Skip to main content
POST
/
v1
/
responses
curl --request POST \
  --url https://api.edgee.ai/v1/responses \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "openai/gpt-4o",
  "input": "What is the capital of France?"
}
'
{
  "id": "resp_abc123",
  "object": "response",
  "status": "completed",
  "created_at": 1677652288,
  "model": "openai/gpt-4o",
  "output": [
    {
      "id": "msg_1",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Paris"
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 8,
    "output_tokens": 1,
    "total_tokens": 9
  }
}

Documentation Index

Fetch the complete documentation index at: https://www.edgee.ai/docs/llms.txt

Use this file to discover all available pages before exploring further.

Creates a response using the OpenAI Responses API format (POST /v1/responses). This endpoint is compatible with OpenAI’s Responses API, making it easy to use with tools like the Codex CLI.

Authorizations

​
Authorization
string
header
required

Bearer authentication header of the form Bearer <token>, where <token> is your API key. More info here

Headers

​
X-Edgee-Tags
string

Comma-separated list of tags for categorizing and filtering requests in analytics and logs. Example: production,agent,codex

​
X-Edgee-Debug
boolean

Enable debug mode to include additional debugging information in the response.

​
X-Edgee-Compression-Model
enum<string>

Compression bundle to apply.

Available options:
claude,
opencode,
cursor,
codex

Body

application/json
​
model
string
required

ID of the model to use, with provider prefix. Format: {author_id}/{model_id}.

Example:

"openai/gpt-4o"

​
input
required

The input to the model. Either a plain string (treated as a single user message) or a flat array of typed input items (messages, function calls, function call outputs).

​
instructions
string

System-level instruction prepended to the conversation. An alternative to including a system role message in the input array.

​
stream
boolean
default:false

If set, the response is streamed as Server-Sent Events (SSE).

​
max_output_tokens
integer

Maximum number of tokens to generate.

Required range: x >= 1
​
tools
object[]

Tools available to the model. Uses the Responses API flat format (no nested function key).

​
tool_choice

Controls tool selection.

Available options:
auto,
none
​
temperature
number

Sampling temperature between 0 and 2. Higher values produce more random outputs.

Required range: 0 <= x <= 2
​
top_p
number

Nucleus sampling probability. Alternative to temperature.

​
tags
string[]

List of string tags for categorizing and filtering requests in analytics and logs. Can also be sent via the X-Edgee-Tags header.

​
enable_debug
boolean

Enable debug mode to include additional information in the response.

​
edgee_tool_ids
string[]

List of Edgee-managed tool IDs to include automatically (e.g. edgee_current_time, edgee_generate_uuid). Each ID must be activated for your API key.

Example:
["edgee_current_time", "edgee_generate_uuid"]
​
edgee_pending_id
string

Pending operation ID when continuing a conversation after Edge Tool execution. The gateway injects stored Edge Tool results into the conversation history.

​
compression_model
enum<string>

Selects the compression bundle to apply to the request. Equivalent to the X-Edgee-Compression-Model header.

Available options:
claude,
opencode,
codex,
cursor

Response

Response created successfully

​
id
string
required

Unique identifier for the response, prefixed with resp_.

Example:

"resp_abc123"

​
object
enum<string>
required
Available options:
response
​
status
enum<string>
required

completed for non-streaming responses; in_progress is emitted on the initial response.created SSE event.

Available options:
completed,
in_progress
​
created_at
number
required

Unix timestamp (as a float) of when the response was created.

Example:

1677652288

​
model
string
required

The model used to generate the response.

Example:

"openai/gpt-4o"

​
output
object[]
required

Array of output items produced by the model.

​
usage
object
required

Token usage statistics for the response.