---
title: "Claude Haiku 5.5 — LLM-TEST.com"
url: /models/claude-haiku-5-5/
canonical_url: https://llm-test.com/models/claude-haiku-5-5/
language: en
type: model
summary: "The fast, low-cost member of the Claude 5 family, built for latency-sensitive and high-throughput tasks. Punches above its price for classification, extraction and lightweight chat."
last_updated: "2026-11-05"
---

# Claude Haiku 5.5

_Anthropic · Fast_

The fast, low-cost member of the Claude 5 family, built for latency-sensitive and high-throughput tasks. Punches above its price for classification, extraction and lightweight chat.

## At a glance

- Released: Sep 15, 2026
- Provider: Anthropic
- Context window: 500,000 tokens
- Max output: 32,000 tokens
- Modalities: Text + image → text
- Knowledge cutoff: April 2026
- API model ID: `claude-haiku-5-5`
- License: Proprietary (API only)

## Pricing

- Standard: $0.10 input / $0.50 output per 1M tokens
- Batch: $0.05 input / $0.25 output per 1M tokens
- Example: a 1,500-token prompt + 650-token answer ≈ $0.0005 (standard)

## What's new vs Claude Haiku 5 (April 2026)

- Lower latency and higher throughput
- Better instruction following for its size
- Improved short-context reasoning
- Smaller context and output than larger Claude tiers

## Best use cases

- **High-volume classification** — Tags and routes large streams of text cheaply.
- **Data extraction** — Pulls structured fields from documents at low cost.
- **Lightweight chat** — Powers quick, simple assistant interactions at scale.

## Strengths

- Very low cost
- Low latency
- High throughput
- Solid for simple tasks

## Limitations

- Limited deep reasoning
- Smaller context window

## Where to get access

- Consumer app: Claude apps (web, macOS, Windows, iOS, Android) — https://claude.ai
- API: the Anthropic Console — https://console.anthropic.com
- Also available: Amazon Bedrock and Google Vertex AI
- Docs: https://docs.anthropic.com

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/