modelgrep
A

Anthropic: Claude Opus 4.8 (Fast)

anthropic/claude-opus-4.8-fast

ReasoningToolsJSONVision
Use via OpenRouter ↗
Intelligence
Design Elo
Speed
121
46th fastest
Latency
1.6s
first token
Input price
$10.00
282nd cheapest
Context
1M
128K max out

How it compares

Faster than84%
of all ranked models
Cheaper than5%
of all ranked models

Overview

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

Providers & pricing (1)

ProviderIn $/MOut $/MUptime
Anthropic$10.00$50.0099.9%

Specifications

Context window1M
Max output128K
Knowledge cutoff
Input modalitiestext, image, file
Output modalitiestext
Prompt caching
Cache read price$1.00/M
ModeratedYes

Claude Opus 4.8 (Fast) FAQ

How much does Claude Opus 4.8 (Fast) cost?

Claude Opus 4.8 (Fast) costs $10.00 per million input tokens and $50.00 per million output tokens via OpenRouter, making it 282nd cheapest of 298 paid models.

How fast is Claude Opus 4.8 (Fast)?

Claude Opus 4.8 (Fast) generates around 121 tokens per second with 1.6s time-to-first-token (p50), the 46th fastest tracked model.

What is Claude Opus 4.8 (Fast)'s context window?

Claude Opus 4.8 (Fast) supports a 1M-token context window and can output up to 128K tokens. It accepts text, image, file input.

Compare head-to-head