Free API Developer Reference

High-speed AI reasoning API gateway supporting OpenAI SDK drop-in compatibility, standard REST JSON completions, and sub-second Server-Sent Events (SSE) token streaming.

Base URL & Authentication

By default, the server is hosted locally at port 8000 or your deployment domain.

Interface	Base URL	Authentication
Native REST Endpoints	`https://freeapi.space`	None required.
OpenAI SDK Endpoint	`https://freeapi.space/v1`	Accepts any placeholder string (e.g. `api_key="free-api-key"`).

Headers: Send Content-Type: application/json on all POST requests. To consume streaming endpoints via standard HTTP clients, set Accept: text/event-stream.

Quickstart

Send your first query to the native endpoint using cURL, Python, or JavaScript:

curl -X POST "https://freeapi.space/api/chat" \
  -H "Content-Type: application/json" \
  -d '{"prompt": "Explain the halting problem concisely."}'

import httpx

response = httpx.post(
    "https://freeapi.space/api/chat",
    json={"prompt": "Explain the halting problem concisely."},
    timeout=60.0
)
data = response.json()
print(data["ai_response"])

const response = await fetch('https://freeapi.space/api/chat', {
  method: 'POST',
  headers: { 'Content-Type': 'application/json' },
  body: JSON.stringify({ prompt: 'Explain the halting problem concisely.' })
});

const data = await response.json();
console.log(data.ai_response);

OpenAI SDK Compatibility

The server provides complete drop-in compatibility with official OpenAI SDKs, LangChain, LiteLLM, and LlamaIndex. Point your client to base_url="https://freeapi.space/v1".

from openai import OpenAI

client = OpenAI(
    base_url="https://freeapi.space/v1",
    api_key="free-api-key"  # Any non-empty string is accepted
)

stream = client.chat.completions.create(
    model="gpt-4o",
    messages=[
        {"role": "system", "content": "You are an expert tutor."},
        {"role": "user", "content": "Explain Dijkstra's algorithm."}
    ],
    stream=True
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="", flush=True)
print()

from openai import OpenAI

client = OpenAI(
    base_url="https://freeapi.space/v1",
    api_key="free-api-key"
)

response = client.chat.completions.create(
    model="gpt-4o",
    messages=[{"role": "user", "content": "Explain Dijkstra's algorithm."}],
    stream=False
)

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

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://freeapi.space/v1',
  apiKey: 'free-api-key'
});

const stream = await openai.chat.completions.create({
  model: 'gpt-4o',
  messages: [{ role: 'user', content: 'Explain Dijkstra\'s algorithm.' }],
  stream: true
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content || '');
}

from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage

llm = ChatOpenAI(
    base_url="https://freeapi.space/v1",
    api_key="free-api-key",
    model="gpt-4o",
    streaming=True
)

for chunk in llm.stream([HumanMessage(content="Explain Dijkstra's algorithm.")]):
    print(chunk.content, end="", flush=True)

POST /v1/chat/completions

Creates a model completion for the chat message history. Supports both standard JSON payloads and real-time SSE chunk streams. Also accessible via alias POST /chat/completions.

Request Body

Parameter	Type	Required	Description
`messages`	array	Optional	List of message objects: `[{"role": "user"\|"system"\|"assistant", "content": "..."}]`.
`model`	string	Optional	Model identifier. Defaults to `"gpt-4o"`.
`stream`	boolean	Optional	If set to `true`, partial message deltas will be sent as Server-Sent Events. Defaults to `false`.
`prompt`	string	Optional	Direct prompt string (alternative to message arrays).

Request Example

{
  "model": "gpt-4o",
  "messages": [
    {"role": "system", "content": "You are an expert tutor."},
    {"role": "user", "content": "Explain binary search."}
  ],
  "stream": false
}

Response (200 OK — JSON Mode)

{
  "id": "chatcmpl-3a9f0e1b2c4d5e6f7a8b9c0d",
  "object": "chat.completion",
  "created": 1724370000,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Binary search is an efficient algorithm for finding an item from a sorted list of items..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 64,
    "total_tokens": 76
  }
}

GET /

Returns the API service name, operational status, and endpoint directory for automated client discovery.

Response (200 OK)

{
  "service": "Free API",
  "status": "online",
  "openai_compatible": true,
  "endpoints": {
    "openai_chat": "POST /v1/chat/completions",
    "chat": "POST /api/chat",
    "stream": "POST /api/chat/stream",
    "status": "GET /api/status",
    "docs": "GET /docs",
    "playground": "GET /playground"
  }
}

GET /api/status

Retrieves the browser worker health status.

Response Schema

Field	Type	Description
`status`	string	Health state of the server (e.g. `"healthy"`).

Response Example

{
  "status": "healthy"
}

POST /api/chat

Executes an AI generation task. Returns the complete response object. If stream: true is specified, seamlessly delegates to the SSE streaming pipe.

Request Body

Parameter	Type	Required	Description
`prompt`	string	Optional	The question or prompt to send. If omitted, a question is selected randomly from the problem pool.
`stream`	boolean	Optional	When `true`, delivers tokens via SSE stream. Defaults to `false`.

Response (200 OK — JSON Mode)

{
  "id": "msg_1787403401",
  "timestamp": "2026-08-23 00:30:15",
  "user_prompt": "Design an algorithm to find the median of two sorted arrays.",
  "ai_response": "To find the median in O(log(min(n,m))) time, we perform a binary search on the partition..."
}

Test Endpoint: POST /api/chat

Stream SSE tokens (stream: true)

Response

POST /api/chat/stream

Dedicated SSE streaming endpoint emitting chunks with mime-type text/event-stream. Each chunk provides the newly generated text delta, cumulative output, and completion status.

Wire Format Example

data: {"delta": "Binary ", "full_text": "Binary ", "done": false}

data: {"delta": "search works ", "full_text": "Binary search works ", "done": false}

data: {"delta": "by halving the interval.", "full_text": "Binary search works by halving the interval.", "done": false}

data: {"delta": "", "full_text": "...", "done": true, "id": "msg_1787403402"}

data: [DONE]

SSE Streaming Protocol

The server sends Server-Sent Events with standard data: line prefixes, terminating with data: [DONE].

Event Stage	JSON Payload	Behavior
OpenAI Delta Chunk	`{"object": "chat.completion.chunk", "choices": [{"delta": {"content": "..."}}]}`	Emitted per token when using `/v1/chat/completions` with `stream=true`.
Native Stream Chunk	`{"delta": "...", "full_text": "...", "done": false}`	Emitted by `/api/chat/stream` and `/api/chat`.
Native Done Chunk	`{"done": true, "id": "...", "full_text": "..."}`	Sent upon generation completion with final status and message ID.
Termination	`data: [DONE]`	Signals the client to close the SSE connection.

Error Codes & Handling

Standard HTTP status codes are used to communicate success or error states:

Status Code	Condition	Example Body
200 OK	Request processed successfully.	`{"status": "healthy", ...}`
422 Unprocessable	Request body failed schema validation.	`{"detail": [{"loc": ["body", "stream"], "msg": "value is not a valid boolean"}]}`
500 Server Error	Browser worker or session failure.	`{"detail": "Failed to retrieve AI response."}`