Create a response - Yelu AI API

curl https://api.yelu.ai/v1/responses \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "instructions": "Answer for a software engineering audience.",
    "input": "What is idempotency?",
    "max_output_tokens": 160
  }'

const response = await fetch('https://api.yelu.ai/v1/responses', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    instructions: 'Answer for a software engineering audience.',
    input: 'What is idempotency?',
    max_output_tokens: 160,
  }),
});

if (!response.ok) throw new Error(await response.text());
const data = await response.json();
const text = data.output
  .flatMap((item) => item.content ?? [])
  .filter((item) => item.type === 'output_text')
  .map((item) => item.text)
  .join('');
console.log(text);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/responses",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "instructions": "Answer for a software engineering audience.",
        "input": "What is idempotency?",
        "max_output_tokens": 160,
    },
    timeout=60,
)
response.raise_for_status()
data = response.json()
text = "".join(
    part["text"]
    for item in data["output"]
    for part in item.get("content", [])
    if part.get("type") == "output_text"
)
print(text)

{
  "id": "resp_01JYELU9R2",
  "object": "response",
  "created_at": 1783900800,
  "status": "completed",
  "model": "gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "id": "msg_01JYELU9R3",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Idempotency means repeating the same operation has the same intended effect as performing it once."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 22,
    "total_tokens": 42
  }
}

{
  "error": {
    "message": "Input is required for this request.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "missing_required_parameter"
  }
}

POST

responses

curl https://api.yelu.ai/v1/responses \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "instructions": "Answer for a software engineering audience.",
    "input": "What is idempotency?",
    "max_output_tokens": 160
  }'

const response = await fetch('https://api.yelu.ai/v1/responses', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    instructions: 'Answer for a software engineering audience.',
    input: 'What is idempotency?',
    max_output_tokens: 160,
  }),
});

if (!response.ok) throw new Error(await response.text());
const data = await response.json();
const text = data.output
  .flatMap((item) => item.content ?? [])
  .filter((item) => item.type === 'output_text')
  .map((item) => item.text)
  .join('');
console.log(text);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/responses",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "instructions": "Answer for a software engineering audience.",
        "input": "What is idempotency?",
        "max_output_tokens": 160,
    },
    timeout=60,
)
response.raise_for_status()
data = response.json()
text = "".join(
    part["text"]
    for item in data["output"]
    for part in item.get("content", [])
    if part.get("type") == "output_text"
)
print(text)

{
  "id": "resp_01JYELU9R2",
  "object": "response",
  "created_at": 1783900800,
  "status": "completed",
  "model": "gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "id": "msg_01JYELU9R3",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Idempotency means repeating the same operation has the same intended effect as performing it once."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 22,
    "total_tokens": 42
  }
}

{
  "error": {
    "message": "Input is required for this request.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "missing_required_parameter"
  }
}

Creates a response from text or structured input. The Responses API represents model output as typed items and is the recommended surface for new agentic workflows.

Endpoint

POST https://api.yelu.ai/v1/responses

Headers

Authorization

string

required

API key using the format Bearer $YELU_API_KEY.

Content-Type

string

required

Must be application/json.

Request body

model

string

required

A model ID returned by GET /v1/models.

input

string | array

Text input or an array of typed input messages/items. Supply input unless continuing in a provider-supported way.

instructions

string

High-priority instructions for the response.

previous_response_id

string

ID of a prior response to continue a conversation when the selected model/provider supports stored response state.

max_output_tokens

integer

Maximum output tokens, including model-specific reasoning usage where applicable.

temperature

number

Sampling temperature on models that expose this control.

top_p

number

Nucleus sampling probability on models that expose this control.

stream

boolean

default:"false"

Returns typed Server-Sent Events when true.

tools

array

Tools the model may call, including function definitions supported by the selected model.

tool_choice

string | object

Controls whether and which tool the model may select.

reasoning

object

Reasoning configuration. Supported fields include effort (low, medium, or high) and provider-supported summary controls.

truncation

string

default:"disabled"

auto allows context truncation when supported; disabled fails instead of silently removing context.

Response

string

required

Unique response identifier.

object

string

required

Always response for the completed response object.

created_at

integer

required

Unix timestamp for creation.

status

string

required

completed, failed, in_progress, or incomplete.

model

string

required

Model that handled the request.

output

array

required

Typed output items. A message item commonly includes id, status, role, and a content array with output_text objects. Tool calls appear as separate items.

usage

object

Input, output, total, cached, or reasoning token accounting supplied by the selected model.

curl https://api.yelu.ai/v1/responses \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "instructions": "Answer for a software engineering audience.",
    "input": "What is idempotency?",
    "max_output_tokens": 160
  }'

const response = await fetch('https://api.yelu.ai/v1/responses', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    instructions: 'Answer for a software engineering audience.',
    input: 'What is idempotency?',
    max_output_tokens: 160,
  }),
});

if (!response.ok) throw new Error(await response.text());
const data = await response.json();
const text = data.output
  .flatMap((item) => item.content ?? [])
  .filter((item) => item.type === 'output_text')
  .map((item) => item.text)
  .join('');
console.log(text);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/responses",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "instructions": "Answer for a software engineering audience.",
        "input": "What is idempotency?",
        "max_output_tokens": 160,
    },
    timeout=60,
)
response.raise_for_status()
data = response.json()
text = "".join(
    part["text"]
    for item in data["output"]
    for part in item.get("content", [])
    if part.get("type") == "output_text"
)
print(text)

{
  "id": "resp_01JYELU9R2",
  "object": "response",
  "created_at": 1783900800,
  "status": "completed",
  "model": "gpt-4o-mini",
  "output": [
    {
      "type": "message",
      "id": "msg_01JYELU9R3",
      "status": "completed",
      "role": "assistant",
      "content": [
        {
          "type": "output_text",
          "text": "Idempotency means repeating the same operation has the same intended effect as performing it once."
        }
      ]
    }
  ],
  "usage": {
    "input_tokens": 20,
    "output_tokens": 22,
    "total_tokens": 42
  }
}

{
  "error": {
    "message": "Input is required for this request.",
    "type": "invalid_request_error",
    "param": "input",
    "code": "missing_required_parameter"
  }
}

Error codes

Status	Code or type	Meaning
`400`	`invalid_request_error`	Invalid input item, field, tool, or model capability.
`401`	`authentication_error`	Missing or invalid API key.
`403`	`permission_denied`	The model or operation is not allowed.
`404`	`model_not_found` or response not found	Invalid model or unsupported prior response ID.
`413`	`request_too_large`	Input exceeds the accepted request or context size.
`429`	`rate_limit_error`	Request limit reached.
`500`–`504`	`server_error`	Temporary gateway or upstream failure.

Provider support for stored response state varies. Persist the conversation state your application needs; do not rely solely on previous_response_id without testing the selected model route.

Last modified on July 13, 2026

Create a chat completion Generate an image

​Endpoint

​Headers

​Request body

​Response

​Error codes

Endpoint

Headers

Request body

Response

Error codes