Haiku 5.5
The current Haiku: cheap and fast for bulk work. A prompt over 100K tokens bills at five times the rate.
Pricing, per million tokens
- Input
- $0.06
- Output
- $0.30
- Cache write
- $0.075
- Cache read
- $0.006
Four counters, each at its own rate: input, output, cache write and cache read. The same numbers are returned by the catalogue route of the API.
How to call it
Send anthropic/claude-haiku-5-5 in the model field of a request to https://api.gtokens.io/api/v1/chat/completions from an OpenAI-compatible client, or to https://api.gtokens.io/v1/messages from a Messages API client. The same model answers on both, with tool calls and streaming.