Chat Completions

Unified endpoint for 70+ LLM models. OpenAI-compatible drop-in replacement — just change the base URL.

POST/v1/ai/chat/completions

$0.01/call

Overview

A single endpoint that gives you access to 70+ LLM models from OpenAI, Anthropic, Google, Meta, DeepSeek, xAI, Qwen, Mistral, Perplexity, and more. Fully OpenAI-compatible — swap the base URL and it works with any OpenAI SDK.

There are two ways to call the AI API:

Endpoint	Format	Model Source
`POST /v1/ai/chat/completions`	OpenAI-compatible (snake_case)	`model` field in body
`POST /v1/ai/chat`	YepAPI simplified (camelCase)	`model` field in body

Both hit the same infrastructure. Pick whichever fits your stack.

OpenAI SDK Drop-In

Point any OpenAI SDK at YepAPI by changing the base URL:

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "YOUR_API_KEY",
  baseURL: "https://api.yepapi.com/v1/ai",
});

const response = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-4.6",
  messages: [{ role: "user", content: "Explain quantum computing in one paragraph." }],
});

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

Works with Python, Node, Go, or any language with an OpenAI-compatible client.

Usage

OpenAI-Compatible Endpoint

const res = await fetch("https://api.yepapi.com/v1/ai/chat/completions", {
  method: "POST",
  headers: {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "anthropic/claude-sonnet-4.6",
    messages: [{ role: "user", content: "What is the capital of France?" }],
    temperature: 0.7,
    max_tokens: 1024,
  }),
});
const data = await res.json();
console.log(data.choices[0].message.content);

curl -X POST https://api.yepapi.com/v1/ai/chat/completions \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{"role": "user", "content": "What is the capital of France?"}],
    "temperature": 0.7,
    "max_tokens": 1024
  }'

YepAPI Simplified Endpoint

const res = await fetch("https://api.yepapi.com/v1/ai/chat", {
  method: "POST",
  headers: {
    "x-api-key": "YOUR_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "claude-sonnet-4.6",
    messages: [{ role: "user", content: "What is the capital of France?" }],
    temperature: 0.7,
    maxTokens: 1024,
  }),
});
const { data } = await res.json();
console.log(data.message.content);

Info

The /v1/ai/chat endpoint accepts short aliases like gpt-4o, claude-sonnet, or gemini-flash — no need for the full provider/model format.

Request Body

`/v1/ai/chat/completions` (OpenAI-compatible, snake_case)

Parameter	Type	Required	Description	Default
`model`	`string`	Yes	Model ID (e.g. `openai/gpt-4o`, `anthropic/claude-sonnet-4.6`)	—
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`max_tokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`top_p`	`number`	No	Nucleus sampling threshold	`1.0`
`frequency_penalty`	`number`	No	Penalize repeated tokens	`0`
`presence_penalty`	`number`	No	Penalize tokens already present	`0`
`stop`	`string \| string[]`	No	Stop sequences	—
`stream`	`boolean`	No	Enable SSE streaming	`false`

`/v1/ai/chat` (YepAPI simplified, camelCase)

Parameter	Type	Required	Description	Default
`model`	`string`	No	Model ID or alias (e.g. `gpt-4o`, `claude-sonnet`)	`openai/gpt-4o-mini`
`messages`	`Message[]`	Yes	Array of `{ role, content }` objects	—
`maxTokens`	`number`	No	Maximum tokens in the response	Model default
`temperature`	`number`	No	Sampling temperature (0.0–2.0)	`1.0`
`topP`	`number`	No	Nucleus sampling threshold	`1.0`
`frequencyPenalty`	`number`	No	Penalize repeated tokens	`0`
`presencePenalty`	`number`	No	Penalize tokens already present	`0`
`stop`	`string \| string[]`	No	Stop sequences	—
`stream`	`boolean`	No	Enable SSE streaming	`false`

Model Aliases

The /v1/ai/chat endpoint accepts short aliases so you don't need the full provider/model format:

Alias	Resolves To
`gpt-4o`	`openai/gpt-4o`
`gpt-4o-mini`	`openai/gpt-4o-mini`
`gpt-5.4`	`openai/gpt-5.4`
`claude-opus`	`anthropic/claude-opus-4.6`
`claude-sonnet`	`anthropic/claude-sonnet-4.6`
`claude-haiku`	`anthropic/claude-haiku-4`
`gemini-pro`	`google/gemini-2.5-pro`
`gemini-flash`	`google/gemini-2.5-flash`
`grok`	`x-ai/grok-4.20`
`deepseek-v3`	`deepseek/deepseek-chat-v3`
`deepseek-r1`	`deepseek/deepseek-r1`
`sonar-pro`	`perplexity/sonar-pro`
`llama-scout`	`meta-llama/llama-4-scout`
`qwen`	`qwen/qwen3.6-plus`
`mistral-small`	`mistralai/mistral-small-2603`

You can also pass the full provider/model format to either endpoint.

Response Formats

`/v1/ai/chat/completions` (OpenAI-compatible)

{
  "id": "chatcmpl-abc123",
  "object": "text_completion",
  "created": 1713100000,
  "model": "anthropic/claude-sonnet-4.6",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 14,
    "completion_tokens": 8,
    "total_tokens": 22
  }
}

`/v1/ai/chat` (YepAPI simplified)

{
  "ok": true,
  "data": {
    "id": "chatcmpl-abc123",
    "model": "anthropic/claude-sonnet-4.6",
    "message": {
      "role": "assistant",
      "content": "The capital of France is Paris."
    },
    "usage": {
      "promptTokens": 14,
      "completionTokens": 8,
      "totalTokens": 22
    },
    "costUsd": 0.000162
  }
}

Streaming

Set "stream": true to receive Server-Sent Events.

`/v1/ai/chat/completions` (OpenAI-compatible SSE)

data: {"id":"chatcmpl-abc123","model":"anthropic/claude-sonnet-4.6","choices":[{"index":0,"delta":{"role":"assistant","content":"The"},"finish_reason":null}]}
data: {"id":"chatcmpl-abc123","model":"anthropic/claude-sonnet-4.6","choices":[{"index":0,"delta":{"content":" capital"},"finish_reason":null}]}
data: [DONE]

`/v1/ai/chat` (YepAPI simplified SSE)

data: {"id":"chatcmpl-abc123","delta":{"role":"assistant","content":"The"},"model":"anthropic/claude-sonnet-4.6","index":0}
data: {"id":"chatcmpl-abc123","delta":{"content":" capital"},"model":"anthropic/claude-sonnet-4.6","index":0}
data: [DONE]

List Available Models

curl https://api.yepapi.com/v1/ai/models

Returns every available model with pricing, context window, and capabilities. This endpoint is free and does not require authentication.

Under the Hood

We handle auth, billing, and response normalization — you just send messages.

Chat Completions

On this page