gpt-6-luna
GPT-6 Luna (OpenAI), the fastest of the line: 922K input tokens, 128K output, vision and reasoning (`reasoning_effort` none to max, default medium).
Tools, `temperature`, `top_p` and `logprobs` work only with `reasoning_effort: "none"`. A prompt over 272,000 input tokens bills the whole request at the long-context rates; `service_tier` `priority` and `flex` bill at their own rates.
| Slug | gpt-6-luna |
| Kind | chat |
| Vendor | openai |
| Endpoint | POST /v1/chat/completions |
Charged per job from what the generator reports it rendered — your Logs show the exact figure for each one; see balance and billing.
Calling it
curl https://api.sociaro.com/v1/chat/completions \
-H "Authorization: Bearer $SOCIARO_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-luna",
"messages": [{"role": "user", "content": "hello"}]
}'Parameters
messagesmax_completion_tokensstreamstream_optionsreasoning_effortresponse_formattoolstool_choiceparallel_tool_callstemperaturetop_plogprobstop_logprobsservice_tierstoresafety_identifierprompt_cache_keyuser