OpenAI
GPT-6 Luna
The light GPT-6 model, at the lowest text rate in the catalogue, for bulk work.
Pricing, per million tokens
- Input
- $0.06
- Output
- $0.30
- Cache read
- $0.006
Three counters, each at its own rate: input, output and cache read. The same numbers are returned by the catalogue route of the API.
How to call it
Send openai/gpt-6-luna in the model field of a request to https://api.gtokens.io/api/v1/chat/completions from an OpenAI-compatible client. This model answers in that shape only and with text only: a request that declares tools or attaches an image is refused with 400, a streamed request receives the finished reply in one piece, and max_tokens does not cut the reply short. The reasoning effort is set with reasoning.effort.