PPromptoll
Public beta · drop-in OpenAI replacement

Switch OpenAI to
Chinese frontier models,
cut AI spend 90%.

DeepSeek v3.1, Qwen Plus, GLM 4.6, Kimi K2 —— production-grade models the big Chinese labs use in their own products, at a fraction of GPT-4o's cost. One API. No Chinese entity required. Pay in USD.

one line change, 100× cheaper
from openai import OpenAI

client = OpenAI(
    base_url="https://promptoll.com/v1",
    api_key="zai_•••",
)

client.chat.completions.create(
    model="deepseek-v3.1",   # or "auto" — we pick the cheapest
    messages=[{"role": "user", "content": "Hello"}],
)

Production-grade models at wholesale prices

Same APIs, same quality tier. We handle the account setup, fapiao, and cross-border routing so you don't have to.

DeepSeek v3.1≈ gpt-4o · 1/36 price
Qwen Plus≈ gpt-4o-mini · 1/3 price
GLM 4.6coding specialist · cheap
Kimi K2200K context · cheap
Gemini 2.5 FlashGoogle · fast · cheap
DeepSeek R1o1-level reasoning · 1/100 price
Want GPT-5 / Claude Opus / Gemini Pro too? Same API — charged at standard rates. Perfect for quality-sensitive fallback.

Why this actually works

Chinese labs competed harder on price-performance. Your bill is the beneficiary.

🔌

Drop-in OpenAI replacement

Same SDK, same message format, same streaming semantics. Change one line and you're done.

Smart arbitrage routing

Send model="auto" and we route to the cheapest model that meets your quality bar. Opt in per-tenant.

📊

Token-accurate billing

Every request logs prompt/completion tokens at microcent precision. See cost, revenue, margin per request.

🔑

Per-key model binding

Issue scoped keys locked to a specific model. Sell fixed-price SKUs to your own customers.

🌍

No Chinese entity required

Sign up with an email, pay with USD via Stripe. We handle the rest on the provider side.

Global edge delivery

Routes via the lowest-latency path for your users — US, EU, APAC all covered.

Live in under 5 minutes

No contracts. No minimums. Point back to OpenAI any time.

01

Sign up

Email + password. $5 credit, enough for thousands of requests.

02

Mint an API key

Console → API Keys → Create. Optionally bind it to a specific model.

03

Swap base_url

Point your OpenAI SDK at promptoll.com/v1. Code stays the same.

04

Watch your bill drop

Every request shows cost / price / model used in the dashboard.

Transparent pricing

Cheaper than calling the provider direct.

We buy in bulk, pass most of the savings to you. Your bill is wholesale × 1.15 on Scale — still below any public rate card.

Rough per-1K-token cost (input)
model             $ / 1K input tokens
─────────────────────────────────────
gpt-4o            $0.00250   (baseline)
claude-sonnet-4-6 $0.00300
gpt-4.1-mini      $0.00040
─────────────────────────────────────
deepseek-v3.1     $0.00014   ← 18× cheaper
qwen-plus         $0.00040
glm-4.6           $0.00060
gemini-2.5-flash  $0.00015

Ship AI without the wallet bleed.

$5 free credit — no card required. Upgrade when you outgrow the free tier.