OpenAI-compatible inference · now in invite-only beta

Private GPU instances,
one API away.

Rent a dedicated instance of any open-weights model — Llama, Qwen, Gemma, DeepSeek and more — behind a single OpenAI-compatible endpoint. Billed per running minute, with keys you control.

chat.py
# pip install openai
from openai import OpenAI

client = OpenAI(
  base_url="https://api.flexier.io/v1",
  api_key="sk-ac-live-…",
)

stream = client.chat.completions.create(
  model="qwen3-8b",
  messages=[{"role": "user", "content": "Ship it."}],
  stream=True,
)
Model catalog

Eight families. One endpoint.

~62 models — from a small model you can stream in real time to 8×-GPU giants — plus embeddings. Rent one as a private instance and address it by name.

Llama

3.1 / 3.3 · 1B → 405B

Qwen

3 · 0.6B → 235B MoE

Gemma

3 · 1B → 27B IT

DeepSeek

V3 · R1 · distills

Kimi

K2 · Moonshot · 8× GPU

Hunyuan

Tencent · 7B → Large

GLM

Zhipu · 9B → 32B

MiniMax

M2.7 · 8× GPU

Embeddings

Qwen3 · Gemma · GTE

A control plane built for developers.

Everything you need to run production inference — and nothing you don’t.

Private per-minute instances

Rent a dedicated GPU instance of any catalog model. Metered per running minute — provisioning is free, and a stopped instance costs nothing.

Load-balancing groups

Put several of your same-model instances behind one name; the gateway balances requests across the least-loaded ready replica.

Drop-in OpenAI API

Point the OpenAI SDK at one /v1 base URL. Chat completions, streaming and embeddings — no code rewrite.

Built-in chat playground

Prompt any running instance or group straight from the console — pick a target, stream a reply, no keys or curl.

Org-scoped keys

Issue keys per organization with per-key rate limits, scope them to specific instances or groups, and revoke instantly.

Per-minute cost visibility

A billing-grade runtime ledger with per-instance and daily breakdowns — see exactly what you spend, down to the minute.

62
Models in the catalog
8
Open-weights families
/v1
OpenAI-compatible
per-min
Billed while running

Have an invite code?

Create your organization, mint a key, and make your first call in under two minutes.