Checked against the OpenRouter public models feed. Prices are copied, not estimated.

The Best Model ForWhich AI model to use, from ten labs.

xAI (Grok) · Chat · x-ai/grok-4.7

Grok 4.7

Short answer

OpenRouter describes Grok 4.7 as SpaceXAI's flagship for coding, agentic tasks, and knowledge work, particularly long-running software engineering where the model checks its own work. Context on this row is 500,000 tokens. No knowledge cutoff is published. Grok 4.7 is listed at $2.00 input and $6.00 output per million tokens, with a 500,000-token context window. In: file, image, text. Out: text. Tools: Yes. Open weights: No public weights id listed.

Tools: Yes.

Facts

Facts for Grok 4.7. OpenRouter models API, checked 20 Nov 2026.
FactValueSource
Release date 21 Sep 2026 OpenRouter field created. This is the listing date the feed publishes. Checked 20 Nov 2026.
Context window 500,000 tokens OpenRouter field context_length. Checked 20 Nov 2026.
Max output 450,000 tokens OpenRouter field top_provider.max_completion_tokens. Checked 20 Nov 2026.
Input price $2.00 per million tokens. Published per-token rate 0.000002. OpenRouter field pricing.prompt, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Output price $6.00 per million tokens. Published per-token rate 0.000006. OpenRouter field pricing.completion, USD per token, multiplied by 1,000,000. Checked 20 Nov 2026.
Batch input price $1.60 per million tokens Sibling OpenRouter id ending in :batch, field pricing.prompt. Checked 20 Nov 2026.
Batch output price $4.80 per million tokens Sibling OpenRouter id ending in :batch, field pricing.completion. Checked 20 Nov 2026.
Input modalities file, image, text OpenRouter field architecture.input_modalities. Checked 20 Nov 2026.
Output modalities text OpenRouter field architecture.output_modalities. Checked 20 Nov 2026.
Tools Yes OpenRouter field supported_parameters contains tools. Checked 20 Nov 2026.
Open weights No public weights id listed OpenRouter field hugging_face_id. Empty means no public weights id is listed, which is not a legal opinion. Checked 20 Nov 2026.
Knowledge cutoff Unknown OpenRouter field knowledge_cutoff. Checked 20 Nov 2026.
Reasoning Supported, and the feed marks it required OpenRouter field reasoning. Missing means unknown, not unsupported. Checked 20 Nov 2026.
Other published prices web_search: 0.005 USD
input_cache_read: 0.0000005 USD
Other OpenRouter pricing fields, shown raw. The documented unit is USD per token, request, or unit — not converted to per million. Checked 20 Nov 2026.

A $0 token price does not mean the model is free to use. Another published price field is non-zero and may be the one you are billed on.

Listing blurb

Grok 4.7 is SpaceXSI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...

Listing blurb, via OpenRouter. It is their text, not a measurement by this site.

Third-party index

These numbers are copied from OpenRouter's benchmarks.artificial_analysis object, which attributes them to Artificial Analysis. The Best Model For did not run the test. A blank in the feed stays unknown.

Guide note · 19 Nov 2026

OpenRouter describes Grok 4.7 as SpaceXAI's flagship for coding, agentic tasks, and knowledge work, particularly long-running software engineering where the model checks its own work. Context on this row is 500,000 tokens. No knowledge cutoff is published.

What it is good for

A coding task that has to review its own patch

The listing calls out long-running engineering and self-checks. Use it when you will let a task run and you want a second pass in the same family. Read the patch anyway.

Grok 4.7 is listed at $2.00 input and $6.00 output per million tokens, with a 500,000-token context window.

Briefing from a stack of PDFs

File input and a large window hold several reports. Ask the briefing to quote the files. The feed does not list a cutoff, so do not treat silence as up-to-date knowledge.

Grok 4.7 is listed at $2.00 input and $6.00 output per million tokens, with a 500,000-token context window.

The tasks are editorial illustrations, not measured benchmarks. The prices in them are read from today's feed.

Questions

How much does Grok 4.7 cost?

Grok 4.7 is listed at $2.00 input and $6.00 output per million tokens, with a 500,000-token context window. A batch route is listed at $1.60 input and $4.80 output per million tokens. Other price fields, if any, are on this page and are not converted.

Does Grok 4.7 have open weights?

No public weights id is listed on the OpenRouter row. The Best Model For does not treat that as a legal claim that weights do not exist anywhere.

What is Grok 4.7 good for?

OpenRouter describes Grok 4.7 as SpaceXAI's flagship for coding, agentic tasks, and knowledge work, particularly long-running software engineering where the model checks its own work. Context on this row is 500,000 tokens. No knowledge cutoff is published.