Claude Haiku 4.5 (Batch)

anthropic/claude-haiku-4.5-batch

A chat model with a 200K-token context window, at $0.525 per million input tokens and $2.625 per million output tokens.

Details

Maker: anthropic
Kind: Chat
Context window: 200,000 tokens
Max output: 64,000 tokens
Input: $0.525 per million tokens
Cached input: $0.0525 per million tokens, 90% off
Cache write: $0.65625 per million tokens
Output: $2.625 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: 2025-10-15
Newer model: anthropic/claude-haiku-5.5Released later by the same maker, costs no more, and lists the same capabilities. Compare the two

Description

Claude Haiku 4.5 matches Sonnet 4's performance on coding, computer use, and agent tasks at substantially lower cost and faster speeds. It delivers near-frontier performance and Claude’s unique character at a price point that works for scaled sub-agent deployments, free tier products, and intelligence-sensitive applications with budget constraints.

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-4.5-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