xAI: Grok Code Fast 1
This model is no longer available.Add AI to your application with Puter.js.
Explore Other Models
Model Card
Grok Code Fast 1 is a speedy, economical reasoning model built from scratch specifically for agentic coding workflows, released August 2025. It excels at TypeScript, Python, Java, Rust, C++, and Go with a 256K context window and ~92 tokens/second throughput.
Context Window 256K
tokens
Max Output 256K
tokens
Input Cost $0.2
per million tokens
Output Cost $1.5
per million tokens
Input text
modalities
Tool Use Yes
Knowledge Cutoff Oct 2023
Release Date Aug 28, 2025
Code Example
Add AI to your app with the Puter.js AI API, no API keys or setup required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
More AI Models From xAI
Grok 4.7
Grok 4.7 is xAI's flagship chat model, released September 21, 2026 as the successor to Grok 4.6. It is built on a larger base model with extended reinforcement learning focused on difficult, multi-hour tasks and on stronger self-verification of its own output. On the Artificial Analysis Intelligence Index it scores 46, trailing Claude Fable 5.1 and GPT-5.6 Sol at 53 each, but it improves over Grok 4.6 on professional-work benchmarks: AA Briefcase rises from 1,546 to 1,657, the Harvey Legal Agent Benchmark from 15.8% to 19.6%, and HealthBench Professional from 48.5% to 56.7%. For coding it scores 46.3% on CursorBench 4.0, ahead of GPT-5.6 Sol Max (41.7%) but behind Claude Fable 5.1 (51.8%). With a 500K token context window, it suits coding and knowledge-work agents that want frontier price-performance rather than the top agentic score.
ChatGrok 4.6
Grok 4.6 is xAI's frontier model for long-running agents and interactive, visual development work, built on the same 1.5-trillion-parameter V9 foundation as Grok 4.5 with additional supervised fine-tuning and reinforcement learning. It matches GPT-5.6 Sol on the Artificial Analysis Intelligence Index (both score 61) and leads on CursorBench v3.2 at 69.9%, with gains over Grok 4.5 across coding, research, and agentic benchmarks. xAI highlights it for vulnerability patching, engineering design work, and turning a rough product idea into a working first version, with improved self-testing on longer tasks. The model accepts text and image input with text-only output, a 500,000 token context window, and no output token limit. Reasoning effort is configurable across four levels (low, medium, high, xhigh), and it supports function calling, web search, X search, and code execution. At $2 per million input tokens and $6 per million output tokens, it costs the same as Grok 4.5.
ImageGrok Imagine Image 2.0
Grok Imagine Image 2.0 is xAI's second-generation text-to-image and image-editing model, released August 7, 2026 as the Quality Mode successor to Grok Imagine Image and Grok Imagine Image (Quality). It is built to produce images usable in real work rather than drafts: it follows instructions closely, plans typography and layout, and preserves elements across generations and edits. New editing tools include a magic wand for targeted region edits, segmentation for selecting precise areas, background removal with transparency, and multi-reference editing that accepts up to five input images in one generation. Smart resize recomposes an image across nine aspect ratios automatically. xAI reports it ranks second in the world on both the Arena text-to-image and image-edit leaderboards, behind OpenAI's gpt-image-2. It ships with ready-made templates for recurring workflows such as product shots, headshots, icons, and game assets, making it suited to product photography, e-commerce content, and character or marketing design work.
Frequently Asked Questions
Grok Code Fast 1 is no longer available through Puter.js. Explore other AI models for alternatives.
| Price per 1M tokens | |
|---|---|
| Input | $0.2 |
| Output | $1.5 |
Grok Code Fast 1 was created by xAI and released on Aug 28, 2025.
Grok Code Fast 1 supports a context window of 256K tokens. For reference, that is roughly equivalent to 512 pages of text.
Grok Code Fast 1 can generate up to 256K tokens in a single response.
Grok Code Fast 1 has a knowledge cutoff date of Oct 2023. This means the model was trained on data available up to that date.
Grok Code Fast 1 accepts the following input types: text. It produces: text.
Yes, Grok Code Fast 1 supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.
Grok Code Fast 1 scores 14.1 on the Artificial Analysis Intelligence Index, outperforming 54% of tracked models. On math, it scores 43.3 (outperforms 43% of models).
Yes — the Grok Code Fast 1 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials