Create a chat completion

curl https://api.yelu.ai/v1/chat/completions \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a concise technical editor."},
      {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."}
    ],
    "temperature": 0.2,
    "max_completion_tokens": 80
  }'

const response = await fetch('https://api.yelu.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    messages: [
      { role: 'system', content: 'You are a concise technical editor.' },
      { role: 'user', content: 'Rewrite: APIs should fail in predictable ways.' },
    ],
    temperature: 0.2,
    max_completion_tokens: 80,
  }),
});

if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).choices[0].message.content);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "messages": [
            {"role": "system", "content": "You are a concise technical editor."},
            {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."},
        ],
        "temperature": 0.2,
        "max_completion_tokens": 80,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json()["choices"][0]["message"]["content"])

{
  "id": "chatcmpl_01JYELU8D1",
  "object": "chat.completion",
  "created": 1783900800,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "APIs should return consistent, well-defined errors."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 29,
    "completion_tokens": 10,
    "total_tokens": 39
  }
}

{
  "error": {
    "message": "The model field is required.",
    "type": "invalid_request_error",
    "param": "model",
    "code": "missing_required_parameter"
  }
}

POST

chat

completions

curl https://api.yelu.ai/v1/chat/completions \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a concise technical editor."},
      {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."}
    ],
    "temperature": 0.2,
    "max_completion_tokens": 80
  }'

const response = await fetch('https://api.yelu.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    messages: [
      { role: 'system', content: 'You are a concise technical editor.' },
      { role: 'user', content: 'Rewrite: APIs should fail in predictable ways.' },
    ],
    temperature: 0.2,
    max_completion_tokens: 80,
  }),
});

if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).choices[0].message.content);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "messages": [
            {"role": "system", "content": "You are a concise technical editor."},
            {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."},
        ],
        "temperature": 0.2,
        "max_completion_tokens": 80,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json()["choices"][0]["message"]["content"])

{
  "id": "chatcmpl_01JYELU8D1",
  "object": "chat.completion",
  "created": 1783900800,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "APIs should return consistent, well-defined errors."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 29,
    "completion_tokens": 10,
    "total_tokens": 39
  }
}

{
  "error": {
    "message": "The model field is required.",
    "type": "invalid_request_error",
    "param": "model",
    "code": "missing_required_parameter"
  }
}

Creates a model response from an ordered list of conversation messages. This endpoint is the broadest compatibility choice for existing OpenAI SDK integrations.

Endpoint

POST https://api.yelu.ai/v1/chat/completions

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.

messages

array

required

Ordered conversation messages. Each item has a role (system, developer, user, assistant, or tool, as supported by the model) and content. Content can be text or a multimodal content array.

temperature

number

default:"1"

Sampling temperature from 0 to 2. Prefer changing either temperature or top_p, not both.

top_p

number

default:"1"

Nucleus sampling probability from 0 to 1.

max_completion_tokens

integer

Maximum tokens the model may generate. Support and accounting of reasoning tokens are model-specific.

stream

boolean

default:"false"

When true, returns Server-Sent Events with incremental completion chunks.

stream_options

object

Streaming options. Set include_usage to true to request a final usage chunk when supported.

stop

string | string[]

Up to the model’s supported number of sequences that stop generation.

presence_penalty

number

default:"0"

Value from -2 to 2 that adjusts reuse based on whether tokens appeared.

frequency_penalty

number

default:"0"

Value from -2 to 2 that adjusts reuse based on token frequency.

tools

array

Function definitions the model may call. Validate all generated arguments before execution.

tool_choice

string | object

Use none, auto, required, or a named function choice when supported.

response_format

object

Requests JSON object or JSON schema output on compatible models. See Structured output.

reasoning_effort

string

low, medium, or high on compatible reasoning models.

user

string

A stable, non-sensitive identifier for your end user. Do not send direct personal information.

Response

string

required

Unique completion identifier.

object

string

required

chat.completion for non-streaming requests; streaming chunks use chat.completion.chunk.

created

integer

required

Unix timestamp for creation.

model

string

required

Model that produced the completion.

choices

array

required

Generated alternatives. Each choice contains index, an assistant message, and finish_reason such as stop, length, tool_calls, or content_filter.

usage

object

Token accounting, commonly prompt_tokens, completion_tokens, and total_tokens. Additional fields can appear for supported models.

curl https://api.yelu.ai/v1/chat/completions \
  -H "Authorization: Bearer $YELU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "You are a concise technical editor."},
      {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."}
    ],
    "temperature": 0.2,
    "max_completion_tokens": 80
  }'

const response = await fetch('https://api.yelu.ai/v1/chat/completions', {
  method: 'POST',
  headers: {
    Authorization: `Bearer ${process.env.YELU_API_KEY}`,
    'Content-Type': 'application/json',
  },
  body: JSON.stringify({
    model: 'gpt-4o-mini',
    messages: [
      { role: 'system', content: 'You are a concise technical editor.' },
      { role: 'user', content: 'Rewrite: APIs should fail in predictable ways.' },
    ],
    temperature: 0.2,
    max_completion_tokens: 80,
  }),
});

if (!response.ok) throw new Error(await response.text());
console.log((await response.json()).choices[0].message.content);

import os
import requests

response = requests.post(
    "https://api.yelu.ai/v1/chat/completions",
    headers={"Authorization": f"Bearer {os.environ['YELU_API_KEY']}"},
    json={
        "model": "gpt-4o-mini",
        "messages": [
            {"role": "system", "content": "You are a concise technical editor."},
            {"role": "user", "content": "Rewrite: APIs should fail in predictable ways."},
        ],
        "temperature": 0.2,
        "max_completion_tokens": 80,
    },
    timeout=60,
)
response.raise_for_status()
print(response.json()["choices"][0]["message"]["content"])

{
  "id": "chatcmpl_01JYELU8D1",
  "object": "chat.completion",
  "created": 1783900800,
  "model": "gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "APIs should return consistent, well-defined errors."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 29,
    "completion_tokens": 10,
    "total_tokens": 39
  }
}

{
  "error": {
    "message": "The model field is required.",
    "type": "invalid_request_error",
    "param": "model",
    "code": "missing_required_parameter"
  }
}

Error codes

Status	Code or type	Meaning
`400`	`invalid_request_error`	Invalid messages, fields, values, JSON, or model capability.
`401`	`authentication_error`	Missing or invalid API key.
`403`	`permission_denied`	The key cannot use the requested model or operation.
`404`	`model_not_found`	Model ID is unavailable; refresh the model list.
`413`	`request_too_large`	Context or request body is too large.
`429`	`rate_limit_error`	Account or group request limit reached.
`500`–`504`	`server_error`	Temporary gateway or upstream failure.

Streaming

Parse SSE completion chunks safely.

Function calling

Connect chat models to application tools.

Last modified on July 13, 2026

List models Create a response

​Endpoint

​Headers

​Request body

​Response

​Error codes

Streaming

Function calling

Endpoint

Headers

Request body

Response

Error codes