Anthropic: Claude Opus 4.8 (Fast)

Image input File input Text input Text output
Author's Description

Fast-mode variant of [Opus 4.8](/anthropic/claude-opus-4.8) - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: https://platform.claude.com/docs/en/build-with-claude/fast-mode

Key Specifications
Cost
+$$$$$
Context
1M
Released
May 27, 2026
Speed
Ability
Reliability
Supported Parameters

This model supports the following parameters:

Tool Choice Response Format Include Reasoning Tools Max Tokens Stop Reasoning Structured Outputs
Features

This model supports the following features:

Structured Outputs Reasoning Tools Response Format
Performance Summary

Anthropic's Claude Opus 4.8 (Fast) demonstrates strong performance, particularly in speed and reliability. It consistently performs among the fastest models, ranking in the 76th percentile across benchmarks. The model exhibits exceptional reliability with a 99% success rate, indicating minimal technical failures. However, this speed comes at a premium, as its pricing is positioned at the 4th percentile, making it one of the more expensive options. In terms of capabilities, Claude Opus 4.8 (Fast) excels in complex tasks such as Coding (96% accuracy, 94th percentile), Reasoning (94% accuracy, 75th percentile), and Mathematics (94% accuracy, 73rd percentile). It achieved perfect accuracy in Ethics, also being noted as the most accurate and fastest model at its price point for this category. While its General Knowledge (99.5% accuracy) is high, its percentile ranking is moderate. A notable area for improvement is its handling of Hallucinations, where its 94% accuracy places it in the 43rd percentile, suggesting it occasionally struggles to acknowledge uncertainty. Instruction Following (71% accuracy) also presents a moderate performance.

Model Pricing

Current Pricing

Feature Price (per 1M tokens)
Prompt $10
Completion $50
Input Cache Read $1
Input Cache Write $12.5
Web Search $10000

Price History

Available Endpoints
Provider Endpoint Name Context Length Pricing (Input) Pricing (Output)
Anthropic
Anthropic | anthropic/claude-4.8-opus-fast-20260528 1M $10 / 1M tokens $50 / 1M tokens
Benchmark Results
Benchmark Category Reasoning Strategy Free Executions Accuracy Cost Duration
Other Models by anthropic