gpt-6.2-astra
OpenAI's GPT-6.2 Astra — its most capable model, for hard and long projects: building and revising software, operating a computer, and working with documents, slides and spreadsheets.
Takes text and images, answers in text, with a context window of about 1.05M tokens and up to 128K tokens of output.
| Slug | gpt-6.2-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-6.2-astra",
"messages": [{"role": "user", "content": "hello"}]
}'Parameters
frequency_penaltylogit_biaslogprobstop_logprobsmax_tokensmax_completion_tokensmodalitiespredictionnpresence_penaltyseedstopstreamstream_optionstemperaturetop_ptoolstool_choicefunction_callfunctionsmax_retriesextra_headersparallel_tool_callsaudioweb_search_optionsservice_tiersafety_identifierprompt_cache_keyprompt_cache_retentionstoreresponse_formatuser