⚠ This model is no longer available

Grok 4.7 was removed from RealRelay on 2026-10-19. This page is kept as a historical record: prices mentioned below are no longer valid, and the API no longer serves this model.

Grok 4.7

xAI's flagship model for coding, agentic tasks and knowledge work, with file, image and text input.

Similar models still available

Overview

Grok 4.7 is xAI's flagship model for coding, agentic tasks and knowledge work. xAI says it is particularly strong at long-running software engineering tasks and at verifying its own work. It supports reasoning, tool calling, structured output and vision, accepts file, image and text input, and returns text.

It has a 500,000-token context window. It accepts text, image and file input and returns text. It was released on September 21, 2026. Its knowledge cutoff is May 2026.

Capabilities

Grok 4.7 supports reasoning, tool calling and structured output, the three abilities that long-running agentic work depends on: planning a task, acting through tools, and returning results in a predictable format.

Beyond text, it accepts files and images as input, so a report, a screenshot or a design file can travel in the same request as the instructions. Responses are text.

Pricing

Grok 4.7 is priced from $2.00 per 1M input tokens and $6.00 per 1M output tokens. Cached input reads cost $0.50 per 1M tokens. The prices shown are for the starting tier; requests with very long prompts are billed at higher rates.

Grok 4.7 is available through RealRelay's OpenAI-compatible API.

Use cases

Use Grok 4.7 for long-running software engineering tasks, where an agent edits code, runs tools and checks its own work before reporting back with structured results.

It also fits knowledge work built on documents: send a file or screenshot with a question, and have the model extract, compare or summarise what it contains.

What is Grok 4.7?

Grok 4.7 is xAI's flagship model for coding, agentic tasks and knowledge work. xAI says it is particularly strong at long-running software engineering tasks and at verifying its own work. It supports reasoning, tool calling, structured output and vision, accepts file, image and text input, and returns text.

How much does Grok 4.7 cost?

Grok 4.7 is priced from $2.00 per 1M input tokens and $6.00 per 1M output tokens. Cached input reads cost $0.50 per 1M tokens. The prices shown are for the starting tier; requests with very long prompts are billed at higher rates.

What is the context window of Grok 4.7?

Grok 4.7 has a 500,000-token context window.

What inputs and outputs does Grok 4.7 support?

Grok 4.7 accepts text, image and file input and returns text.

Does Grok 4.7 support tool calling and structured output?

Yes. Grok 4.7 supports reasoning, tool calling and structured output, and it accepts files and images as well as text.

When was Grok 4.7 released?

Grok 4.7 was released on September 21, 2026.

How do I call Grok 4.7 through the API?

Call Grok 4.7 through RealRelay's OpenAI-compatible API by setting the model field to xai/grok-4.7.

Pricing

no longer offered
Grok 4.7 was removed from RealRelay on 2026-10-19. This page is kept as a historical record: prices mentioned below are no longer valid, and the API no longer serves this model.

Specifications (as of 2026-10-19)

Context window
500K
Released
2026-09-21
Knowledge cutoff
May 2026
Input
File / Image / Text
Output
Text
Capabilities
Reasoning, Structured output, Tool use, Vision