OpenAI-compatible · API live

All your favorite open source LLMs.

Access 11 leading open source models — Qwen, GLM, DeepSeek, MiniMax, Kimi, Mistral, Llama and more — through a single base URL and a single key. No vendor lock-in. No surprise bills. Just plug in and build.

Base URL

https://transcribe.h0yx2rtus9gfkf.flashpanel.link/api/v1

Get an API key Explore Models

Access leading AI models of top labs in one place

OpenAI

Anthropic

DeepSeek

Grok

Qwen

Built for every workflow.

One key. Every frontier model. Whoever you are, you stop babysitting provider accounts and start shipping.

Get started free

Developers

One .env key. Swap models by editing a single string. No new SDKs, no new dashboards.

AI Agent builders

Route planning to a reasoning model, classification to a fast small one — same endpoint, same auth, zero glue code.

Startups

Prototype on free models, deploy on the best ones. Switch providers when the next frontier model drops — without touching your codebase.

Researchers

Run the same prompt across GPT-4o, Claude, Gemini, DeepSeek in one loop. Compare quality, latency, cost — from a single script.

Three lines. That's the whole change.

If your code already uses the OpenAI SDK, point it here. Nothing else moves.

from openai import OpenAI

client = OpenAI(
    base_url="https://transcribe.h0yx2rtus9gfkf.flashpanel.link/api/v1",
    api_key="YOUR_KEY",
)

resp = client.chat.completions.create(
    model="qwen/qwen3.6-flash",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://transcribe.h0yx2rtus9gfkf.flashpanel.link/api/v1",
  apiKey: process.env.KADEGATE_KEY,
});

const r = await client.chat.completions.create({
  model: "qwen/qwen3.6-flash",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(r.choices[0].message.content);

curl https://transcribe.h0yx2rtus9gfkf.flashpanel.link/api/v1/chat/completions \
  -H "Authorization: Bearer $KADEGATE_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.6-flash","messages":[{"role":"user","content":"Hello"}]}'

Built for production.

The boring infrastructure work, already finished.

OpenAI-compatible

Use the official SDK or curl. Change the base URL and the API key — that's it.

Real streaming

Server-sent events with the same data: frames and [DONE] sentinel.

Predictable pricing

Free for testing. Weekly plans for production. No metered tokens, no surprise bills.

Key management

Per-project keys. Rotate, revoke, audit — every request is logged.

∞

No token caps

Only request-rate limits per 5-hour window. Stream as much as your plan allows.

Honest analytics

Per-key usage, error rates, token counts and full request logs in your dashboard.

Why not just use providers directly?

Managing five provider accounts is a part-time job. Here's the honest comparison.

What you need	5 separate providers	Kadegate
API keys to manage	5 keys, 5 dashboards	1 key
Switch models	Rewrite SDK config	Change one string
Billing	Per-token, per provider	One flat plan
Streaming format	Different per provider	Identical SSE always
Usage logs	Scattered across portals	One dashboard, per-key
New model support	Update each integration	Instant, zero changes
Rate limit handling	Build your own fallback	Automatic failover

Your keys, your data

We never store request payloads. Keys are hashed at rest.

99.9% uptime SLA

Live status at /status. Automatic provider failover on errors.

Full request logs

Every request logged: model, tokens, latency, status code.

OpenAI SDK native

No custom client. The official SDK works unchanged, out of the box.

Start free. Scale when ready.

Three plans. Clear limits. Billed weekly. Cancel anytime.

Free

$0/wk

For testing and hobby projects.

All 11 models
50 requests / 5-hour window
API key included
Community support

Start free

Popular

Pro

$9/wk

For production applications.

1,000 requests / 5-hour window
Priority routing
Multiple private keys
Email support

Upgrade to Pro

Max

$19/wk

For high-volume production.

2,000 requests / 5-hour window
Priority routing
Unlimited API keys
Priority email support

Upgrade to Max