The Lowest-Cost AI Cloud

// Serverless inference · OpenAI-compatible · pay per token.

OpenAI-compatible /v1/chat/completions. Bring your existing SDK, point at our base URL, ship.

openai-python v1

from openai import OpenAI

client = OpenAI(
  base_url="https://cloud.mixerbox.com/v1",
  api_key="sk-mb-…",
)

resp = client.chat.completions.create(
  model="kimi-k2.5",
  messages=[{"role": "user", "content": "hi"}],
)

Swap the base URL — that's the whole integration.

Models on one API

MoonshotAI Minimax Z.AI Alibaba Nvidia Google OpenAI

Built for builders

A drop-in OpenAI-compatible endpoint priced for shipping. Pay per token, never per seat.

◆

Lowest cost

Per-token pricing posted publicly on /models. The price you see is the price you pay — no per-seat fees, no subscription.

◇

Unified API

OpenAI-compatible /v1/chat/completions. Swap your base URL, pick a model. No SDK rewrite.

▶

Pay-as-you-go

Top up your balance once. Pay per token. No subscription, no per-seat fee, no minimum commitment.

◈

Auto top-up

Save a card and we'll auto-charge when your balance falls below a threshold you set. Set it once, never run out mid-request.

⊕

Stream-first

SSE streaming on every model. Same protocol, no special casing.

⊳

Single key, every model

One API key works across every model we serve. No per-model key juggling, no integration rewrites when you switch.

Three lines, ship it

Point your existing OpenAI client at us. Nothing else changes.

/docs → full API reference

curl https://cloud.mixerbox.com/v1/chat/completions \
  -H "Authorization: Bearer sk-mb-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-5.2",
    "messages": [{"role":"user","content":"Hello"}],
    "stream": true
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://cloud.mixerbox.com/v1",
    api_key="sk-mb-...",
)

stream = client.chat.completions.create(
    model="gpt-5.2",
    messages=[{"role":"user","content":"Hello"}],
    stream=True,
)
for chunk in stream:
    print(chunk.choices[0].delta.content, end="")

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://cloud.mixerbox.com/v1",
  apiKey: process.env.MB_CLOUD_KEY,
});

const stream = await client.chat.completions.create({
  model: "gpt-5.2",
  messages: [{ role: "user", content: "Hello" }],
  stream: true,
});
for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0].delta.content ?? "");
}

Use models, pay per token.

No subscription, no per-seat fee, no surprises. Billed per token. Top up from $5, anytime.

See pricing breakdown →

Frequently asked

Is this OpenAI-compatible? +

Yes. /v1/chat/completions — exact same shape as the OpenAI API. Most clients work by changing only the base URL.

Can I see prices before I sign up? +

Yes. Per-token rates for every model are listed on the /models page. The price you see is the price you pay — no per-seat fees.

Can I get a refund? +

Credit purchases are generally final. We may grant refunds case-by-case at our discretion or where required by law. See our Terms of Service for details.

Do you log my prompts? +

We log request metadata (model, token count, latency) for billing. Prompt and response content is handled only as needed to deliver your request, and is not used to train AI models.