Access 14 leading open source models — Qwen, GLM, DeepSeek, MiniMax, Kimi, Mistral, Llama and more — through a single base URL and a single key.
https://kadegate.com/api/v1
One key. Every frontier model. Whoever you are, you stop babysitting provider accounts and start shipping.
Get started.env key. Swap models by editing a single string. No new SDKs, no new dashboards.If your code already uses the OpenAI SDK, point it here. Nothing else moves.
from openai import OpenAI client = OpenAI( base_url="https://kadegate.com/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://kadegate.com/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://kadegate.com/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"}]}'
The boring infrastructure work, already finished.
Use the official SDK or curl. Change the base URL and the API key — that's it.
Server-sent events with the same data: frames and [DONE] sentinel.
Credit-based, per-token pricing. Top up your balance and spend it across any model. No subscriptions.
Per-project keys. Rotate, revoke, audit — every request is logged.
Every new account gets free credits — no card required. Start building in seconds.
Per-key usage, error rates, token counts and full request logs in your dashboard.
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 | Separate bill per provider | One credit balance |
| 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 |
No subscriptions. Add credits, spend them across any model, priced per token.
Every new account gets $5 in credits — no card required. Then top up anytime.
Create your account| Model | Input / 1M | Output / 1M | Cache / 1M |
|---|---|---|---|
| google/gemma-4-26b-a4b-it | $0.06 | $0.33 | $0 |
| google/gemma-4-31b-it | $0.12 | $0.36 | $0 |
| meta-llama/llama-4-maverick | $0.15 | $0.6 | $0 |
| minimax/minimax-m2.7 | $0.27 | $1.08 | $0 |
| minimax/minimax-m3 | $0.3 | $1.3 | $0 |
| qwen/qwen3.5-plus-20260420 | $0.3 | $1.8 | $0 |
| xiaomi/mimo-v2-flash | $0.1 | $0.3 | $0 |
| z-ai/glm-4.7-flash | $0.06 | $0.4 | $0 |
| Anthropic: Claude Opus 4.6 | $5 | $25 | $0 |
| claude-opus-4-8 | $5 | $25 | $0.5 |
| claude-opus-4-7 | $5 | $25 | $0 |
| gpt-5.4-nano | $0.2 | $1.25 | $0 |
Prices in USD per 1,000,000 tokens. See all models →