Claude Haiku 5.5
By Steven Van ·
Requests with up to 100,000 input tokens cost $0.10 per million input tokens, with higher rates above that threshold.
Developers can now select anthropic/claude-haiku-5-5 in Perplexity’s Agent API, with token rates that increase for requests containing more than 100,000 input tokens.
Making a request
Set the model parameter to anthropic/claude-haiku-5-5 and include max_output_tokens. This parameter is required for Anthropic models; omitting it returns an HTTP 400 error. Haiku 5.5 uses default processing only.
Token pricing
For requests with up to 100,000 input tokens, rates per million tokens are $0.10 for input, $0.50 for output and $0.01 for cache reads. Above that threshold, the rates rise to $0.50 for input, $2.50 for output and $0.05 for cache reads.
The Agent API Models reference lists these rates. Charges reflect actual token consumption, and each API response includes exact token counts.