Skip to main content
Use /v1/responses when your client already speaks the OpenAI Responses API format, or when you need Responses-native features such as reasoning controls, web search tools, and official Responses server-sent events. 
curl https://apiany.ai/v1/responses \
  -H "Authorization: Bearer $APIANY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.5",
    "input": "Write a short implementation plan for adding search to a docs site.",
    "reasoning": { "effort": "medium" },
    "text": { "verbosity": "medium" }
  }'

​
Reasoning controls

gpt-5.5 and gpt-5.4 accept Responses reasoning controls. Use reasoning.effort to set the reasoning strength: 
{
  "model": "gpt-5.5",
  "input": "Review this API design and list the main risks.",
  "reasoning": {
    "effort": "high",
    "summary": "auto"
  }
}
Supported reasoning.effort values are none, minimal, low, medium, high, and xhigh. Pass OpenAI Responses tools directly. For web-connected answers, include a web search tool in tools: 
{
  "model": "gpt-5.5",
  "input": "What changed in the latest OpenAI Responses API docs?",
  "tools": [
    { "type": "web_search_preview" }
  ]
}
APIAny.AI forwards Responses-native tools to compatible models that support them. Function tools are also supported.

​
Streaming

Set stream: true to receive the Responses SSE event stream. Events follow the OpenAI Responses format, such as response.created, response.output_text.delta, tool events, and response.completed. 
curl https://apiany.ai/v1/responses \
  -H "Authorization: Bearer $APIANY_API_KEY" \
  -H "Content-Type: application/json" \
  -N \
  -d '{
    "model": "gpt-5.5",
    "input": "Draft three concise release note bullets.",
    "reasoning": { "effort": "low" },
    "stream": true
  }'

​
Notes

  • The model is a public APIAny.AI model ID.
  • max_output_tokens is the Responses-style output token limit.
  • Responses-native fields such as reasoning, text, tools, tool_choice, include, previous_response_id, and store are forwarded when supported by the selected model.