Guide · Updated November 2026

DeepSeek API without Alipay — pay with a normal credit card

If you live outside mainland China, the hardest part of using DeepSeek is not the model — it is the checkout page. The official platform expects a Chinese phone number, and top-ups run through Alipay or WeChat Pay. Here is the workaround that does not involve borrowing someone's account.

Short version: use an OpenAI-compatible gateway that bills in USD. Register with an email → pay with any credit or debit card → set base_url to https://api.novatoken.dev/v1. Same per-token list price, no Chinese identity required.

The three ways people try to pay for DeepSeek — and where each one breaks

RouteWhat it takesWhere it breaks
Official platformChinese phone number, real-name verification, Alipay / WeChat Pay top-upMost international cards are simply not an option; verification is impractical abroad
Borrowed account or virtual CN cardA friend's account, or a resold wallet/virtual cardAccount risk, recharge fees, and the same problem again next month
Card-billed gateway (NovaToken)Email + any credit or debit cardNothing recurring — one key, one balance, works for every model we serve

NovaToken is the third option: we run DeepSeek-class models on our own infrastructure and partner inference capacity, expose them through the standard OpenAI API shape, and bill in USD. Per-token pricing matches the official list price — we are not adding a per-request fee on top.

Set up in three steps

  1. Register with an email. No phone number, no ID. Create an account.
  2. Buy $5 of credits. Any major credit or debit card, charged in USD. Credits never expire.
  3. Change one line. Point base_url at https://api.novatoken.dev/v1 and use your new key.
# Python — the official openai SDK works unchanged
from openai import OpenAI

client = OpenAI(
    api_key="sk-your-novatoken-key",
    base_url="https://api.novatoken.dev/v1"
)

resp = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V4-Flash",
    messages=[{"role": "user", "content": "Summarise this contract in 5 bullets"}],
    stream=True
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")
# curl — no SDK needed
curl https://api.novatoken.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-your-key" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-ai/DeepSeek-V4-Flash","messages":[{"role":"user","content":"Hi"}]}'

What it costs

ModelBest forUSD / 1M tokens
DeepSeek-V4-FlashReasoning, 1M context, agents$0.30 in / $1.20 out
Qwen2.5-7B-InstructFast chat, classification, tool calling$0.10 in / $0.30 out
GLM-5.3-FlashBilingual work, summarisation$0.15 in / $0.50 out
Kimi-K2.7-CodeCode, tool-heavy agents (262K context)$1.20 in / $5.00 out

Cache hits on DeepSeek-V4-Flash are billed at $0.006 / 1M input instead of $0.30 — a 50× discount applied automatically when the upstream reports a cache hit. Long system prompts, agents and coding assistants hit this constantly.

Real-world math: 1M input + 300K output on DeepSeek-V4-Flash is about $0.66. A small side project that sends a few thousand requests a month typically lands between $2 and $5. There is no subscription and nothing expires.

FAQ

Is this the same model as the official DeepSeek API?

Yes — the same open-weight DeepSeek-V4 family, served on our infrastructure and partner capacity. Model names, context window, reasoning behaviour and streaming format are identical.

Can I still use my existing OpenAI code?

Yes. Change base_url and the key. Chat completions, streaming (SSE), tool/function calling and JSON mode all work.

Do you support Alipay or WeChat Pay too?

No — the whole point is that you don't need them. Payment is by card in USD, which is what makes the service usable for people outside mainland China.

Do you keep my prompts?

No. We store timestamps and token counts for billing only. Request bodies are not retained.

What if I only need $5 to test an idea?

That is exactly the starting point. $5 of credits is roughly 25M input tokens on DeepSeek-V4-Flash — enough to build and test something real before committing more.

Can I move to another model later without changing code?

Yes. Every model is behind the same key and endpoint; you change the model string. If you don't want to choose at all, send "model": "auto" and each request is routed to a suitable model at that model's own rate.

Start with $5 — call DeepSeek in the next minute

Card payment, USD, no Chinese phone number, credits never expire.

Buy $5 of credits