Production endpoints for the best open models — DeepSeek, Llama, Qwen. One API, pay as you go.
from openai import OpenAI client = OpenAI( base_url="https://modelhaus.ai/v1", api_key="mh-...", ) resp = client.chat.completions.create( model="deepseek-v4-pro", messages=[{"role": "user", "content": "Explain MoE in one line."}], ) print(resp.choices[0].message.content)
Pick the right model per request — reasoning, code, chat, or embeddings. Prices are USD per 1M tokens.
Drop-in /v1 API. Keep your existing SDK — just change the base URL and key.
Open weights, neutral model names, standard formats. Migrate in or out in minutes.
Your prompts run on infrastructure we operate. No training on your data, ever.
You pay only for the tokens you use. No seats, no minimums, no surprise tiers.
Sign up, verify, create a key, and call the API in under a minute.
Top up with a card, watch your balance and usage in real time, never get a shock invoice.
Point any OpenAI SDK at https://modelhaus.ai/v1 with a key from your dashboard. That's it.
# curl curl https://modelhaus.ai/v1/chat/completions \ -H "Authorization: Bearer mh-..." \ -H "Content-Type: application/json" \ -d '{ "model": "llama-3.3-70b", "messages": [{"role":"user","content":"Hi!"}] }'
Prepaid credits via Stripe. No subscriptions, no minimums.
| Model | Best for | In / 1M | Out / 1M |
|---|---|---|---|
| DeepSeek-V4-Pro | Frontier reasoning | $2.00 | $4.00 |
| Llama 3.3 70B | Flagship chat | $0.60 | $0.90 |
| Qwen2.5 32B | Workhorse chat | $0.30 | $0.50 |
| DeepSeek-R1 | Step-by-step reasoning | $0.40 | $0.80 |
Create an account, grab a key, and start building on frontier open models in minutes.
Get your API key Browse the docs