All models

Opus 5.5

The current Opus: long reasoning and agent work, at a lower rate than Opus 5.

Pricing, per million tokens

Input
$2.40
Output
$12.00
Cache write
$3.00
Cache read
$0.12

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-opus-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.

Quickstart with code samples

All models and pricing