Ordalin
Submit a tool

Reviewed tool profile

Claude Haiku 5.5

Anthropic’s fastest, lowest-cost Claude model for high-volume tasks and coding subagents.

Sources checked

Visit website ↗
Pricing
API usage is billed per million tokens, with two price tiers by prompt length. For prompts up to 100,000 tokens: $0.10 input, $0.50 output, $0.01 cache reads and $0.125 cache writes. For prompts over 100,000 tokens: $0.50 input, $2.50 output, $0.05 cache reads and $0.625 cache writes. Official source 1 ↗
Available as
Available on the Claude Platform API with the model ID claude-haiku-5-5, and on Amazon Web Services, Google Cloud and Microsoft Azure. · The Claude Python and TypeScript SDKs add computer-use and browser-use support in beta, which Anthropic says suits Haiku 5.5. Official source 1 ↗ Official source 1 ↗
Primary group
Coding & Development

What it does

Claude Haiku 5.5 is Anthropic’s smallest and fastest current Claude model, released on October 7, 2026. It is built for high-volume, cost-sensitive work such as summaries, compaction, database queries, classification and coding subagents, and is the first Haiku model with an adjustable effort setting. Anthropic says it costs around 75% less to run than Haiku 4.5 on average.

Official source 1 ↗

Features

  • Low-cost high-volume tasks. Designed for quick, repetitive workloads such as summaries, compaction, database queries and classification. Official source 1 ↗
  • Coding subagent. Pairs with Opus 5.5 and Sonnet 5.5 as a subagent on coding work. Anthropic reports 39.2% on Terminal-Bench 4.0. Official source 1 ↗
  • Adjustable effort. The first Haiku-class model with an effort setting, so users can trade cost against intelligence. Official source 1 ↗
  • Speed for live and browser tasks. Anthropic’s fastest model at standard speed, aimed at live customer support and browser use. Official source 1 ↗
  • Computer and browser use. Scores 72.4% on the OSWorld 2.1 offline subset; the Claude SDKs add computer and browser use in beta. Official source 1 ↗

Pricing & free limits

API — prompts up to 100K tokens

$0.10 input / $0.50 outputUSD per million tokens

Cache reads $0.01 and cache writes $0.125 per million tokens. Anthropic says about 90% of previous Haiku requests fall in this tier. Official source 1 ↗

API — prompts over 100K tokens

$0.50 input / $2.50 outputUSD per million tokens

Cache reads $0.05 and cache writes $0.625 per million tokens. Official source 1 ↗

Billing details

Anthropic says Haiku 5.5 is priced 90% below Haiku 4.5 for requests up to 100,000 tokens and 50% below for longer requests, but its updated tokenizer uses slightly more tokens per task. Official source 1 ↗

Claude Max and Team subscribers receive a monthly Claude Platform API credit: $100 for Max 5x, $200 for Max 20x and up to $500 pooled for Team. It can be used on any Claude model. Official source 1 ↗

Free access & limits

Free access and its limits were not established by the checked official sources.

Best for & limitations

Run cheap subagents for lookups and summaries alongside a larger lead model. Official source 1 ↗

Classify, summarise or compact large volumes of text at low cost. Official source 1 ↗

Power live customer-support and browser-use agents where latency matters. Official source 1 ↗

Answer questions over one or a few documents at production scale. Official source 1 ↗

Automate CRM reporting and record audits. Official source 1 ↗

  • Not for complex agentic coding. Anthropic says Sonnet 5.5 and Opus 5.5 remain better for complex agentic coding; Haiku 5.5 suits narrowly scoped tasks. Official source 1 ↗
  • Higher prices for long prompts. Prompts over 100,000 tokens cost five times more per token than shorter prompts. Official source 1 ↗
  • Cybersecurity restrictions. Safeguards allow defensive security work but block penetration testing and other attacker-style techniques. Official source 1 ↗
Claude Haiku 5.5 product screenshot
Website previewFixed desktop viewport · 1440 × 900

Similar tools

Published tools that share its categories.