xAI's coding and knowledge-work model, released on September 21, 2026. This page collects official parameters, independent evaluations, and community task notes. Availability in Tabbit depends on your account's live model picker.
Use in Tabbit
Use in Tabbit Grok 4.7
Grok 4.7 · Model overview
Check the evidence before choosing a workflow
A compact view of reviewed task guides, public evaluations, and evidence boundaries. Client access still depends on your current account.
The OpenRouter model page labels x-ai/grok-4.7 as SpaceXAI's Grok 4.7, lists input / output prices of $1.60 / $4.80 per million tokens, and gives OpenRouter SDK and cURL examples; the reasoning-level field in the request body, and the list prices for Low, Medium, and High, were not read in this collection.
Prepare
model ID, reasoning or call parameters, API endpoint, task, acceptance criteria
Runtime
The Quick Start says the OpenRouter API is OpenAI-compatible, and shows the OpenRouter SDK and POST https://openrouter.ai/api/v1/chat/completions.
xAI Official Documentation: Grok 4.7 API Parameters and Reasoning Levels
The model name on the public xAI API is grok-4.7. The reasoning levels listed in the documentation are Low, medium, high (default), or xhigh, with an input price of $2.00 / 1M tokens and an output price of $6.00 / 1M tokens. Grok 4.7 Fast is written as a faster deployment of the same model, billed at twice the standard token price, and it appears only in Cursor and Grok Build.
Prepare
model ID, reasoning or call parameters, API endpoint, task, acceptance criteria
Runtime
the xAI API's Responses API and Chat Completions; the US regional endpoint https://us.api.x.
Box's prompt and result for reviewing the Merewick claim with Grok 4.7 in AI Studio
This Box post is a 41-second Box Agent preview. In Box AI Studio, Grok 4.7 is selected and a claim-review prompt is entered for the folder "Active Commercial Property Claims", producing the file Claim Reconciliation Review Merewick Coastal Foods ASC-26-0184.md.
Prepare
case to reproduce, model ID, client, acceptance criteria
Runtime
The address bar in the video is app.box.com/ai, and after submission it is app.box.com/ai/sessions/15102758759. The post calls this a Box Agent preview and points to Box AI Studio.
xAI News (the browser title suffix is SpaceXAI; the footer copyright is SpaceXAI LLC)Vendor report
Grok 4.7 Benchmarks: Official Scores on CursorBench 4.0, DeepSWE v1.1 & EEBench
xAI positions Grok 4.7 as a coding and knowledge-work model and self-reports CursorBench 4.0, DeepSWE v1.1 and EEBench scores — vendor claims from the 2026-09-21 release page, not an independent rerun.
Evidence
Vendor report
Boundary
Treating the scores on this page as a third-party rerun; replacing the speed and price slogans in the headline with a measured comparison experiment; folding results for the fast variant, Grok 4.6, or other reasoning tiers into Grok 4.7 xHigh; comparing win rates or cost efficiency without a sample size, a harness。
xAI / SpaceXAI official model-card PDF (hosted on media.x.ai)Vendor report
xAI Official Model Card: Grok 4.7 Safety Evaluation and Use Boundaries
The official model card describes Grok 4.7 as a deployed checkpoint after Grok 4.6, aimed at coding, engineering, and office tasks. It lists available channels, the training cutoff date, and capability and safety scores at the xhigh or high tier. The card does not mention a fast variant or an API model ID.
Evidence
Vendor report
Boundary
Treating official scores as a third-party rerun; applying a score from one tier to another; counting results for Grok 4.6, Grok 4.5, or comparison models as Grok 4.7 results; using unprotected capability probes as a substitute for post-deployment refusal behavior; or adding fast variants, consumer products。
Grok 4.7 Scores 46 on Intelligence Index v4.3 — Artificial Analysis Measurement
Artificial Analysis measured Grok 4.7 at xhigh: Intelligence Index v4.3 of 46 and Coding Agent Index v1.5 of 56 on Grok Build, beating Grok 4.6 on knowledge-work Elo.
Evidence
Independent measurement
Boundary
Substituting the scores on this page for the self-reported benchmarks on the xAI release page; treating Grok 4.6 high and xhigh as the same tier; treating Terminal-Bench 4.0 in the Coding Agent Index as the same-named item in the Intelligence Index; reading about 7.1 minutes as end-to-end wall-clock time that includes。
Review Grok 4.7 API configuration, official benchmarks, independent evaluations, and community reports, then check availability in your account's live model picker.
