Serve Llama, Gemma, Qwen, DeepSeek and Kimi through a single OpenAI-compatible endpoint. Serverless GPUs, token-accurate billing, keys you control.
# pip install openai from openai import OpenAI client = OpenAI( base_url="https://api.aicloud.dev/v1", api_key="sk-ac-live-…", ) stream = client.chat.completions.create( model="llama-3.1-8b-instruct", messages=[{"role": "user", "content": "Ship it."}], stream=True, )
From an 8B you can stream in real time to 8×-GPU giants that scale from zero — pick a slug and go.
3.1 8B · 3.3 70B
3 27B IT
3 32B · Embeddings
V3 · scale-from-zero
K2 · 8× GPU giant
Qwen3-Embedding
Everything you need to run production inference — and nothing you don’t.
Point the OpenAI SDK at one base URL. Chat, streaming and embeddings — no code rewrite.
Autoscaling replicas on datacenter-grade hardware. Giants cold-start from zero on demand.
Every prompt and completion token counted, with per-model and daily breakdowns.
Issue and revoke keys per organization, with per-key rate limits. Revocation is instant.
Sessions handled by Ory Kratos. Prompts are never persisted on GPU workers.
Time-to-first-token under 2s on small models. SSE relayed verbatim, no buffering.
Create your organization, mint a key, and make your first call in under two minutes.