Responses API

The Responses API provides a simplified interface for generating AI responses, compatible with the OpenAI Responses format.

POST/v1/responses

Request Parameters

Parameter	Type	Required	Description
`model`	string	Yes	The model to use (e.g. "gpt-4o", "o3")
`input`	string \| array	Yes	Input text or array of message objects with role and content
`instructions`	string	No	System instructions to guide the model's behavior
`max_output_tokens`	integer	No	Maximum number of tokens to generate
`stream`	boolean	No	If true, returns a stream of server-sent events. Default: false

Request Example

curl https://api.osiris.ai/v1/responses \
  -H "Authorization: Bearer sk-osiris-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "instructions": "You are a helpful assistant.",
    "input": "What is the capital of France?"
  }'

Response Format

Response

{
  "id": "resp_abc123",
  "object": "response",
  "created_at": 1712678400,
  "model": "gpt-4o",
  "status": "completed",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "The capital of France is Paris."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 25,
    "output_tokens": 12,
    "total_tokens": 37
  }
}

Conversation Input

The input field can be a string for simple prompts, or an array of messages for multi-turn conversations:

Multi-turn conversation

{
  "model": "gpt-4o",
  "instructions": "You are a helpful assistant.",
  "input": [
    { "role": "user", "content": "What is 2 + 2?" },
    { "role": "assistant", "content": "2 + 2 equals 4." },
    { "role": "user", "content": "And what is that times 3?" }
  ]
}

SSE Event Types

When streaming is enabled, the API sends the following event types:

Event	Description
`response.created`	The response object has been created
`response.output_text.delta`	A chunk of output text has been generated
`response.output_text.done`	The output text generation is complete
`response.completed`	The full response is complete with usage data

Streaming Example

curl https://api.osiris.ai/v1/responses \
  -H "Authorization: Bearer sk-osiris-YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "stream": true,
    "input": "Tell me a short joke."
  }'

The SSE stream will produce events in this format:

SSE stream format

event: response.created
data: {"type":"response.created","response":{"id":"resp_abc123","object":"response","status":"in_progress","model":"gpt-4o","output":[]}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":"Why"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" did"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" the"}

event: response.output_text.delta
data: {"type":"response.output_text.delta","delta":" chicken..."}

event: response.output_text.done
data: {"type":"response.output_text.done","text":"Why did the chicken cross the road? To get to the other side!"}

event: response.completed
data: {"type":"response.completed","response":{"id":"resp_abc123","object":"response","status":"completed","model":"gpt-4o","usage":{"input_tokens":10,"output_tokens":18,"total_tokens":28}}}