# Grok Code Fast 1

> xAI's first dedicated agentic coding model — fast, cheap, 256K context, text-only.

- Maker: xAI (Grok)
- Line: Grok Code
- Canonical page: https://ai-tldr.dev/models/grok-code-fast-1/
- Updated: 2026-06-18

## In short

Grok Code Fast 1 is xAI's first model built specifically for agentic coding, released on August 28, 2025. It has a 256K-token context window and costs $0.20 per million input tokens and $1.50 per million output tokens. You can use it through xAI, OpenRouter and Oracle Cloud (OCI Generative AI).

## Facts

| Fact | Value | Source |
| --- | --- | --- |
| Context window | 256K (max output 16K) | [1] |
| Input price | $0.20 per million tokens (cached $0.02) | [2] |
| Output price | $1.50 per million tokens | [2] |
| Licence | Proprietary · API only | [1] |
| Released | 28 August 2025 | [3] |
| Knowledge cutoff | Not disclosed by xAI | [1] |

## Sources

1. [Grok Code Fast 1 on OpenRouter](https://openrouter.ai/x-ai/grok-code-fast-1)
2. [xAI Releases Grok Code Fast 1 (InfoQ)](https://www.infoq.com/news/2025/09/xai-grok-fast1/)
3. [Grok Code Fast 1 — official announcement](https://x.ai/news/grok-code-fast-1)

## Overview

Grok Code Fast 1 is xAI's first model built specifically for agentic coding, released on August 28, 2025. Internally codenamed "sonic," it is positioned as a speedy and economical reasoning model that handles the high-volume, iterative work of software development — reading code, calling tools, and editing files inside coding agents — rather than a general-purpose chat model.

xAI says it built Grok Code Fast 1 from scratch on a new architecture, using a pre-training corpus rich in programming content and post-training on datasets reflecting real-world pull requests and coding tasks. The model is text-only (no image, audio, video, or document input), ships with a 256K-token context window, and was tuned for low latency and aggressive prompt caching so it stays interactive during agent loops. xAI reported throughput of roughly 90–100 tokens per second in partner workflows.

At launch the model was offered free for a limited time through GitHub Copilot, Cursor, Cline, Kilo Code, Roo Code, opencode, and Windsurf, then priced very cheaply on the xAI API at $0.20 per million input tokens and $1.50 per million output tokens. Grok Code Fast 1 was deprecated on May 15, 2026, with retirement scheduled for August 15, 2026, as xAI moved its coding line toward newer Grok Code / Grok Build models.

## Benchmarks

- SWE-bench Verified: 70.8% ([source](https://www.infoq.com/news/2025/09/xai-grok-fast1/))

## Pricing

- Input: $0.20 per million tokens
- Cached input: $0.02 per million tokens
- Output: $1.50 per million tokens

Offered free for a limited time at launch through partners including GitHub Copilot, Cursor, Cline, Kilo Code, Roo Code, opencode, and Windsurf.

Source: https://www.infoq.com/news/2025/09/xai-grok-fast1/

## Strengths

- Purpose-built for agentic coding: reading, editing, and tool-calling inside coding agents
- Very low cost — $0.20 input / $1.50 output per million tokens
- Low latency with high throughput (~90–100 tokens/sec reported), keeping agent loops interactive
- 256K-token context window for working across larger codebases
- Aggressive prompt caching ($0.02/1M cached input) suited to repeated agent prompts
- Strong reported coding result: 70.8% on SWE-bench Verified (xAI's internal harness)

## Best for

- Agentic coding inside tools like Cursor, Cline, GitHub Copilot, and Windsurf
- High-volume, iterative code editing and refactoring where cost and speed matter
- Codebase navigation and multi-file changes within a 256K context
- Drafting and resolving pull-request-style fixes
- Cost-sensitive coding pipelines that call an LLM many times per task

## How to access

- [xAI](https://docs.x.ai/docs/models) — model id `grok-code-fast-1`
- [OpenRouter](https://openrouter.ai/x-ai/grok-code-fast-1) — model id `x-ai/grok-code-fast-1`
- [Oracle Cloud (OCI Generative AI)](https://docs.oracle.com/en-us/iaas/Content/generative-ai/xai-grok-code-fast-1.htm) — model id `xai.grok-code-fast-1`

## Grok Code versions

- [Grok Build 0.1](https://ai-tldr.dev/models/grok-build-0-1/) (April 2026)
- Grok Code Fast 1 (28 August 2025) — this page

## FAQ

### What is Grok Code Fast 1?

It is xAI's first model built specifically for agentic coding, released August 28, 2025 (codename "sonic"). It is a fast, low-cost, text-only reasoning model designed to run inside coding agents rather than as a general chat model.

### How much does Grok Code Fast 1 cost?

On the xAI API it is priced at $0.20 per million input tokens and $1.50 per million output tokens, with cached input at $0.02 per million. At launch it was free for a limited time through partners like GitHub Copilot, Cursor, and Cline.

### How does Grok Code Fast 1 score on SWE-bench Verified?

xAI reports 70.8% on the full SWE-bench Verified subset using its own internal harness. Independent harnesses can produce different numbers, so the score reflects xAI's setup.

### Is Grok Code Fast 1 still available?

It was deprecated on May 15, 2026 and is scheduled to retire on August 15, 2026. xAI directs users to migrate to newer Grok coding models.

## Links

- [Grok Code Fast 1 — official announcement](https://x.ai/news/grok-code-fast-1)
- [xAI Releases Grok Code Fast 1 (InfoQ)](https://www.infoq.com/news/2025/09/xai-grok-fast1/)
- [Grok Code Fast 1 on OpenRouter](https://openrouter.ai/x-ai/grok-code-fast-1)
- [xAI Grok Code Fast 1 (Oracle OCI docs)](https://docs.oracle.com/en-us/iaas/Content/generative-ai/xai-grok-code-fast-1.htm)
- [SWE-bench Verified score discussion (Hacker News)](https://news.ycombinator.com/item?id=45064606)

Source: AI/TLDR LLM registry, https://ai-tldr.dev/models/grok-code-fast-1/