---
title: "Grok 4.7 API pricing: ⁨$2⁩ in, ⁨$6⁩ out · DotsAgent"
description: "Grok 4.7 by xAI: price per million input, cached and output tokens, context window, agent features and what a real agent task costs on it."
url: https://dotsagent.io/models/grok-4-7
---

[xAI](https://dotsagent.io/providers/xai)

· Flagship

# Grok 4.7 API pricing and specs

xAI's flagship reasoning model, with effort settings from low to xhigh and encrypted reasoning returned by the Responses API.

Input

$2

Cached input

$0.50

Output

$6

US dollars per million tokens, standard tier, short-prompt rate

There is no Batch API for this model. A faster variant at twice the price is offered only inside Cursor and xAI's own coding tool, not in the public API.

Prompts over 200K tokens are billed at $4 input, $1 cached and $12 output per million, and the higher rate applies to the whole request.

## Spec sheet

- **API model string**: `grok-4.7`
- **Provider**: [xAI](https://dotsagent.io/providers/xai)
- **Context**: 500K tokens
- **Max output**: —
- **Released**: September 21, 2026
- **Batch API**: No batch discount listed
- **Documented agent features**: Tool callingStructured outputBuilt-in web searchAdjustable reasoning

## What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

| Workload | Per task | Per 1,000 tasks |
| --- | --- | --- |
| Support bot 4 calls, short tool lookups | $0.052 | $52 |
| Coding agent 30 calls, files and test output | $2.68 | $2,684 |
| Browser agent 25 calls, screenshots and page text | $1.61 | $1,607 |
| Research agent 15 calls, long search results | $1.38 | $1,380 |

[Change the assumptions](https://dotsagent.io/cost#model=grok-4-7)

## Other xAI models

- [Grok 4.3](https://dotsagent.io/models/grok-4-3): $1.25 / $2.50

- [Grok Build 0.1](https://dotsagent.io/models/grok-build-0-1): $1 / $2

## Similar cost elsewhere

Models from other providers whose cost on the 30-step coding workload is closest to this one.

- [Kimi K3](https://dotsagent.io/models/kimi-k3): $2.97 per coding task

- [Claude Opus 5.5](https://dotsagent.io/models/claude-opus-5-5): $3.39 per coding task

- [Gemini 3.1 Pro Preview](https://dotsagent.io/models/gemini-3-1-pro-preview): $2.05 per coding task

- [Claude Sonnet 5.5](https://dotsagent.io/models/claude-sonnet-5-5): $1.98 per coding task

## Sources

1. [docs.x.ai](https://docs.x.ai/docs/models/grok-4.7)/docs/models/grok-4.7
2. [docs.x.ai](https://docs.x.ai/docs/models)/docs/models
3. [x.ai](https://x.ai/news/grok-4-7)/news/grok-4-7
4. [datastudios.org](https://www.datastudios.org/post/xai-launches-grok-4-7-its-most-powerful-model-yet-for-coding-agents-and-knowledge-work)/post/xai-launches-grok-4-7-its-most-powerful-model-yet-for-coding-age

Independent reference for people who build AI agents. Not affiliated with any vendor named here.

© 2026 DotsAgent · Facts checked October 1, 2026