Claude Haiku 5.5
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-5-5License
Proprietary (API only)
Pricing
Standard
Input$0.10 / 1M
Output$0.50 / 1M
Batch (50% off)
Input$0.05 / 1M
Output$0.25 / 1M
A typical 1,500-token prompt with a 650-token answer costs ≈ $0.0005 on the standard tier. Run your own prompt through the calculator →
What's new vs the previous model
Compared withClaude 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 & limitations
Strengths
- Very low cost
- Low latency
- High throughput
- Solid for simple tasks
Limitations
- Limited deep reasoning
- Smaller context window
How to test it
- No-code: open claude.ai and pick Claude Haiku 5.5 from the model switcher — no API key needed.
- Playground: sign in to the Anthropic Console and run prompts in the workbench, then copy the generated code.
- API: create a key in the Anthropic Console and call the API (example below).
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "claude-haiku-5-5",
"max_tokens": 1024,
"messages": [{"role": "user", "content": "Explain tokenization in one paragraph."}]
}'Where to get access
Consumer app
Chat with Claude Haiku 5.5 in Claude apps (web, macOS, Windows, iOS, Android).
claude.ai ↗