Grok Code Fast 1 API

A speedy and economical reasoning model that excels at agentic coding with function calling and structured outputs.

Modalities: TextText
In / Out price: $1/$2per 1M
Context window: 250K tokens
Released: Sep 30, 2025

Grok Code Fast 1 overview

Grok Code Fast 1 by xAI

Its massive 256,000-token context window allows for handling large codebases and multi-file projects without truncation.

Grok Code Fast 1 specs

Model ID: x-ai/grok-code-fast-1
Developer: xAI
Context window: 256,000 tokens
Max output: 255,000 tokens
Input: Text
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

Grok Code Fast 1 Description

Grok Code Fast 1 is xAI's specialized, fast, and economical coding assistant optimized for agentic coding workflows. It excels at handling high-volume, practical software development tasks including code generation, debugging, editing, and multi-step agentic operations. Built with speed, efficiency, and cost-effectiveness in mind, Grok Code Fast 1 is particularly proficient in TypeScript, Python, Java, Rust, C++, and Go, offering deep integration into developer pipelines with structured, traceable reasoning outputs.

Performance Benchmarks

Context Window: 256,000 tokens (max prompt + response)
Max Output: Up to 16,000 tokens (playground capped)
Architecture: 314B-parameter Mixture-of-Experts (MoE) for speed and capability
Throughput: ~92 tokens per second

Performance Metrics

Accurate across coding tasks with 93.0% coding accuracy and 75.0% instruction following accuracy
Strong classification and knowledge performances: perfect in morality, email classification, general knowledge
Reasoning Accuracy: 80.0%, with visible step-by-step reasoning traces for developer inspection and steering
Competitive speed and throughput supporting real-time coding workflows

Key Capabilities

Massive long-context handling for entire codebases or multi-file projects
Agentic coding with native function/tool calls and multi-step operation chaining
Traceable reasoning outputs revealing intermediate steps to boost transparency and steerability
Multi-language support for practical software stacks including major modern programming languages
Economical pricing designed for high-volume developer use and iterative workflows

Optimal Use Cases

Agentic coding assistants for autonomous code writing, debugging, and system integration
Large-scale codebase analysis and multi-file editing without coherence loss
Coding research and evaluation demanding precise reasoning and logic transparency
Integration into CI/CD pipelines with high throughput and cost efficiency

Comparison with Other Models

vs. Grok 4: Grok Code Fast 1 trades some general reasoning and tool-use sophistication for much higher speed and cost efficiency specifically in coding workflows. Grok 4 better supports complex AGI-style reasoning and tool integration beyond coding.

vs. Claude 4 Opus: Claude excels in language safety and nuanced instruction following, while Grok Code Fast 1 delivers faster, structured agentic coding with visible reasoning traces.

vs. GPT-4o: GPT-4o leads in multimodal and browsing features; Grok Code Fast 1 focuses on coding speed, throughput, and agentic tool-enabled workflows.

Use cases

Agentic coding assistants for autonomous code writing, debugging, and system integration
Large-scale codebase analysis and multi-file editing without coherence loss
Coding research and evaluation demanding precise reasoning and logic transparency
Integration into CI/CD pipelines with high throughput and cost efficiency

Capabilities

Function calling
Streaming
Structured outputs
Reasoning

Grok Code Fast 1 benchmarks by Artificial Analysis

See how Grok Code Fast 1 scores on independent evaluations. Data retrieved Nov 3, 2026.

Humanity's Last Exam#242 / 4588%Score GPQA Diamond#199 / 43972.7%Score AA-LCR#203 / 39153%Score IFBench#185 / 32541.4%Score

Benchmark results

Compare 10 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Grok Code Fast 1 API pricing

Grok Code Fast 1 pricing in US dollars
Usage	Price	Unit
Input	$1	1M tokens
Output	$2	1M tokens
Cached input	$0.2	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Grok Code Fast 1 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Grok Code Fast 1	$1	$2
Grok Build 0.1	$1	$2
Grok 4.7	$2	$6
Grok 4.6	$2	$6
Grok 4.5	$2	$6

How to use the Grok Code Fast 1 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "x-ai/grok-code-fast-1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "x-ai/grok-code-fast-1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "x-ai/grok-code-fast-1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Grok Code Fast 1 FAQ

What is the context window of Grok Code Fast 1?

Grok Code Fast 1 has a 256,000 tokens context window and can return up to 255,000 tokens.

What inputs and outputs does Grok Code Fast 1 support?

Grok Code Fast 1 takes text as input and returns text.

What is the model ID for Grok Code Fast 1?

Use x-ai/grok-code-fast-1 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

How much does Grok Code Fast 1 cost?

Grok Code Fast 1 costs $1 input and $2 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Grok Code Fast 1 support streaming?

Yes, Grok Code Fast 1 can stream responses as they are generated.

Who created Grok Code Fast 1?

Grok Code Fast 1 was built by xAI .

Is Grok Code Fast 1 a multimodal model?

No. It only handles text input and produces text output.

Can Grok Code Fast 1 call multiple tools at once?

Yes, it supports parallel tool calls along with function calling and structured outputs.

Start building with Grok Code Fast 1

Get API key

Grok Code Fast 1 API

x-ai/grok-code-fast-1

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "x-ai/grok-code-fast-1",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "x-ai/grok-code-fast-1",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "x-ai/grok-code-fast-1",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Talk to our sales team

Thanks for reaching out

Grok Code Fast 1 API

Grok Code Fast 1 overview

Grok Code Fast 1 by xAI

Grok Code Fast 1 specs

Grok Code Fast 1 Description

Performance Benchmarks

Performance Metrics

Key Capabilities

Optimal Use Cases

Comparison with Other Models

Use cases

Capabilities

Grok Code Fast 1 benchmarks by Artificial Analysis

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Grok Code Fast 1 API pricing

Grok Code Fast 1 vs other models: token prices

How to use the Grok Code Fast 1 API

Build with your agent

1Get your API key

2Make your first request

Related articles

Grok Code Fast 1 FAQ

Start building with Grok Code Fast 1

Grok Code Fast 1 API

Build with your agent

1Get your API key

2Make your first request

Grok Code Fast 1 API

Grok Code Fast 1 overview

Grok Code Fast 1 by xAI

Grok Code Fast 1 specs

Grok Code Fast 1 Description

Performance Benchmarks

Performance Metrics

Key Capabilities

Optimal Use Cases

Comparison with Other Models

Use cases

Capabilities

Benchmark results

Humanity's Last Exam

GPQA Diamond

AA-LCR

IFBench

τ²-Bench Telecom

Grok Code Fast 1 API pricing

Grok Code Fast 1 vs other models: token prices

How to use the Grok Code Fast 1 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Grok Code Fast 1

Grok 4.7

Grok 4.6

Grok 4.5

GLM-5

GPT-6.1 Terra

Claude 4.5 Haiku

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Grok Code Fast 1 FAQ

Start building with Grok Code Fast 1