QFOXAI API Docs

Compatibility Tester

Before connecting a customer project, run a short backend check from your dashboard. It verifies health, model access, key status, and one small chat request without exposing your API secret.

Integration Paths

Pick the path closest to your product. QFOXAI keeps authentication, model aliases, quota headers, and errors consistent across all of them.

Developer Cookbook

These recipes help customers build real features quickly: support tools, CRM actions, billing assistants, search, safety, and batch jobs.

Go-Live Checklist

Use this before a customer project moves from testing to paid production traffic.

OpenAI-Compatible Client Settings

Authentication

QFOXAI accepts Bearer auth and the common OpenAI-compatible API key header modes used by third-party tools.

Endpoints

Use /v1 for new integrations. /api/v1 remains available for older clients.

Chat Completions

The request body follows the OpenAI chat-completions shape. An allowed public alias is honored exactly. When model is omitted, QFOXAI applies the API-key default, project default, smart routing, and finally the platform default. Private service identifiers are never accepted as public model names.

Vision And File Workflows

Use chat completions for image understanding, screenshots, product photos, scanned documents, and document/code text workflows. For images, send OpenAI-compatible image_url content parts. For PDFs, DOC files, spreadsheets, logs, or source code, extract the useful text in your app and send it as normal message content or chunks.

curl -X POST "https://qfoxai.com/v1/chat/completions" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI",
    "messages": [
      {
        "role": "user",
        "content": [
          {"type": "text", "text": "Explain this image for a product listing."},
          {"type": "image_url", "image_url": {"url": "data:image/png;base64,BASE64_IMAGE_HERE"}}
        ]
      }
    ],
    "max_tokens": 700
  }'

Image Generation

Create images from your application using the same QFOXAI API key and subscription limits. QFOXAI keeps private image infrastructure and routing details hidden; clients only use the public QFOXAI image label.

curl -X POST "https://qfoxai.com/v1/images/generations" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI Image",
    "prompt": "Premium launch campaign for a blue smart speaker",
    "n": 1,
    "quality": "hd",
    "aspect": "landscape",
    "mode": "product",
    "enhance_prompt": true,
    "design": {
      "brand": "NOVA AUDIO",
      "headline": "Sound, Reimagined",
      "subtitle": "Room-filling clarity in a compact design",
      "badge": "NEW",
      "cta": "Discover now",
      "layout": "split",
      "accent_color": "#2563EB"
    },
    "response_format": "b64_json"
  }'

Cost And Quota Estimate

Use the estimate endpoint before large requests, customer previews, background jobs, or image workflows. It returns estimated tokens, estimated cost, current quota context, and whether the request fits the active plan.

curl -X POST "https://qfoxai.com/v1/estimate" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI",
    "endpoint": "chat",
    "messages": [
      {"role": "user", "content": "Write a short support reply"}
    ],
    "max_tokens": 300
  }'

Embeddings

Use embeddings for search, matching, lightweight RAG, and document indexing. Requests use the same API key, subscription quota, and token accounting as other QFOXAI API calls.

curl -X POST "https://qfoxai.com/v1/embeddings" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI-Embeddings",
    "input": "QFOXAI provides AI chat and API access.",
    "dimensions": 384
  }'

Moderation

Use the moderation endpoint to pre-check prompts, form submissions, support messages, or user-generated content before sending it into a production workflow.

curl -X POST "https://qfoxai.com/v1/moderations" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI-Moderation",
    "input": "Text to review before publishing"
  }'

Examples

curl -X POST "https://qfoxai.com/v1/chat/completions" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI",
    "messages": [
      {"role": "user", "content": "Write a short support reply"}
    ],
    "temperature": 0.7,
    "max_tokens": 800
  }'

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.QFOXAI_API_KEY,
  baseURL: "https://qfoxai.com/v1"
});

const response = await client.chat.completions.create({
  model: "QFOXAI",
  messages: [{ role: "user", content: "Hello QFOXAI" }]
});

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

from openai import OpenAI

client = OpenAI(
    api_key="qf_your_key",
    base_url="https://qfoxai.com/v1"
)

response = client.chat.completions.create(
    model="QFOXAI",
    messages=[{"role": "user", "content": "Hello QFOXAI"}],
)

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

use Illuminate\Support\Facades\Http;

$response = Http::withToken(config('services.qfoxai.key'))
    ->acceptJson()
    ->post('https://qfoxai.com/v1/chat/completions', [
        'model' => 'QFOXAI',
        'messages' => [
            ['role' => 'user', 'content' => 'Hello QFOXAI'],
        ],
    ]);

$answer = $response->json('choices.0.message.content');

Streaming

Set stream to true. QFOXAI returns chat.completion.chunk events and ends with [DONE].

{
  "model": "QFOXAI",
  "stream": true,
  "messages": [
    {"role": "user", "content": "Stream a short answer"}
  ]
}

Batch API

Use batch jobs for non-live work such as summaries, product descriptions, drafts, and background customer tasks. Batch requests use the same authentication, public model aliases, quotas, and safety controls as chat completions.

curl -X POST "https://qfoxai.com/v1/batches" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "endpoint": "/v1/chat/completions",
    "completion_window": "24h",
    "requests": [
      {
        "custom_id": "job-1",
        "method": "POST",
        "url": "/v1/chat/completions",
        "body": {
          "model": "QFOXAI",
          "messages": [
            {"role": "user", "content": "Write a short welcome email"}
          ],
          "max_tokens": 300
        }
      }
    ]
  }'

curl "https://qfoxai.com/v1/batches/{batch_id}" \
  -H "Authorization: Bearer qf_your_key"

Limits, Usage, And Headers

curl "https://qfoxai.com/v1/key" \
  -H "Authorization: Bearer qf_your_key"

API Lifecycle Notices

QFOXAI keeps the public API version branded and stable. When a future behavior change needs client action, system can enable lifecycle notices without changing integration code.

Error Format

Errors return JSON with a stable error.type field so clients can show renew, upgrade, retry, or support actions.

{
  "error": {
    "message": "Invalid API key.",
    "type": "auth_error",
    "code": "auth_error",
    "param": null,
    "request_id": "req_...",
    "support_url": "https://qfoxai.com/docs/api",
    "details": {}
  }
}

Service Availability

If QFOXAI returns a temporary service error, the request was accepted but could not be completed at that moment. Retry shortly, reduce the request size, or contact support if it continues.

curl "https://qfoxai.com/v1/chat/completions" \
  -H "Authorization: Bearer qf_your_key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "QFOXAI",
    "messages": [{"role": "user", "content": "Say hello"}],
    "max_tokens": 120
  }'