Enterprise DNAEnterprise DNA
xAI logo

Models · Best vision

Grok 4.7

by xAI

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

Visit xAI ↗

Our verdict

Not reviewed yet

We have not reviewed Grok 4.7 yet

No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.

How we review records

From the listing

About Grok 4.7

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6.

Best for

Reasoning and tool-connected analysis

Notes

Grok 4.7 is listed in the EDNA Models directory from the OpenRouter catalogue.

Pros

  • Working over supplied documents with explicit questions
  • text, image, file input; text output on the listed OpenRouter route

Cons

  • Assuming the API has current web knowledge without search tools
  • Letting retrieved web text issue instructions to an agent
  • Catalogue base token rates have additional pricing overrides. Context length, time window, caching, reasoning, tools or media can change total cost; the simple calculator is not a full quote.

Key facts

What we have checked

Input price
$2.00 per million tokens
Checked OpenRouter models API
Output price
$6.00 per million tokens
Checked OpenRouter models API
Price on amazon-bedrock
$0.500 per million cached input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$2.00 per million input tokens
Checked OpenRouter models API
Price on amazon-bedrock
$6.00 per million output tokens
Checked OpenRouter models API
Price on xai
$0.500 per million cached input tokens
Checked OpenRouter models API
Price on xai
$2.00 per million input tokens
Checked OpenRouter models API
Price on xai
$6.00 per million output tokens
Checked OpenRouter models API
Latest version
x-ai/grok-4.7-20260916
Checked OpenRouter models API
Gpqa diamond
92.7% (for 21 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Frontiermath tiers 1 3 v2 private
53% (for 21 Sept 2026)
Checked Epoch AI (CC BY 4.0)
Simpleqa verified
56% (for 21 Sept 2026)
Checked Epoch AI (CC BY 4.0)

Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.

API access

How to call it

Call via OpenRouter with model id `x-ai/grok-4.7`.

  • openrouter · x-ai/grok-4.7 · Docs

OpenRouter id: x-ai/grok-4.7

Price

What Grok 4.7 costs, over time

Input price

$1.60 to $2.00

US dollars per million input tokens. 24 Sept 2026 to 7 Nov 2026, 34 days.

Source: OpenRouter models API. Checked .

Output price

$4.80 to $6.00

US dollars per million output tokens. 24 Sept 2026 to 7 Nov 2026, 34 days.

Source: OpenRouter models API. Checked .

Prices by host

HostPriceOver timeChecked
amazon-bedrockCached input$0.500 per million cached input tokensSince 7 Nov 2026No change recordedOpenRouter models API
amazon-bedrockInput$2.00 per million input tokensSince 7 Nov 2026No change recordedOpenRouter models API
amazon-bedrockOutput$6.00 per million output tokensSince 7 Nov 2026No change recordedOpenRouter models API
xaiCached input$0.500 per million cached input tokensSince 24 Oct 2026No change recordedOpenRouter models API
xaiInput$2.00 per million input tokensSince 24 Oct 2026No change recordedOpenRouter models API
xaiOutput$6.00 per million output tokensSince 24 Oct 2026No change recordedOpenRouter models API

Usage

How much Grok 4.7 is used

Tokens served a day

10B to 32.2B

tokens a day on OpenRouter. 21 Sept 2026 to 7 Nov 2026, 48 readings.

Source: OpenRouter model activity (741 of 741 series). Checked .

Scores

How Grok 4.7 scores

Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.

ScoreValueSourceChecked
Artificial Analysis Intelligence Index35.5indexAs of 7 Nov 2026Artificial Analysis via OpenRouter
LMArena text rating (Elo)1,398EloAs of 7 Nov 2026LMArena (CC-BY-4.0), published 2026-11-06
LMArena web development rating (Elo)1,638EloAs of 7 Nov 2026LMArena (CC-BY-4.0), published 2026-11-06
LMArena vision rating (Elo)1,231EloAs of 7 Nov 2026LMArena (CC-BY-4.0), published 2026-11-06
Design Arena rating (Elo)1,313EloAs of 7 Nov 2026Design Arena via OpenRouter
Apex agents (best-across-versions)54.6percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Arc agi (best-across-versions)90.2percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Arc agi 2 (best-across-versions)61.4percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Chess puzzles (best-across-versions)41percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Dtbench (best-across-versions)96percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Frontiercode (best-across-versions)47.6percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Frontiermath tier 4 v2 private (best-across-versions)17.1percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Show 10 more scores
ScoreValueSourceChecked
Frontiermath tiers 1 3 v2 private (best-across-versions)53percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Frontierswe (best-across-versions)29.5percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Furniture assembly (best-across-versions)20.8percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Gpqa diamond (best-across-versions)92.7percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Lmca (best-across-versions)49.4percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Mystery game puzzles (best-across-versions)29percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Otis mock aime 2024 2025 (best-across-versions)Saturated98.1percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Proofbench (best-across-versions)26percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Simpleqa verified (best-across-versions)56percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Weirdml v3 (best-across-versions)18.7percentAs of 21 Sept 2026Epoch AI (CC BY 4.0)
Saturated
Top models score close to the maximum, so this test no longer separates them.

Sources

Where this comes from

A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.

Changelog

What changed

  1. Price changed

    output per mtok: 4.8 to 6

    Source: OpenRouter models API

  2. Price changed

    input per mtok: 1.6 to 2

    Source: OpenRouter models API

USAGE / OPENROUTER

How much Grok 4.7 is used

Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.

Tokens, last 7 days
241B ▼19.4%
Requests, last 7 days
6.1M
Tool calls, last 7 days
2.5M
Intelligence score
35.5
People's vote
1398
Average cost per request
$3.85
Price per million tokens
$2 in · $6 out
0100B200B21 Sept: 10B tokens, 206K requests22 Sept: 60.1B tokens, 1M requests23 Sept: 37.9B tokens, 743K requests24 Sept: 41.4B tokens, 808K requests25 Sept: 120B tokens, 1.7M requests26 Sept: 58.2B tokens, 1M requests27 Sept: 42.4B tokens, 779K requests28 Sept: 34.9B tokens, 638K requests29 Sept: 45.3B tokens, 743K requests30 Sept: 57.7B tokens, 910K requests1 Oct: 52B tokens, 884K requests2 Oct: 94.8B tokens, 1.5M requests3 Oct: 19.3B tokens, 436K requests4 Oct: 37B tokens, 623K requests5 Oct: 67.5B tokens, 858K requests6 Oct: 76.8B tokens, 1.1M requests7 Oct: 113B tokens, 1.5M requests8 Oct: 172B tokens, 2.1M requests9 Oct: 138B tokens, 1.6M requests10 Oct: 57B tokens, 685K requests11 Oct: 26.7B tokens, 545K requests12 Oct: 55.4B tokens, 845K requests13 Oct: 81.5B tokens, 1.3M requests14 Oct: 61.4B tokens, 915K requests15 Oct: 55.2B tokens, 989K requests16 Oct: 40.1B tokens, 724K requests17 Oct: 19B tokens, 682K requests18 Oct: 36.3B tokens, 644K requests19 Oct: 30.6B tokens, 692K requests20 Oct: 42.6B tokens, 774K requests21 Oct: 82.3B tokens, 1.1M requests22 Oct: 151B tokens, 1.8M requests23 Oct: 118B tokens, 1.7M requests24 Oct: 51.3B tokens, 1.1M requests25 Oct: 54.9B tokens, 897K requests26 Oct: 47.1B tokens, 892K requests27 Oct: 40.7B tokens, 793K requests28 Oct: 41B tokens, 920K requests29 Oct: 39.9B tokens, 893K requests30 Oct: 39.7B tokens, 836K requests31 Oct: 36B tokens, 810K requests1 Nov: 25.1B tokens, 595K requests2 Nov: 29.9B tokens, 798K requests3 Nov: 34.2B tokens, 902K requests4 Nov: 42.1B tokens, 1.1M requests5 Nov: 37.7B tokens, 1.1M requests6 Nov: 40.1B tokens, 935K requests7 Nov: 32.2B tokens, 724K requests21 Sept5 Oct19 Oct2 Nov7 NovSee where it ranks on the leaderboard →

MODEL FIELD GUIDE / SOURCE EVIDENCE

What you can do with Grok 4.7.

Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-11-03. Hosting routes and app features can differ.

DeveloperxAI
Exact model identifierx-ai/grok-4.7
Inputtext, image, file
Outputtext
Tool calling
Listed support
Structured output
Listed support
Reasoning controls
Listed support
Availability
available
Price basis
token
Licence verification
Check the developer licence; the model name is insufficient
Context length
500K tokens
Knowledge cutoff
Not established
Developer release date
Not established
First seen in the catalogue
21 Sept 2026
Listed retirement date
Not established

Catalogue base token rates have additional pricing overrides. Context length, time window, caching, reasoning, tools or media can change total cost; the simple calculator is not a full quote.

Consider it for

  • Working over supplied documents with explicit questions
  • Designing a read-only research workflow

Watch for

  • Assuming the API has current web knowledge without search tools
  • Letting retrieved web text issue instructions to an agent

PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA

Try the model on a small, checkable task.

Create a read-only research plan to compare three supplier return policies. Specify sources, dates and fields to capture; do not browse, buy or contact anyone.

Check the result: The plan requires official dated policies, handles missing evidence and contains no purchase or contact step.

Compare another approach

anthropic claude sonnet 5 5 ↗openai gpt 6 1 sol ↗
Inspect the sources and their scope
provider source ↗

Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.

Checked 2026-10-19
catalogue source ↗

x-ai/grok-4.7: listed route capabilities, availability and prices; provider endpoints can differ.

Checked 2026-11-03
openrouter.ai ↗

Source for reasoning controls, first seen, tool calling, context length, input, output, structured output.

Checked 2026-11-03
How to evaluate a model for your work →

FROM SPECIFICATIONS TO YOUR WORK

Is this the right model for your job?

Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.

Extract document dataWorkflow & starter prompt ↗Run a reliable agentWorkflow & starter prompt ↗

What would it cost?

Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.

Working out the cost...

Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗

Check the source

Price date: 7 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.

Model source & availability ↗

Understand the evidence

Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.

Intelligence Index: 35.5 (2026-11-06) ↗Vals Index: 58.564 (2026-11-06) ↗Design Arena: 1313 (2026-11-06) ↗
Compare this model with alternatives →
Free 27-page guide

Get the free Developer’s Field Guide

A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.

Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.

No spam. Unsubscribe any time.

← Back to ModelsSubmit your own entry →