All Models
xAI logo

Grok Code Fast 1

xAI

Grok Code Fast 1 is a fast and cost-effective reasoning model excelling in agentic coding. Built from scratch on an entirely new architecture with a pretraining corpus rich in programming content and post-training datasets on real pull requests and coding tasks. The model has mastered grep, terminal, and file editing tools, making it ideal for IDE integration. Particularly strong in TypeScript, Python, Java, Rust, C++, and Go.

Key Specifications

Parameters
-
Context
256.0K
Release Date
August 27, 2025
Average Score
71.0%
API DocumentationResearch PaperResults Blog

Timeline

Key dates in the model's history
Announcement
August 27, 2025
Last Update
January 22, 2026
Today
September 10, 2026

Technical Specifications

Parameters
-
Training Tokens
-
Knowledge Cutoff
-
Family
-
Capabilities
MultimodalZeroEval

Pricing & Availability

Input (per 1M tokens)
$0.20
Output (per 1M tokens)
$1.50
Max Input Tokens
256.0K
Max Output Tokens
10.0K
Supported Features
Function CallingStructured OutputCode ExecutionWeb SearchBatch InferenceFine-tuning

Benchmark Results

Model performance metrics across various tests and benchmarks

Programming

Programming skills tests
SWE-Bench Verified
internal • Self-reported
71.0%

License & Metadata

License
proprietary
Announcement Date
August 27, 2025
Last Updated
January 22, 2026

Similar Models

All Models
xAI logo

Grok-1.5

xAI

Best score:0.8 (MMLU)
Released:Mar 2024
xAI logo

Grok 4.3

xAI

Released:May 2026
Price:$1.25/1M tokens
xAI logo

Grok-1.5V

xAI

MM
Released:Apr 2024
xAI logo

Grok-4 Fast Non-Reasoning

xAI

MM
Released:Aug 2025
Price:$0.20/1M tokens
xAI logo

Grok-4 Fast Reasoning

xAI

MM
Released:Aug 2025
Price:$0.20/1M tokens
MiniMax logo

MiniMax M2.1

MiniMax

Best score:0.9 (TAU)
Released:Dec 2025
Price:$0.30/1M tokens
Mistral AI logo

Devstral Medium

Mistral AI

Released:Jul 2025
Price:$0.40/1M tokens
Anthropic logo

Claude 3.5 Haiku

Anthropic

Best score:0.9 (HumanEval)
Released:Oct 2024
Price:$0.80/1M tokens

Recommendations are based on similarity of characteristics: developer organization, multimodality, parameter size, and benchmark performance. Choose a model to compare or go to the full catalog to browse all available AI models.