Roboflow

GoogleGoogleReleased Feb 2026Proprietary

Gemini 3.1 Pro

Gemini 3.1 Pro scores 76.8% overall on Roboflow's Vision Evals (November 17, 2026 snapshot), #20 of 72 models (GPT-6.2 Sol leads at 90.3%).

Its best task is object detection (67.4%, #19 of 72) and it ranks lowest on counting (71.6%, #26 of 72), a task most models score well on. It is a proprietary model from Google, so commercial use follows Google's terms.

Vision Evals76.8%Field median 65.3% · #20 of 72
Cost$0.010/ sampleField median $0.0037 · #57 of 72
Speed8.4s/ sampleField median 10.2s · #22 of 72

Gemini 3.1 Pro Interactive Demo

Model settings

Thinking level

Max output tokens

Default 65,536 · max 65,536

Sign in to adjust thinking and output length per run.

Results appear here. Add an image or pick an example to run Gemini 3.1 Pro.

Gemini 3.1 Pro Vision Evals

Vision Evals is Roboflow's ground-truth benchmark: every model runs the same real-world samples across five vision tasks, and answers are scored against ground truth.

Evals updated November 17, 2026Pricing updated November 18, 2026

Strengths and weaknesses

Strengths

TaskScoreMedianRank
Identification100.0%85.9%#1 of 72

Weak spot

TaskScoreMedianRank
Counting71.6%66.0%#26 of 72

Above the field median, but its lowest rank.

Score by taskScoreRank
Identification
100.0%#1
OCR
72.6%#18
Object Detection
67.4%#19
Reasoning
72.2%#24
Counting
71.6%#26

Gemini 3.1 ProField median

Ranks out of 72 models (56 for OCR)

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection
67.4%
#19 of 72$0.0108.76s
Counting
71.6%
#26 of 72$0.00716.19s
Identification
100.0%
#1 of 72$0.00705.93s
OCR (low)
72.6%
#18 of 56$0.0108.51s
OCR (high)
73.1%
#19 of 56$0.02618.64s
Reasoning (low)
72.2%
#24 of 72$0.0129.27s
Reasoning (high)
74.8%
#23 of 59$0.02113.32s
  • Thinking longer helps: 0.5 points higher on ocr at high effort for 2.6x the cost and 2.2x the latency.
  • Thinking longer helps: 2.6 points higher on reasoning at high effort for 1.8x the cost and 1.4x the latency.

Price vs. performance

Score vs. cost

Overall benchmark score against estimated cost per sample, on a log scale. Upper-left is the sweet spot: high quality at low cost.

71 of 72 models plotted (the rest have no measured figure for this axis) · scores and efficiency pooled across all five tasks at low effort · Gemini 3.1 Pro highlighted

Gemini 3.1 Pro scores are from a single run per task; a three-run re-run under the current protocol is pending · Methodology

View all Vision Evals →

Gemini 3.1 Pro Overview

Gemini 3.1 Pro is a proprietary multimodal model from Google’s Gemini 3 series, released in early 2026 and designed for advanced reasoning across large multimodal datasets. It accepts text, images, audio, video, and documents, supporting up to a 1-million-token input context with up to 64k output tokens. Compared with Gemini 3 Pro, it improves long-context synthesis and multi-step reasoning, enabling more reliable analysis of large documents, datasets, and software codebases.

Gemini 3.1 Pro Pricing

Gemini 3.1 Pro costs $2.00 per 1M input tokens and $12.00 per 1M output tokens.

Input$2.00 / 1M tokens
Output$12.00 / 1M tokens
Cached input$0.200 / 1M tokens

Pricing updated Nov 18, 2026

Deploy Gemini 3.1 Pro with an API

Gemini 3.1 Pro runs as a hosted REST endpoint through Roboflow Workflows. Pick a task, then hand the prompt to your coding agent or copy the code. Deploying the workflow into a free Roboflow workspace replaces the your-workspace and YOUR_API_KEY placeholders with your own.

Connect your agent to Roboflow (once)

Add the Roboflow MCP server

claude mcp add --transport http roboflow https://mcp.roboflow.com/mcp

Run /mcp and authorize Roboflow in your browser when the OAuth flow opens.

Start a new Claude Code session so the MCP loads, then paste the prompt below (it works the same in any agent).

Deploy this workflow to your Roboflow workspace to use it.

Integrate the Roboflow "Gemini 3.1 Pro" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/gemini-3-1-pro-captioning
- Auth: send my Roboflow API key as `api_key` in the request body, read from the ROBOFLOW_API_KEY env var (never hardcode).
- Body: { "api_key": ..., "inputs": { `image`: { type: "url" | "base64", value } } }.
- Billing: this workflow needs no provider API key — inference runs on my Roboflow credits. A BYO provider key can be added to the model step in the Roboflow workflow editor later.

With the Roboflow MCP connected, call `workflows_get` on "gemini-3-1-pro-captioning" to read the exact input schema (the source of truth), then `workflows_run` on a sample image to confirm the output shape before writing code (the MCP is authenticated, so this needs no key). Without the MCP, use the contract above.

Before running the app, set up these keys so it does not error at runtime:
- `ROBOFLOW_API_KEY` (sent as `api_key`) from https://app.roboflow.com/settings/api
Create a .gitignore'd .env with these variables, using placeholder values for any I haven't given you. Then pause and tell me directly, in your reply: the full path to the .env file, exactly which keys I need to paste in, and the link to get each one. Wait for me to confirm I've added them before you run anything. Do not run the app until I confirm.

Then add the integration to my codebase: match my project's language, framework, and conventions; read every key from environment variables (never hardcode); add basic error handling; and include a small runnable example. If you can't tell what language my project uses, ask me.
Installpip install inference-sdk

Deploy this workflow to your Roboflow workspace to use it.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
# 1. Import the library
from inference_sdk import InferenceHTTPClient

# 2. Connect to your workflow
client = InferenceHTTPClient(
  api_url="https://serverless.roboflow.com",
  api_key="YOUR_API_KEY"
)

# 3. Run your workflow on an image
result = client.run_workflow(
  workspace_name="your-workspace",
  workflow_id="gemini-3-1-pro-captioning",
  images={
    "image": "YOUR_IMAGE.jpg"  # Path to your image file
  },
  use_cache=True  # cache workflow definition for 15 minutes
)

# 4. Get your results
print(result)

Deploy this workflow to your Roboflow workspace to use it.

// Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
const response = await fetch('https://serverless.roboflow.com/your-workspace/workflows/gemini-3-1-pro-captioning', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    api_key: 'YOUR_API_KEY',
    inputs: {
      "image": {"type": "url", "value": "IMAGE_URL"}
    }
  })
});

const result = await response.json();
console.log(result);

Deploy this workflow to your Roboflow workspace to use it.

# Inference runs on your Roboflow credits — no provider API key needed. To bill your own provider account instead, add an api_key to the model step in the Roboflow workflow editor.
curl --location 'https://serverless.roboflow.com/your-workspace/workflows/gemini-3-1-pro-captioning' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"}
  }
}'

Gemini 3.1 Pro License

Proprietary

Gemini 3.1 Pro is proprietary: the weights are not distributed, and the Gemini 3.1 Pro license is the vendor's commercial terms of service that you accept when you call the API.

Commercial use
Permitted under the vendor terms, typically metered per token or per request, with the vendor usage policy applying to your inputs and outputs.
Modification
Not available. Gemini 3.1 Pro weights are closed, so you can configure prompts and use vendor-hosted fine-tuning where it is offered, but you cannot modify the model itself.
Redistribution
Not permitted. You cannot self-host or resell the model; you build on the hosted API instead.

Vendor terms govern data retention, whether your inputs can be trained on, rate limits, and regional availability, and they can change with notice. Review them if you handle regulated or customer data.

Do I need a commercial license for Gemini 3.1 Pro?

Proprietary terms are set by the vendor rather than negotiated per project, and no open-source obligation attaches to your code. If you would rather deploy an open model instead of Gemini 3.1 Pro, Roboflow's licensing page lists the models whose commercial license is included when you deploy on Roboflow.

Do not hesitate to reach out with questions for your commercial project. Our team will help you start solving business problems on the first call. See Roboflow commercial licensing for the models included in each plan.

Talk to sales

License information is provided as a guide and is not legal advice.

Gemini 3.1 Pro Details

Details

Categoryclosed
ModalityMultimodal
Context Window1.0M
LicenseProprietary
Release DateFeb 2026

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRObject DetectionVision LanguageVisual Question Answering

Usage

Past 30 Days

Alternatives to Gemini 3.1 Pro

Other models worth comparing for similar use cases.

Gemini 4 Argon is Google DeepMind's frontier Gemini 4 model, built to sustain extended reasoning across long-horizon workflows in software engineering, enterprise knowledge work…
Claude Opus 4.7 is a proprietary multimodal language model developed by Anthropic, released on April 16, 2026.
OpenAI
GPT-6 Sol is a proprietary multimodal reasoning model from OpenAI, released on September 22, 2026 alongside GPT-6 Luna as an efficiency-oriented tier of the GPT-6 family that…
Qwen3.5-397B-A17B is a 397B-parameter (17B active) open-weight multimodal model developed by Alibaba’s Qwen team, released on 2026-02-16 under Apache-2.0.
Grok 4.6 is a proprietary reasoning model from xAI aimed at long-running agentic workflows, coding, and knowledge work.
MoonshotAI
Kimi K3 is a sparse Mixture-of-Experts large language model developed by Moonshot AI, with 2.8 trillion total parameters and a 1-million-token context window.

Other Google Gemini Pro models

Other versions in the same family as Gemini 3.1 Pro.

Frequently Asked Questions About Gemini 3.1 Pro Vision

Yes. Gemini 3.1 Pro accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is Identification at 100% (#1 of 72 at low effort). You can test it on your own image in the demo above.

Yes, and it is one of the model's strongest vision skills: it scores 72.6% (#18 of 56 at low effort) on Vision Evals OCR, which covers single readings, full transcriptions, structured JSON, and locating text with boxes. Within that, full transcriptions score 88.5%, and returning the fields of a label or form as JSON scores 82.1%.

It's serviceable. On Vision Evals, Gemini 3.1 Pro scores 67.4% mAP@50 on object detection (#19 of 72 at low effort) and 71.6% judge-graded accuracy on object counting.

On our benchmark's task mix, Gemini 3.1 Pro averages $0.01 per sample at $2.00 per 1M input and $12.00 per 1M output tokens (#57 of 72 on cost), with an average speed of 8.4s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Gemini 3.1 Pro sits #20 of 72 at 76.8%, just behind GPT-6 Sol (76.9%) and just ahead of Muse Ember (76.6%). See the full side-by-side: Gemini 3.1 Pro vs GPT-6 Sol.