Claude Haiku 5.5 (Batch)

anthropic/claude-haiku-5.5-batch

A chat model with a 1M-token context window, at $0.0525 per million input tokens and $0.2625 per million output tokens.

Details

Maker: anthropic
Kind: Chat
Context window: 1,000,000 tokens
Max output: 128,000 tokens
Input: $0.0525 per million tokens
Cached input: $0.00525 per million tokens, 90% off
Cache write: $0.065625 per million tokens
Output: $0.2625 per million tokens
Capabilities: Reasoning, tool use, vision, file input
Takes: Text, image, pdf
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2026-10-07

Description

Claude Haiku 5.5 brings adaptive reasoning to Anthropic’s low-cost Haiku family for everyday tasks, tool use, and scaled sub-agent deployments. It is the first Haiku with adjustable effort levels, letting developers balance reasoning depth and token usage for each task, with the option to turn thinking off for simpler requests.

Call it

curl

curl https://phantom.codes/v1/chat/completions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-haiku-5.5-batch",
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model