claude-opus-5-5
Claude Opus 5.5 (Anthropic): 1M-token context, 128K output, vision, tools, and thinking that is always on (set its depth with `reasoning_effort` low|medium|high|max; the default is medium).
Not accepted by the vendor on this model: `temperature`, `top_p`, a forced `tool_choice` (`required` or a named tool; use `auto`), and `response_format` with a JSON schema.
`thinking` takes only `{"type": "adaptive"}`.
| Slug | claude-opus-5-5 |
| Kind | chat |
| Vendor | anthropic |
| 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": "claude-opus-5-5",
"messages": [{"role": "user", "content": "hello"}]
}'Parameters
messagesmax_tokensmax_completion_tokensstreamstream_optionsstoptoolstool_choiceparallel_tool_callsuserthinkingreasoning_effortcache_controlcontext_managementweb_search_options