xAI: Grok 4 Fast

Image input Text input Text output
Author's Description

Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)

Key Specifications
Cost
$$$$
Context
2M
Released
Sep 18, 2025
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Reasoning Tools Top P Response Format Tool Choice Temperature Seed Include Reasoning Structured Outputs Logprobs Max Tokens Top Logprobs
Features

This model supports the following features:

Response Format Reasoning Structured Outputs Tools
Performance Summary

Grok 4 Fast, xAI's latest multimodal model, demonstrates a balanced performance profile with notable strengths in reliability and specific accuracy benchmarks. With a 2M token context window and available in both non-reasoning and reasoning flavors, it was created on September 18, 2025. The model exhibits moderate speed performance, ranking in the 21st percentile across two benchmarks, and offers moderate pricing, placing it in the 39th percentile. A standout feature is its exceptional reliability, achieving a 100% success rate across all benchmarks, indicating consistent and usable responses. In terms of specific performance, Grok 4 Fast achieved 94.0% accuracy in the Coding (Baseline) benchmark, placing it in the 93rd percentile, though with a relatively high duration. Its performance in the Ethics (Baseline) benchmark was particularly impressive, achieving perfect 100.0% accuracy. This makes it the most accurate model at its price point and among models of comparable speed for ethical reasoning. While its speed is moderate, its high accuracy in critical areas like ethics and strong coding performance, coupled with its perfect reliability, position Grok 4 Fast as a robust and dependable option, especially for applications requiring high accuracy and consistent output.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $0.2
Completion $0.5
Input Cache Read $0.05

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
xAI
xAI | x-ai/grok-4-fast 2M $0.2 / 1M tokens $0.5 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by x-ai