Responses

Generate text with any text model using the OpenAI Responses API. This endpoint is a drop-in for client.responses.create(...) — point the OpenAI SDK at ImageRouter by changing the base URL. You are billed on the true token cost of each request.

Curl

curl 'https://api.imagerouter.io/v1/openai/responses' \
-H 'Authorization: Bearer YOUR_API_KEY' \
--json '{
  "model": "openai/gpt-4o-mini",
  "input": "Write a haiku about the ocean."
}'

Javascript

import OpenAI from 'openai'

const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://api.imagerouter.io/v1/openai',
})

const response = await client.responses.create({
model: 'openai/gpt-4o-mini',
input: 'Write a haiku about the ocean.',
})

console.log(response.output_text)

Python

from openai import OpenAI

client = OpenAI(
  api_key="YOUR_API_KEY",
  base_url="https://api.imagerouter.io/v1/openai",
)

response = client.responses.create(
  model="openai/gpt-4o-mini",
  input="Write a haiku about the ocean.",
)

print(response.output_text)

Streaming

Set stream: true to receive a Server-Sent Events stream of Responses API events. The stream is proxied unchanged, and the final response.completed event carries token usage and the true cost.

Curl

curl 'https://api.imagerouter.io/v1/openai/responses' \
-H 'Authorization: Bearer YOUR_API_KEY' \
--json '{
  "model": "openai/gpt-4o-mini",
  "input": "Write a haiku about the ocean.",
  "stream": true
}'

Javascript

import OpenAI from 'openai'

const client = new OpenAI({
apiKey: 'YOUR_API_KEY',
baseURL: 'https://api.imagerouter.io/v1/openai',
})

const stream = await client.responses.create({
model: 'openai/gpt-4o-mini',
input: 'Write a haiku about the ocean.',
stream: true,
})

for await (const event of stream) {
if (event.type === 'response.output_text.delta') process.stdout.write(event.delta)
}

Python

from openai import OpenAI

client = OpenAI(
  api_key="YOUR_API_KEY",
  base_url="https://api.imagerouter.io/v1/openai",
)

stream = client.responses.create(
  model="openai/gpt-4o-mini",
  input="Write a haiku about the ocean.",
  stream=True,
)

for event in stream:
  if event.type == "response.output_text.delta":
      print(event.delta, end="")

Parameters

• model required Text model to use for the response.

• input required The prompt. Either a plain string or an array of input items in OpenAI Responses format.

• stream optional When true, response events are streamed as Server-Sent Events. Defaults to false.

• instructions, max_output_tokens, temperature, top_p, tools, tool_choice, reasoning, text, … optional All standard OpenAI Responses parameters are passed through to the model unchanged.

Response

{
  "id": "resp_...",
  "object": "response",
  "created_at": 1234567890,
  "model": "openai/gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "role": "assistant",
      "content": [{ "type": "output_text", "text": "..." }]
    }
  ],
  "usage": {
    "input_tokens": 12,
    "output_tokens": 24,
    "total_tokens": 36,
    "cost": 0.0000123
  },
  "cost": 0.0001
}

usage.cost is the true upstream cost in USD. The top-level cost field is what was charged to your ImageRouter credits (the true cost, rounded up to the nearest 1/10,000 USD).