gpt-6-astra
GPT-6 Astra (OpenAI): 922K input tokens, 128K output, vision and reasoning (`reasoning_effort` low to max; `none` is not accepted).
Function calling and sampling parameters are not available on Chat Completions for this model.
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-astra |
| 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-astra",
"messages": [{"role": "user", "content": "hello"}]
}'Parameters
messagesmax_completion_tokensstreamstream_optionsreasoning_effortresponse_formatservice_tierstoresafety_identifierprompt_cache_keyuser