Responses (OpenAI)

OpenAI Responses-format inbound adapter. OpenAI's Codex CLI only speaks /v1/responses, so this endpoint lets Codex and the Responses SDK attach.

OpenAI's Codex CLI only speaks the /v1/responses format. PleumRouter provides an inbound adapter that accepts this format and translates it into internal model calls, so you can attach Codex CLI (and the OpenAI Responses SDK) to PleumRouter as-is.

POST/v1/responses

Connecting#

Set the base URL to https://apirouter.pleum.ai/v1 and the API key to your plm_ key. In Codex, set wire_api = "responses" so it calls this endpoint.

connect

export OPENAI_BASE_URL="https://apirouter.pleum.ai/v1"
export OPENAI_API_KEY="plm_..."

responses.ts

OpenAI Responses API (Codex)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "plm_xxxxxxxxxxxxxxxx",
  baseURL: "https://apirouter.pleum.ai/v1",
});

const response = await client.responses.create({
  model: "gpt-4.1",
  input: "Why is the sky blue?",
});

console.log(response.output_text);

OpenAI Responses API (Codex)

from openai import OpenAI

client = OpenAI(
    api_key="plm_xxxxxxxxxxxxxxxx",
    base_url="https://apirouter.pleum.ai/v1",
)

response = client.responses.create(
    model="gpt-4.1",
    input="Why is the sky blue?",
)

print(response.output_text)

OpenAI Responses API (Codex)

curl https://apirouter.pleum.ai/v1/responses \
  -H "Authorization: Bearer plm_xxxxxxxxxxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "input": "Why is the sky blue?"
  }'

POST /v1/responses/{request_id}/feedback is a separate routing feedback endpoint (JWT), not Responses create.

Request body#

Parameter	Type	Required	Description
model	string	Required	Model ID. See the full list at `GET /v1/models`.
input	string \| array	Required	A string, or an array of items (`message` / `function_call` / `function_call_output`).
instructions	string	Optional	Prepended as a system message.
max_output_tokens	integer	Optional	Default 4096. Maps to the internal `max_tokens`.
temperature	number	Optional	Sampling temperature.
top_p	number	Optional	Nucleus sampling.
stream	boolean	Optional	If true, returns a Responses SSE streaming response.
tools	array	Optional	Responses flat function tools (`{type:"function", name, description, parameters}`) are converted. Non-function tools (e.g. web_search) are silently dropped.
tool_choice	string \| object	Optional	String `auto` \| `none` \| `required`, or `{type:"function", name}`.
parallel_tool_calls	boolean	Optional	Whether parallel tool calls are allowed.
metadata	object	Optional	Arbitrary key-value metadata.

request

curl https://apirouter.pleum.ai/v1/responses \
  -H "Authorization: Bearer $PLEUM_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4.1",
    "instructions": "You are a helpful assistant.",
    "input": [
      {
        "type": "message",
        "role": "user",
        "content": "Hello"
      }
    ],
    "max_output_tokens": 4096,
    "stream": false
  }'

Response#

A non-streaming response returns the assistant message in the output array. Each message's content consists of output_text parts, and usage includes input_tokens / output_tokens / total_tokens. Cost is returned in the X-Cost-Krw / X-Cost-Usd response headers, not the body. Extra fields Codex sends (reasoning, text, store, previous_response_id, include, prompt_cache_key) are accepted but ignored.

200 OK

{
  "id": "resp_gpt-4.1-841ms",
  "object": "response",
  "created_at": 1735689600,
  "status": "completed",
  "model": "gpt-4.1",
  "output": [
    {
      "id": "msg_abc123",
      "type": "message",
      "status": "completed",
      "role": "assistant",
      "content": [
        {"type": "output_text", "text": "Hi!", "annotations": []}
      ]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 5,
    "total_tokens": 17
  }
}

Streaming#

With stream: true, Responses SSE events are sent — response.created → response.in_progress → output_item.added / content_part.added / output_text.delta → output_text.done / output_item.done → response.completed with the full usage. Codex reads completed items from output_item.done and determines termination from response.completed.

Responses SSE stream

data: {"type":"response.created","response":{"id":"resp_abc","status":"in_progress"}}

data: {"type":"response.in_progress","response":{"id":"resp_abc"}}

data: {"type":"output_item.added","item":{"id":"msg_abc","type":"message","role":"assistant"}}

data: {"type":"content_part.added","item_id":"msg_abc","part":{"type":"output_text","text":""}}

data: {"type":"response.output_text.delta","item_id":"msg_abc","delta":"Hi"}

data: {"type":"response.output_text.delta","item_id":"msg_abc","delta":"!"}

data: {"type":"response.output_text.done","item_id":"msg_abc","text":"Hi!"}

data: {"type":"output_item.done","item":{"id":"msg_abc","type":"message","role":"assistant","content":[{"type":"output_text","text":"Hi!"}]}}

data: {"type":"response.completed","response":{"id":"resp_abc","status":"completed","usage":{"input_tokens":12,"output_tokens":5,"total_tokens":17}}}

Built-in tools like web_search are not forwarded and are silently dropped. Only {type:"function"} tools are converted and passed to the model.