Google: Gemini 3.1 Pro Preview (batch)
google/gemini-3.1-pro-preview:batch
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
Google's Gemini 3.1 Pro Preview is listed on OpenRouter as a preview multimodal reasoning model in a batch variant. According to the catalog, it accepts text, image, file, audio and video inputs and returns text, with a context window of roughly one million tokens and mandatory reasoning at adjustable effort levels. The listing reports tool calling and structured output support, and records measured results in coding and agentic evaluations. Because the evidence comes from a catalog entry only, capabilities should be validated on real workloads.[1]
Strengths
- The catalog lists a roughly one-million-token context window with text, image, file, audio and video inputs, suiting large multimodal prompts.[1]
- Reasoning effort is selectable across low, medium and high levels, and the listing exposes tool calling, structured outputs and response format controls.[1]
- The catalog records measured results in coding and agentic evaluations, while Google's description claims improved software engineering performance and agentic reliability for this preview.[1]
Limitations
- All evidence here is a single OpenRouter catalog entry; no independent model card was available in this source pack, so vendor-stated capabilities remain unverified.[1]
- The listing marks reasoning as mandatory and output as text only, which may constrain latency-sensitive applications or those needing non-text outputs.[1]
- Preview status and absent fields such as knowledge cutoff mean stability and recency should be validated on real workloads before production use.[1]
Where to use it
- Batch processing of large or multimodal inputs, such as document, audio or video analysis where latency is not critical.[1]
- Software engineering or agentic workflows that can use tool calling and structured outputs, pending validation on the user's own tasks.[1]
- Long-context summarization or question answering over large files, given the catalog-reported context window.[1]
Sources
- [1] OpenRouter catalog · Google: Gemini 3.1 Pro Preview (batch)Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal foundation...
Specifications
- Model ID
- google/gemini-3.1-pro-preview:batch
- Canonical ID
- google/gemini-3.1-pro-preview-20260219
- Creator
- Added to OpenRouter
- 19.02.2026
- Context length
- 1,048,576
- Modality
- text+image+file+audio+video->text
- Input modalities
- audio, file, image, text, video
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $1 / out $6
- 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 | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Coding | AA — next 20% of the cohort | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | reasoning: mandatory · default medium · efforts: high, medium, low · parameters: include_reasoning, reasoning, reasoning_effort |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | input: audio |
| Video | No measurement | input: video |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 68.8 | AA — next 20% of the cohort | 13.11.2026 |
| Artificial Analysis | Agentic index | 8.2 | CC — below the B band | 13.11.2026 |
| Design Arena | agents · agenticgamedevwin rate 43.9% · rank 23 | 1,061Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · agentichtmlslideswin rate 55.8% · rank 4 | 1,226Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslideswin rate 33.8% · rank 7 | 1,112Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslides(html)win rate 54.4% · rank 4 | 1,219Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · agenticslides(python-pptx)win rate 33.9% · rank 7 | 1,107Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · androidnativewin rate 41.1% · rank 40 | 1,035Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · blender3dwin rate 39.8% · rank 18 | 1,037Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · codetovideowin rate 44.8% · rank 15 | 1,122Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · fullstackwin rate 40.5% · rank 34 | 1,047Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · godotgamedevwin rate 54.4% · rank 19 | 1,145Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | agents · htmlslideswin rate 48.5% · rank 18 | 1,048Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · mobileappswin rate 42.3% · rank 42 | 1,088Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · pdfwin rate 39.7% · rank 29 | 1,107Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · pptxslideswin rate 34.1% · rank 7 | 1,110Elo | —Not rated | 13.11.2026 |
| Design Arena | agents · python-pptxslideswin rate 31.9% · rank 25 | 1,109Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · spreadsheetwin rate 32.5% · rank 28 | 1,020Elo | CC — below the B band | 13.11.2026 |
| Design Arena | agents · webappswin rate 44.2% · rank 35 | 1,108Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 58.5% · rank 46 | 1,217Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · asciiartwin rate 63.5% · rank 14 | 1,265Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 64.4% · rank 48 | 1,234Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · datavizwin rate 61.8% · rank 40 | 1,237Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · gamedevwin rate 52.4% · rank 60 | 1,192Elo | BB — next 30% of the cohort | 13.11.2026 |
| Design Arena | models · svgwin rate 67.9% · rank 13 | 1,276Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 69.4% · rank 32 | 1,271Elo | AA — next 20% of the cohort | 13.11.2026 |
| Design Arena | models · websitewin rate 64.4% · rank 47 | 1,245Elo | BB — next 30% of the cohort | 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) |
|---|---|---|---|---|---|---|
| 1,048,576 | $1 | $6 | — | — | — |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.