Model Terminal

Claude Opus 4.8 (Fast)

Claude Opus 4.8 (Fast) is Anthropic's high-speed inference tier for the Claude Opus 4.8 flagship model, optimized for lower latency and higher throughput at approximately 2.5× the default speed. Priced at $10 per million input tokens and $50 per million output tokens, it targets production agentic workflows and coding tasks where responsiveness is critical. Source: supabase.

Value score
Not scored
Context
200K
tokens
Max output
32K
tokens
Price
$15/1M in · $75/1M out

Capability radar

Identity

Developer
Anthropic
Openness
Closed
Modalities
Release
2025-05-22
Knowledge cutoff
Deprecation

Benchmarks

  • GPQA79.6 · 2025-05-22 · source
  • MMLU88.8 · 2025-05-22 · source
  • SWE-bench72.5 · 2025-05-22 · source

Compare nearby

Pricing

Input / 1M
$15
Output / 1M
$75
Speed