of the cohort | — |
| Agents | CC — below the B band | parameters: tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: optional · parameters: include_reasoning, reasoning |
| Document analysis | No measurement | — |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Intelligence index | 4.4 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Coding index | 43.4 | BB — next 30% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 4.2 | 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) |
|---|---|---|---|---|---|---|
| Google AI Studio | 262,144 | $0 | $0 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.