aiaimodel.cards

Claude Haiku 5.5

Language modelCard summarized

For high-volume, latency-sensitive tasks such as classification, extraction, and routing

Active (latest) · retires not before 7 Oct 2027● Re-checked 12 Oct 2026 · 89 facts · 2 corrections · 1 unconfirmedSource: System Card: Claude Haiku 5.5 (144 pp)

Use it via API

$58.80 /month
$1.18 per 1K requests
RAG over docs: 12K in · 600 out · 50K requests/mo · 30% cached · change
Code exampleCompare

Where to call it

  • Claude APIclaude-haiku-5-5
  • Amazon Bedrockanthropic.claude-haiku-5-5
  • Google Vertex AIclaude-haiku-5-5
  • Microsoft Foundry / Azureclaude-haiku-5-5

Supports

  • Image input
  • PDF input
  • Structured outputs
  • Reasoning control
  • Tool calling
  • Web search
  • Prompt caching
  • Batch API
Full feature support

Good for

  • High-volume, latency-sensitive work: classification, routing, extraction, sub-agents
  • Coding: large gains over Haiku 4.5 (SWE-bench Multilingual 83.7% vs 67.4%)
  • Computer use: OSWorld 2.1 offline subset 72.4% vs 15.7% for Haiku 4.5

Watch out for

Overview

Anthropic · 01Haiku, front

Haiku 5.5

For high-volume, latency-sensitive tasks such as classification, extraction, and routing

Cost
$0.10 in
Context
1M
Input / output
$0.10 / $0.50
Max output
128K
Knows up to
June 2026
Released
7 Oct 2026

Anthropic's latest Haiku-class large language model. It significantly outperforms Claude Haiku 4.5 across many domains and in a few areas rivals or exceeds Claude Sonnet 5.5, but is broadly less capable than Claude Opus 5 and crosses no new RSP thresholds. p.2–3

claude-haiku-5-5
Input / output per 1M
$0.10 / $0.50
Context window
1M
Max output
128K
Knows up to
June 2026
Reasoning
Adaptive
Weights
Closed

About this card. A model card is the maker's own account of a model: what it's for, how it was trained and tested, and where it falls short. This page condenses Anthropic's System Card: Claude Haiku 5.5. Every claim carries its source page.