QNP API Documentation

QNP is an OpenAI-compatible API proxy that gives you access to multiple LLM providers through a single endpoint. With configurable fallback: you define the provider chain per API key (primary → fallback₁ → fallback₂). When one fails, the next is tried automatically.

• Configurable fallback — set provider order per key (OpenAI → Anthropic → Groq, etc.)
• OpenAI SDK compatible — drop-in replacement, same base URL pattern
• BYOK or platform credits — use your own provider keys or QNP credits
• Supported providers — OpenAI, Anthropic, Google, Groq, DeepSeek, Mistral, Together, Perplexity, Cohere, and more
• Unified usage, billing, and monitoring

Production base URL: https://qnp.ai/api/api/v1

OpenAI-compatible clients (Cline, OpenAI SDK, etc.): https://qnp.ai/api/api/v1. Set the API key to your qnp- key and choose provider type OpenAI Compatible where applicable.

For chat, model names qnp, or qnp/auto resolve to the first model on your API key fallback chain when you have configured providers; otherwise QNP uses an intent-based default (Sage). Your fallback order still applies to the resolved model.

Quickstart Guide

curl -X POST "https://qnp.ai/api/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qnp/auto","messages":[{"role":"user","content":"Hello!"}]}'

Authentication

All API requests require authentication via your QNP API key. You can pass it in two ways:

Authorization: Bearer YOUR_KEY
# or
X-API-Key: YOUR_KEY

Key Management

• Keys are created in the Dashboard and start with qnp-
• Each key has its own provider chain (fallback order), model access, and rate limits
• Keys can be scoped with allowed IPs, referrers, and permissions (chat, embeddings, images)
• Rotate keys without downtime — the old key is revoked and a new one is generated
• Revoke keys instantly if compromised — they stop working immediately
• Free tier: up to 5 active keys. Pro tier: unlimited keys

Key Scoping

Each key can be configured with:

• Provider Chain — which providers to route requests to, in priority order
• Allowed IPs — restrict key usage to specific IP addresses
• Allowed Referrers — restrict key usage to specific domains
• Permissions — which endpoints the key can access (chat, embeddings, images)
• Budget — set spending limits per key
• Rate Limits — custom RPM/TPM limits per key

Fallback Configuration

Per API key, you define a provider chain: primary provider first, then fallbacks in order. If the primary fails (rate limit, outage, etc.), QNP automatically tries the next in the chain.

Configure fallback in the dashboard when creating or editing an API key: add providers, set priority, and choose models per step. No code changes needed.

With no fallback configured, the key uses platform mode: QNP credits and platform providers. Add your own provider keys (BYOK) to control costs.

Chat Completions

Use any model from your fallback chain. The model is resolved from your configured providers. Model format: provider/model-slug or just model-slug for auto-routing.

curl -X POST "https://qnp.ai/api/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qnp/auto","messages":[{"role":"user","content":"Hello!"}]}'

from openai import OpenAI

client = OpenAI(
    base_url="https://qnp.ai/api/api/v1",
    api_key="YOUR_KEY"
)

response = client.chat.completions.create(
    model="qnp/auto",  # routes to your fallback chain
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "qnp/auto", // routes to your fallback chain
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Embeddings

Create vector embeddings for text. OpenAI-compatible format.

curl -X POST "https://qnp.ai/api/api/v1/embeddings" \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"text-embedding-3-small","input":"The quick brown fox"}'

response = client.embeddings.create(
    model="text-embedding-3-small",
    input="The quick brown fox"
)
print(response.data[0].embedding[:5])

Images

Generate images via DALL-E or other supported providers. OpenAI images API format.

Models

List models available for your API key. Returns all models from your fallback chain (BYOK) or platform providers.

curl "https://qnp.ai/api/api/v1/models" \
  -H "Authorization: Bearer YOUR_KEY"

Streaming

QNP supports Server-Sent Events (SSE) streaming for chat completions. Set "stream": true in your request body. The response will be a stream of data: events in the OpenAI format.

Each SSE event contains a JSON chunk with delta content. The stream ends with data: [DONE].

curl -X POST "https://qnp.ai/api/api/v1/chat/completions" \
  -H "Authorization: Bearer YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qnp/auto","stream":true,"messages":[{"role":"user","content":"Hello!"}]}'

stream = client.chat.completions.create(
    model="qnp/auto",
    messages=[{"role": "user", "content": "Tell me a story"}],
    stream=True
)
for chunk in stream:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Model Catalog

QNP supports 9 providers. Use the model format provider/model-slug for explicit routing or just model-slug to use your fallback chain.

Pricing

Pricing follows the upstream provider — whatever the provider charges is what you pay. No markup. QNP charges for the platform subscription only.

For live per-model pricing and usage details, visit your Dashboard.

Rate Limits

Rate limits are enforced per API key and depend on your subscription tier:

Custom per-key rate limits (RPM, TPM) can be configured in the dashboard for Pro tier keys.

When rate limited, the API returns 429 Too Many Requests with a Retry-After header.

Error Codes

Errors follow OpenAI format: { error: { message, type, code } }

SDK Examples

Use any OpenAI-compatible SDK. Change baseURL and apiKey. Your fallback chain is configured in the dashboard — no SDK changes needed.

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://qnp.ai/api/api/v1",
    api_key="YOUR_KEY"
)

response = client.chat.completions.create(
    model="qnp/auto",  # routes to your fallback chain
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

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

const response = await client.chat.completions.create({
  model: "qnp/auto", // routes to your fallback chain
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

LangChain

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    base_url="https://qnp.ai/api/api/v1",
    api_key="YOUR_KEY",
    model="qnp/auto"  # routes to your fallback chain
)
response = llm.invoke("Hello!")
print(response.content)

Cline Setup

Cline is an AI-powered coding assistant. Use QNP as the provider for configurable fallback and unified API.

Steps

1. Open Cline settings (click the gear icon).
2. Set API Provider to OpenAI Compatible.
3. Base URL: https://qnp.ai/api/api/v1.
4. API Key: Your QNP key (starts with qnp-).
5. Model: Use qnp/auto to auto-resolve to your fallback chain.

Troubleshooting

• 400 invalid_request_error: Ensure your key has at least one provider in its fallback chain. Add Anthropic or OpenAI in Dashboard → Keys → Routing.
• Invalid API Key: Confirm the key starts with qnp- and is active.
• Base URL: Must end with /v1 (no trailing slash).

Setup Script

The setup script auto-detects and configures OpenClaw, Claude Code, and Hermes Agent. Use QNP as the model provider for unified fallback and BYOK.

The setup script will interactively prompt you for your API key and base URL.

curl -fsSL https://www.qnp.ai/setup.sh | bash

What the script does

• Detects installed tools (OpenClaw, Claude Code, Hermes Agent) and configures QNP as provider for each
• Sets input: ["text","image","audio","video"] for all models
• Creates a backup before changes