xAI: Grok Code Fast 1

xAI: Grok Code Fast 1

x-ai · Released Aug 26, 2025 Specialist
Intelligence #115 / 583
54.0 Our Score
Speed #206 / 276
55.4 tokens / sec
Input #274 / 583
$0.200 per 1M tokens
Output #360 / 583
$1.50 per 1M tokens
Context #174 / 583
256,000 tokens

Analysis Summary

Grok Code Fast 1 is xAI's coding-focused fast model, with an intelligence index of 21.6 and a coding index of 23.7. Its standout metric is its agentic index of 46.6, which is strong for its tier and makes it a capable option for multi-step tool-augmented workflows. The tau2 score of 0.757 confirms reliable task completion in agentic settings. Tool use and function calling are supported, and the 256K context window is a meaningful advantage for large codebase or document tasks.

For business use, Grok Code Fast 1 is well suited to agentic coding pipelines, automated tool-use workflows, and tasks requiring reliable multi-step execution at moderate cost. Its livecodebench score of 0.657 is reasonable, and its instruction following at 0.414 is adequate for structured tasks. General reasoning depth is limited, so complex analytical workloads are better handled by larger models.

At $0.20 input and $1.50 output, pricing is competitive for its agentic capability. Teams in the xAI ecosystem looking for a fast, cost-effective model for coding agents and tool-augmented automation will find it a practical choice.

Assessed June 17, 2026

Editorial notes

Grok Code Fast 1 from xAI delivers a strong agentic index and solid coding performance with a 256K context window, at a competitive price for an major providers.

Rankings consider pricing, capabilities, benchmarks, and real-world applicability and are refreshed as new models launch. Feedback?

Performance Profile

Intelligence3.8Technical4.8Value7.5Content6
Intelligence 3.8/10
Technical 4.8/10
Content 6/10
Value 7.5/10

How xAI: Grok Code Fast 1 compares

XAI: Grok Code Fast 1 ranks #125 of 380 AI models we track for overall intelligence, #105 of 292 for agentic tasks. Its 256K-token context window is larger than 70% of the models we list. At $0.20 per million input tokens it is cheaper than 53% of comparable models.

About xAI: Grok Code Fast 1

Grok Code Fast 1 is a speedy and economical reasoning model that excels at agentic coding. With reasoning traces visible in the response, developers can steer Grok Code for high-quality..

Capabilities

Tool Use Function Calling

Performance Indices

Source: Artificial Analysis

21.6 Intelligence Index
46.6 Agentic Index
43.3 Math Index

Benchmark Scores

Intelligence

GPQA Diamond 72.7% Graduate-level scientific reasoning
HLE 7.5% Humanity's Last Exam
MMLU Pro 79.3% Multi-task language understanding
AIME 2025 43.3% Competition mathematics (2025)
SciCode 36.2% Scientific computing

Technical

LiveCodeBench 65.7% Live coding evaluation
TerminalBench Hard 17.4% Agentic terminal tasks
τ²-Bench 75.7% Conversational agent benchmark

Content

IFBench 41.4% Instruction following
LCR 48.3% Long-context reasoning

Benchmark data from Artificial Analysis and Hugging Face

How does xAI: Grok Code Fast 1 stack up?

Compare side-by-side with other specialist models.

Compare Models

Model Information

OpenRouter ID x-ai/grok-code-fast-1
Providerx-ai
Release Date August 26, 2025
Context Length256,000 tokens
Max Completion10,000 tokens
Status Active

Pricing

Token Type Cost per 1M tokens Cost per 1K tokens
Input $0.20 $0.000200
Output $1.50 $0.001500

Leaderboard Categories

Frequently asked questions about xAI: Grok Code Fast 1

How much does xAI: Grok Code Fast 1 cost?

xAI: Grok Code Fast 1 costs $0.20 per million input tokens and $1.50 per million output tokens.

What is the context window of xAI: Grok Code Fast 1?

xAI: Grok Code Fast 1 has a context window of 256,000 tokens (256K).

What can xAI: Grok Code Fast 1 do?

xAI: Grok Code Fast 1 supports tool use and function calling.

Who created xAI: Grok Code Fast 1?

xAI: Grok Code Fast 1 is developed by xAI and was released on August 26, 2025.