Create Chat Completion - Requesty Docs

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is an LLM gateway?"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is an LLM gateway?"},
    ],
    max_tokens=1024,
    temperature=0.7,
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.REQUESTY_API_KEY,
  baseURL: "https://router.requesty.ai/v1",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is an LLM gateway?" },
  ],
  max_tokens: 1024,
  temperature: 0.7,
});

console.log(response.choices[0].message.content);

{
  "id": "chatcmpl-abc123def456",
  "object": "chat.completion",
  "created": 1748200000,
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "An LLM gateway is a unified API layer that routes requests to multiple large language model providers. It normalizes different API formats, handles failover, load balancing, and provides centralized monitoring and cost tracking across providers like OpenAI, Anthropic, Google, and others."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 52,
    "total_tokens": 76,
    "cost": 0.000038
  }
}

POST

chat

completions

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is an LLM gateway?"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is an LLM gateway?"},
    ],
    max_tokens=1024,
    temperature=0.7,
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.REQUESTY_API_KEY,
  baseURL: "https://router.requesty.ai/v1",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is an LLM gateway?" },
  ],
  max_tokens: 1024,
  temperature: 0.7,
});

console.log(response.choices[0].message.content);

{
  "id": "chatcmpl-abc123def456",
  "object": "chat.completion",
  "created": 1748200000,
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "An LLM gateway is a unified API layer that routes requests to multiple large language model providers. It normalizes different API formats, handles failover, load balancing, and provides centralized monitoring and cost tracking across providers like OpenAI, Anthropic, Google, and others."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 52,
    "total_tokens": 76,
    "cost": 0.000038
  }
}

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [
      {
        "role": "system",
        "content": "You are a helpful assistant."
      },
      {
        "role": "user",
        "content": "What is an LLM gateway?"
      }
    ],
    "max_tokens": 1024,
    "temperature": 0.7
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_REQUESTY_API_KEY",
    base_url="https://router.requesty.ai/v1",
)

response = client.chat.completions.create(
    model="openai/gpt-4o-mini",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is an LLM gateway?"},
    ],
    max_tokens=1024,
    temperature=0.7,
)

print(response.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.REQUESTY_API_KEY,
  baseURL: "https://router.requesty.ai/v1",
});

const response = await client.chat.completions.create({
  model: "openai/gpt-4o-mini",
  messages: [
    { role: "system", content: "You are a helpful assistant." },
    { role: "user", content: "What is an LLM gateway?" },
  ],
  max_tokens: 1024,
  temperature: 0.7,
});

console.log(response.choices[0].message.content);

{
  "id": "chatcmpl-abc123def456",
  "object": "chat.completion",
  "created": 1748200000,
  "model": "openai/gpt-4o-mini",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "An LLM gateway is a unified API layer that routes requests to multiple large language model providers. It normalizes different API formats, handles failover, load balancing, and provides centralized monitoring and cost tracking across providers like OpenAI, Anthropic, Google, and others."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 24,
    "completion_tokens": 52,
    "total_tokens": 76,
    "cost": 0.000038
  }
}

Web Search

Enable real-time web search by adding { "type": "web_search" } to the tools array. Requesty translates this to each provider’s native web search format automatically.

{
  "model": "anthropic/claude-sonnet-4-20250514",
  "messages": [
    { "role": "user", "content": "What are the latest news in London today?" }
  ],
  "tools": [{ "type": "web_search" }],
  "stream": true
}

Works with Anthropic, Vertex/Gemini, OpenAI, xAI, and Perplexity models. See the Web Search guide for response format details and provider-specific behavior.

PDF Support

Send PDFs using the input_file content type. You can provide the PDF as either base64-encoded data or a URL.

Using Base64-Encoded PDF

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Summarize this PDF"
          },
          {
            "type": "input_file",
            "filename": "document.pdf",
            "file_data": "data:application/pdf;base64,<base64-encoded-pdf-data>"
          }
        ]
      }
    ]
  }'

Using PDF URL

curl https://router.requesty.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_REQUESTY_API_KEY" \
  -d '{
    "model": "anthropic/claude-sonnet-4-20250514",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "Summarize this PDF"
          },
          {
            "type": "input_file",
            "filename": "document.pdf",
            "file_data": "https://example.com/document.pdf"
          }
        ]
      }
    ]
  }'

Parameters

type: Must be "input_file"
filename: The name of the PDF file (e.g., "document.pdf")
file_data: Either base64-encoded PDF content or a URL to the PDF file

Authorizations

Authorization

string

header

required

API key for authentication

Body

application/json

messages

object[]

required

An array of message objects with role and content

Show child attributes

model

string

default:openai/gpt-4o-mini

The model name. If omitted, defaults to openai/gpt-4o-mini.

Example:

"openai/gpt-4o-mini"

max_tokens

integer

Maximum number of tokens to generate

temperature

number

Controls randomness of the output

top_p

number

Controls diversity of the output

stream

boolean

Enable Server-Sent Events (SSE) streaming responses

tools

object[]

Available tools for the model. Supports function tools for custom function calling and web_search for real-time web search.

Show child attributes

tool_choice

string

Specifies how tool calling should be handled

response_format

object

For structured responses (some models only)

Response

Chat completion response

string

required

Unique identifier for the completion

object

string

required

Object type

created

integer

required

Timestamp of creation

model

string

required

Model used for completion

choices

object[]

required

Show child attributes

usage

object

Show child attributes

Last modified on June 8, 2026

​Web Search

​PDF Support

​Using Base64-Encoded PDF

​Using PDF URL

​Parameters

Authorizations

Body

Response

Web Search

PDF Support

Using Base64-Encoded PDF

Using PDF URL

Parameters