Roboflow

GrokSpaceXAIReleased Sep 2026Proprietary

Grok 4.7

Grok 4.7 scores 63.5% overall on Roboflow's Vision Evals (October 26, 2026 snapshot), #33 of 65 models (Gemini 4 Argon leads at 87.5%).

Its best task is reasoning (64.2%, #25 of 65) and its weakest is object detection (40.4%, #47 of 65). It is a proprietary model from SpaceXAI, so commercial use follows SpaceXAI's terms.

Vision Evals63.5%Field median 63.5% · #33 of 65
Cost$0.020/ sampleField median $0.0033 · #58 of 65
Speed33.3s/ sampleField median 10.4s · #59 of 65

Grok 4.7 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 Grok 4.7.

Grok 4.7 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 October 26, 2026Pricing updated November 6, 2026

Strengths and weaknesses

Best showing

TaskScoreMedianRank
Reasoning64.2%58.1%#25 of 65

Weak spot

TaskScoreMedianRank
Object Detection40.4%56.4%#47 of 65

Below the field median.

Score by taskScoreRank
OCR
63.6%#25
Reasoning
64.2%#25
Identification
87.5%#27
Counting
61.7%#36
Object Detection
40.4%#47

Grok 4.7Field median

Ranks out of 65 models (49 for OCR)

Results by task

TaskScoreField (0 to 100)RankCost / sampleSpeed
Object Detection (low)
40.4%
±0.6, Mean of 3 runs, range 39.8 to 41.0
#47 of 65$0.02132.56s
Object Detection (high)
41.2%
±1.6, Mean of 3 runs, range 39.6 to 42.8
#30 of 33$0.02849.09s
Counting (low)
61.7%
±1.3, Mean of 3 runs, range 60.8 to 63.5
#36 of 65$0.01116.76s
Counting (high)
60.8%
±1.3, Mean of 3 runs, range 59.5 to 62.2
#30 of 33$0.01732.45s
Identification (low)
87.5%
±3.1, Mean of 3 runs, range 84.4 to 90.6
#27 of 65$0.00636.18s
Identification (high)
80.2%
±1.6, Mean of 3 runs, range 78.1 to 81.3
#31 of 33$0.009313.61s
OCR
63.6%
#25 of 49$0.02338.94s
Single value
54.4%
Transcription
89.5%
Structured JSON
86.4%
Text localization
14.8%
Reasoning (low)
64.2%
±2.3, Mean of 3 runs, range 62.3 to 66.9
#25 of 65$0.01526.03s
Reasoning (high)
66.9%
±1.3, Mean of 3 runs, range 65.6 to 68.2
#29 of 52$0.02451.09s
  • Thinking longer helps: 0.7 points higher on object detection at high effort for 1.4x the cost and 1.5x the latency.
  • Thinking longer does not help: 0.9 points lower on counting at high effort for 1.6x the cost and 1.9x the latency.
  • Thinking longer does not help: 7.3 points lower on identification at high effort for 1.5x the cost and 2.2x the latency.
  • Thinking longer helps: 2.7 points higher on reasoning at high effort for 1.7x the cost and 2x 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.

64 of 65 models plotted (the rest have no measured figure for this axis) · scores and efficiency pooled across all five tasks at low effort · Grok 4.7 highlighted

Grok 4.7 scores are the mean of 3 runs per task at both low and high effort; OCR is a single preliminary run · Methodology

View all Vision Evals →

Grok 4.7 Overview

Grok 4.7 is a proprietary multimodal reasoning model from SpaceXAI that accepts images alongside text and returns text-only output. On visual inputs it supports image captioning, visual question answering, OCR, document and chart question answering, and image classification and tagging, with all results expressed as generated text rather than bounding boxes or masks. Its 500,000 token context window leaves room for several images, long documents, or extended conversations about visual content in a single request.

Grok 4.7 Pricing

Grok 4.7 costs $2.00 per 1M input tokens and $6.00 per 1M output tokens.

Input$2.00 / 1M tokens
Output$6.00 / 1M tokens
Cached input$0.500 / 1M tokens

Pricing updated Nov 6, 2026

Deploy Grok 4.7 with an API

Grok 4.7 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 "Grok 4.7" workflow into my app.

- Endpoint: POST https://serverless.roboflow.com/<your-workspace>/workflows/grok-4-7-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 "grok-4-7-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="grok-4-7-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/grok-4-7-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/grok-4-7-captioning' \
--header 'Content-Type: application/json' \
--data '{
  "api_key": "YOUR_API_KEY",
  "inputs": {
    "image": {"type": "url", "value": "IMAGE_URL"}
  }
}'

Grok 4.7 License

Proprietary

Grok 4.7 is proprietary: the weights are not distributed, and the Grok 4.7 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. Grok 4.7 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 Grok 4.7?

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 Grok 4.7, 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.

Grok 4.7 Details

Details

Categoryclosed
Context Window500K
LicenseProprietary
Commercial usecommercial use per vendor terms
Release DateSep 2026

Vision Tasks

CaptioningChart Question AnsweringClassificationDocument Question AnsweringImage TaggingMulti-Label ClassificationOCRVision LanguageVisual Question AnsweringObject Detection

Usage

Past 30 Days

Alternatives to Grok 4.7

Other models worth comparing for similar use cases.

Anthropic
Claude Opus 5.5
Claude Opus 5.5 is a proprietary multimodal reasoning model from Anthropic and the first entry in the Claude 5.5 family.
OpenAI
GPT-6.1 Sol
GPT-6.1 Sol is a reasoning model in OpenAI's GPT-6 series that accepts text and image input and returns text.
Google
Gemini 4 Argon
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…
MoonshotAI
Kimi K3
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.
Qwen
Qwen3.8 Max
Qwen3.8 Max is the flagship tier of Alibaba's Qwen3.8 family, a sparse mixture-of-experts multimodal model with roughly 2.4 trillion total parameters of which about 95 billion…
Mistral
Mistral Large 4
Mistral Large 4, nicknamed Le Chonk, is a natively multimodal mixture-of-experts model from Mistral that accepts interleaved text and image input and produces text output.

Frequently Asked Questions About Grok 4.7 Vision

Yes. Grok 4.7 accepts image input and handles OCR, object counting, identification, visual reasoning, and object detection. On Roboflow's Vision Evals its strongest task is OCR at 63.6% (#25 of 49 at low effort). You can test it on your own image in the demo above.

Yes. it scores 63.6% (#25 of 49 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 89.5%, and returning the fields of a label or form as JSON scores 86.4%.

Not its strength. On Vision Evals, Grok 4.7 scores 40.4% mAP@50 on object detection (#47 of 65 at low effort) and 61.7% judge-graded accuracy on object counting. For production counting or precise localization, pairing it with a specialized detector like RF-DETR or your own trained model in a Roboflow Workflow is usually more reliable: detect the objects, then count the detections.

On our benchmark's task mix, Grok 4.7 averages $0.02 per sample at $2.00 per 1M input and $6.00 per 1M output tokens (#58 of 65 on cost), with an average speed of 33.3s per sample across the benchmark. Actual cost depends on your images and prompts.

On the overall Vision Evals ranking, Grok 4.7 sits #33 of 65 at 63.5%, just behind Qwen3.5 27B (64.1%) and just ahead of Qwen3.5 35B-A3B (62.5%). See the full side-by-side: Grok 4.7 vs Qwen3.5 27B.