Claude Haiku 5.5

Available

anthropic/claude-haiku-5.5

Lowest-cost Claude model for high-volume, simple tasks.

Chat
1M context
128K max output
Vision
Tools

Try in Playground Compare

Pricing

Input: $0.10 / 1M tokens
Output: $0.50 / 1M tokens
Cached input: $0.01 / 1M tokens
Input, prompts over 100K: $0.50 / 1M tokens
Output, prompts over 100K: $2.50 / 1M tokens

Once a prompt reaches 100,001 tokens, the whole request is billed at the long-prompt rate.

What it costs

A typical request: 2,000 tokens in, 500 out$0.0005

1,000 of those requests$0.45

Performance on SparrowCodes

Measured from real requests over the last 7 days.

No traffic yet. Speed, latency and success rate appear here once this model has served requests on SparrowCodes; we don't show estimates.

Official benchmarks

Scores published by the model's maker, under their test conditions.

GDPval-AA v2.11620 Elo
AA-Briefcase v1.11578 Elo
OSWorld 2.1 (offline subset) · partial72.4%
Humanity's Last Exam · no tools45.9%
Humanity's Last Exam · with tools57.4%
Terminal-Bench 4.039.2%
FrontierCode 1.1 (Main)46.4%
Chartography · no tools46.4%

Source: Anthropic: Claude Haiku 5.5 announcement (2026-10-07)

Specifications

Type: Chat
Served by: Anthropic
Context window: 1,000,000 tokens
Maximum output: 128,000 tokens
Input types: Text, Image
Tool calling: Supported

Use it

curl https://api.sparrowcodes.com/v1/chat/completions \
  -H "Authorization: Bearer $SPARROW_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-5.5",
    "messages": [{"role": "user", "content": "Explain rate limiting in one paragraph."}]
  }'

Set "model" to anthropic/claude-haiku-5.5. The response includes its exact cost.

More from Anthropic

All models