Claude Haiku 4.5 (Batch)
Anthropic
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.
- Language
- Explicit caching
- File input
- Reasoning
- Tool use
- Vision
- Structured output
- Context
- 200K
- Max output
- 64K
- Input / 1M
- $0.500
- Output / 1M
- $2.50
Quickstart
Point any OpenAI-compatible client at Maxynetic Systems and pass anthropic/claude-haiku-4.5-batch as the model.
curl https://api.maxynetic.com/v1/chat/completions \
-H "Authorization: Bearer $MAXYNETIC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "anthropic/claude-haiku-4.5-batch",
"messages": [{ "role": "user", "content": "Explain routing in one line." }]
}'Pricing
Billed per token with no markup on the underlying provider rate.
Input
Per 1M prompt tokens
$0.500
Output
Per 1M completion tokens
$2.50
Cache read
Per 1M cached prompt tokens
$0.050
Cache write
Per 1M tokens written to cache
$0.625
A 1M-token prompt with 250K tokens of output costs about $1.13.