Create a chat completion

curl https://api.pipellm.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PIPELLM_API_KEY" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai/v1",
)
print(client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
).choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PIPELLM_API_KEY,
  baseURL: "https://api.pipellm.ai/v1",
});
const response = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

{
  "id": "<string>",
  "object": "<string>",
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {},
      "delta": {},
      "finish_reason": "<string>"
    }
  ],
  "usage": {}
}

POST

chat

completions

curl https://api.pipellm.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PIPELLM_API_KEY" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai/v1",
)
print(client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
).choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PIPELLM_API_KEY,
  baseURL: "https://api.pipellm.ai/v1",
});
const response = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

{
  "id": "<string>",
  "object": "<string>",
  "model": "<string>",
  "choices": [
    {
      "index": 123,
      "message": {},
      "delta": {},
      "finish_reason": "<string>"
    }
  ],
  "usage": {}
}

Use Authorization: Bearer $PIPELLM_API_KEY. Pick model from GET /v1/models.

Endpoint

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

This free route accepts OpenAI-compatible requests and routes only to OpenAI-compatible platforms. To keep the OpenAI format while calling Anthropic or Gemini models, use the OpenAI Format Converter.

curl https://api.pipellm.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PIPELLM_API_KEY" \
  -d '{
    "model": "gpt-5",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["PIPELLM_API_KEY"],
    base_url="https://api.pipellm.ai/v1",
)
print(client.chat.completions.create(
    model="gpt-5",
    messages=[{"role": "user", "content": "Hello"}],
).choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PIPELLM_API_KEY,
  baseURL: "https://api.pipellm.ai/v1",
});
const response = await client.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(response.choices[0].message.content);

Code Examples

cURL
Python
Node.js
Go

curl https://api.pipellm.ai/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $PIPELLM_API_KEY" \
  -d '{
    "model": "gpt-5",
    "max_completion_tokens": 1024,
    "messages": [
      {
        "role": "user",
        "content": "Why is the sky blue?"
      }
    ]
  }'

import os
from openai import OpenAI

client = OpenAI(
  api_key=os.getenv('PIPELLM_API_KEY'),
  base_url='https://api.pipellm.ai/v1'
)

response = client.chat.completions.create(
  model='gpt-5',
  messages=[
    {
      'role': 'user',
      'content': 'Why is the sky blue?'
    }
  ]
)

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.PIPELLM_API_KEY,
  baseURL: 'https://api.pipellm.ai/v1'
});

const response = await client.chat.completions.create({
  model: 'gpt-5',
  messages: [
    {
      role: 'user',
      content: 'Why is the sky blue?'
    }
  ]
});

package main

import (
  "context"
  "os"
  openai "github.com/sashabaranov/go-openai"
)

func main() {
  config := openai.DefaultConfig(os.Getenv("PIPELLM_API_KEY"))
  config.BaseURL = "https://api.pipellm.ai/v1"
  client := openai.NewClientWithConfig(config)

  resp, _ := client.CreateChatCompletion(
    context.Background(),
    openai.ChatCompletionRequest{
      Model: "gpt-5",
      Messages: []openai.ChatCompletionMessage{
        {
          Role:    openai.ChatMessageRoleUser,
          Content: "Why is the sky blue?",
        },
      },
    },
  )
}

Request Parameters

Pick model from GET /v1/models. Native /v1/chat/completions only routes to OpenAI-compatible platforms.

string

required

Model ID visible to your account.

array

required

Conversation messages. At least one item.

Show messages[]

string

required

system, user, assistant, or tool.

string | array

required

Plain text, or an array of content parts.

Show content parts

string

required

text or image_url.

string

Required when type is text.

object

Required when type is image_url. Set url to an HTTPS URL or a data URL.

string

Optional speaker name.

string

Required when role is tool.

number

Sampling temperature, 0–2. Default 1.

integer

Maximum tokens to generate.

integer

Preferred maximum for newer OpenAI-compatible models. Use this instead of max_tokens when the model requires it.

boolean

If true, return server-sent events. See Streaming.

object

Streaming extras.

Show stream_options fields

boolean

If true, the last SSE chunk includes usage.

number

Nucleus sampling, 0–1.

integer

Number of completions to generate. Default 1.

string | string[]

Stop sequence or list of stop sequences.

number

Presence penalty, -2 to 2. Default 0.

number

Frequency penalty, -2 to 2. Default 0.

array

Function tools the model may call. See Function Calling.

Show tools[]

string

required

Always function.

object

required

Tool definition.

Show function fields

string

required

Function name.

string

What the function does.

object

JSON Schema for the function arguments.

string | object

auto, none, or {"type":"function","function":{"name":"..."}}.

string

End-user identifier for abuse tracking.

Response Format

{
  "id": "chatcmpl-xxx",
  "object": "chat.completion",
  "created": 1234567890,
  "model": "gpt-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The sky appears blue because..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 10,
    "completion_tokens": 50,
    "total_tokens": 60
  }
}

string

Completion ID.

string

chat.completion, or chat.completion.chunk when streaming.

string

Model that produced the response.

array

Completion choices.

Show choices[]

integer

Choice index.

object

Present when stream is false. Contains role, content, and optional tool_calls.

object

Present when streaming. Partial role / content / tool_calls.

string

stop, length, or tool_calls.

object

Token counts: prompt_tokens, completion_tokens, total_tokens.

Errors

Same envelope as Errors.

400 invalid_request_error

Malformed JSON, missing model / messages, or a protocol mismatch on this native route.

{
  "error": {
    "type": "invalid_request_error",
    "code": "400",
    "message": "The 'model' field is required but was not provided in the request"
  }
}

401 authentication_error

Missing or invalid API key.

{
  "error": {
    "type": "authentication_error",
    "code": "401",
    "message": "Incorrect API key provided. Please visit https://console.pipellm.ai/account/api-keys to find your API key."
  }
}

402 insufficient_balance

Balance check failed before the request was processed.

{
  "error": {
    "type": "insufficient_balance",
    "code": "402",
    "message": "Insufficient balance. Please recharge your account at https://console.pipellm.ai/billing."
  }
}

429 rate_limit_error

Account RPM exceeded. See Rate Limits.

{
  "error": {
    "type": "rate_limit_error",
    "code": "429",
    "message": "Rate limit exceeded. Your current limit is 120 requests per minute (approximately 2.00 requests per second). Please visit https://console.pipellm.ai/billing to upgrade your plan for higher limits."
  }
}

Function Calling

Function Calling allows models to generate structured JSON to call functions in your code.

Python
Node.js

tools = [
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get the current weather in a location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": {"type": "string", "description": "City name"}
        },
        "required": ["location"]
      }
    }
  }
]

response = client.chat.completions.create(
  model="gpt-5",
  messages=[{"role": "user", "content": "What's the weather in Tokyo?"}],
  tools=tools,
  tool_choice="auto"
)

if response.choices[0].message.tool_calls:
  tool_call = response.choices[0].message.tool_calls[0]
  # Execute your function and return result

const tools = [
  {
    type: "function",
    function: {
      name: "get_weather",
      description: "Get the current weather in a location",
      parameters: {
        type: "object",
        properties: {
          location: { type: "string", description: "City name" }
        },
        required: ["location"]
      }
    }
  }
];

const response = await client.chat.completions.create({
  model: 'gpt-5',
  messages: [{ role: 'user', content: "What's the weather in Tokyo?" }],
  tools: tools,
  tool_choice: 'auto'
});

if (response.choices[0].message.tool_calls) {
  const toolCall = response.choices[0].message.tool_calls[0];
  // Execute your function and return result
}

Function Calling Documentation

Complete guide on defining functions and handling responses

API Guides

API Reference

Create a chat completion

Endpoint

Code Examples

Request Parameters

Response Format

Errors

Function Calling

Function Calling Documentation

​Endpoint

​Code Examples

​Request Parameters

​Response Format

​Errors

​Function Calling

Function Calling Documentation

Endpoint

Code Examples

Request Parameters

Response Format

Errors

Function Calling