FAQ

AIPower is an OpenAI-compatible API gateway providing access to 16 AI models from 9 providers through one endpoint. Includes GPT-5, Claude, Gemini, and 10 Chinese AI models (DeepSeek, Qwen, GLM, Kimi, Doubao, MiniMax) — the only gateway with this breadth of Chinese AI.

Create an account at aipower.me (no credit card). You get 10 trial calls immediately. Use your API key with any OpenAI SDK by changing base_url to https://api.aipower.me/v1. Premium models unlock after a $5 top-up.

No — just use the standard openai Python/Node/Go SDK. Change two lines (base_url and api_key). That's it.

Yes. Visit aipower.me/try — 5 demo messages per day per IP, no registration. For more, create an account.

Pay-per-token for self-serve credits. Models range from $0.01/M tokens (GLM-4 Flash) to $50/M tokens (Claude Opus 4.6 output, CN tier). Optional Team and BYOK plans add monthly platform fees for shared budgets, provider keys, and priority support.

Credit card (USD via Stripe), WeChat Pay (CNY or HKD), and Alipay (CNY/USD/HKD). Minimum top-up is $5 or local equivalent. Larger top-ups ($50+) earn bonus credits up to +35%.

No. Your pre-paid credits never expire.

No subscription is required for normal API use. Pay-as-you-go credits never expire. Optional Team, BYOK, and Enterprise plans are available when you need shared budgets, BYOK, SSO, SLA, or procurement support.

Stack: Sign up (+10 trial calls) → First top-up $5+ (+100 bonus calls automatically added) → Refer a friend who tops up (+500 as referrer / +20 as referee). A $5+ top-up unlocks GPT, Claude, Gemini, Kimi, MiniMax, and premium reasoning models.

No. Adding a card is optional and does NOT unlock credits by itself (bot protection policy). Only completing a real top-up of $5+ grants the +100 bonus.

Billing is done by AI POWER LIMITED (Hong Kong). Commercial receipts are provided on payment. For mainland China companies needing fapiao or bulk pricing, contact Frank directly on WeChat +86 177 1736 5886 or email enterprise@aipower.me.

16 models: GPT-5, GPT-4o Mini, Claude Opus 4.6, Claude Sonnet 4, Gemini 2.5 Pro/Flash, DeepSeek V3/R1, Qwen Plus/Turbo, GLM-5.1, GLM-4 Flash, Kimi K2.5, Moonshot v1 8K, MiniMax Text 01, Doubao Pro 256K.

Use model="auto" and AIPower picks the best-fit model for your task, then logs the route for billing and debugging. Advanced route aliases include auto-code, auto-best, auto-fast, auto-cheap, and auto-free.

Yes. AIPower handles Chinese provider access for you — no +86 phone, no Chinese bank card needed. Just sign up with email.

Yes. AIPower is reachable from within China (via Cloudflare). Our servers handle the upstream connection to Anthropic/OpenAI/Google — your IP never connects to them directly.

Claude Sonnet 4 and GLM-5.1 are the strongest coding options. DeepSeek V3 is a good default for everyday coding tasks, while auto-code routes coding work to the model best suited for the request.

Use model="auto" first. For classification, extraction, filtering, and simple batch jobs, AIPower can route to utility models such as GLM-4 Flash or Doubao Pro while keeping the same API shape and usage logs.

Yes. Drop-in replacement. Python, Node.js, Go, curl — any OpenAI client works. Change base_url to https://api.aipower.me/v1 and use your AIPower key.

Yes. Server-Sent Events (SSE) streaming supported for all chat completion endpoints.

Yes — supported on models that support it (GPT-5, Claude Sonnet/Opus). Works with LangChain, Vercel AI SDK, and raw OpenAI SDK.

Trial accounts: 5 requests/minute. Paid accounts: 60 requests/minute default. Higher limits are available for Team and Enterprise plans — email enterprise@aipower.me.

Under 50ms routing overhead (Cloudflare edge). Total latency = our routing + upstream model latency. Typically 200-500ms from Asia, 100-300ms from US.

Yes. /v1/responses endpoint is supported alongside /v1/chat/completions.

Embeddings support is coming soon. For now, use chat completions for text understanding tasks, or email us for early access.

No. We don't store prompts or responses. We only log token counts for billing. All traffic is TLS-encrypted.

Keys are SHA-256 hashed in our database. Original key is shown only once at creation. Revoke/rotate at /dashboard/keys.

SOC 2 is in progress. Current controls: Stripe-level payment security, Cloudflare DDoS protection, no prompt logging, TLS everywhere. DPA available for enterprise.

Cloudflare Workers run at the edge closest to you. Upstream calls go to provider regions (OpenAI: US, Anthropic: US, DeepSeek/Qwen: China). We don't route through intermediaries.

可以。api.aipower.me 在 Cloudflare 上，国内直连，不需要翻墙。

支持。可以用微信支付或支付宝以 CNY 或 HKD 充值，最低 $5（约 ¥36）。

不会。您的 IP 只连接到我们的 Cloudflare 节点，不会直接接触 OpenAI/Anthropic。我们的上游账号是企业级账号，稳定性有保障。

企业客户可开 AI POWER LIMITED (香港公司) 的商业发票。联系 frank@aipower.me。

We focus on Chinese AI model access (10 models vs OpenRouter's few), smart routing (6 modes), WeChat Pay, and no-card trial calls. OpenRouter has broader model variety (300+ niche models). We're complementary — many devs use both.

Together AI focuses on open-source model hosting. AIPower is a unified gateway to proprietary and Chinese models. Use Together for custom Llama/Mistral deployments, AIPower for GPT+Claude+DeepSeek via one API.

OpenAI is one provider. AIPower gives one account for GPT, Claude, Gemini, DeepSeek, Qwen, GLM, Kimi, and Doubao, plus WeChat Pay / Alipay, usage logs, routing controls, and Team/BYOK options.

Yes. Enterprise pilots start at $299/mo and can include committed-use pricing, dedicated support, SSO, custom contracts, usage exports, and SLA options. See aipower.me/enterprise or email enterprise@aipower.me.

Yes for enterprise plans. Send a PO or signed agreement to enterprise@aipower.me.

Not currently. Our gateway runs on Cloudflare Workers. For air-gapped deployments, contact enterprise@aipower.me to discuss.

Yes — standard GDPR-compliant Data Processing Agreement available on request.