Launch offer — every new account starts with 500,000 quota ($1) — up to 9M+ tokens. No card needed. Claim it →
500,000 free quota at sign-up ($1) · up to 9M+ tokens · no card required

One API key.
Every open model.

Qwen, DeepSeek, GLM, Kimi and more open-weight models behind one OpenAI-compatible endpoint. Start with 500,000 free quota ($1) — up to 9M+ tokens — then pay only for what you use. No subscription.

OpenAI-compatible Anthropic-compatible (Claude Code ready) Pay-as-you-go, from $0.10 / 1M tokens Card top-up, no wallet needed 500,000 quota free ($1) — up to 9M+ tokens
your first call — works with curl, Python, JS, Cursor, Cline…
curl https://api.novatoken.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-…your NovaToken key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Models & pricing

Straightforward per-token pricing

Q

Qwen

Alibaba's flagship open model — fast, cheap, great for everyday tasks and agents.
In $0.10/M Out $0.30/M
D

DeepSeek

DeepSeek V3.2 — top-tier reasoning and coding, with ultra-cheap cache hits.
In $0.30/M Out $1.20/M Cache hit $0.006/M
G

GLM

Zhipu GLM series — strong bilingual (EN/CN) chat and tool-calling performance.
In $0.15/M Out $0.50/M
K

Kimi

Moonshot Kimi — long-context specialist for documents and research workflows.
In $1.20/M Out $5.00/M

Not sure which to pick? Set model: "auto" and NovaToken routes each request to the best-capable, cheapest model that fits — you're billed at that model's actual rate.

Why NovaToken

Built for developers who just want it to work

Pay as you go

$5 one-off pack or monthly plans. No subscription lock-in — unused balance never expires.

Auto routing

One auto model picks the right engine per request, and you pay the real per-token rate of whichever model answers.

Drop-in compatible

OpenAI protocol out of the box, plus an Anthropic-compatible endpoint for Claude Code. Works with LangChain, LlamaIndex, n8n, curl.

Transparent billing

A live usage dashboard shows every call, every token, every cent — in your console, no support ticket needed.

Plans

Start with $5. Upgrade when it clicks.

🎁
Start free — 500,000 quota ($1), up to 9M+ tokens Credited automatically the moment you sign up. No card, no commitment, no expiry.
Claim free credit →

$5 credits

Try it out · side projects
$5 one-time
  • ≈ 50M input tokens on Qwen2.5-7B
  • ≈ 16M input tokens on DeepSeek-V4-Flash
  • No expiry, no monthly fee
Buy $5
Most popular

$20 credits

Regular use · small products
$20 one-time
  • ≈ 200M input tokens on Qwen2.5-7B
  • ≈ 66M input tokens on DeepSeek-V4-Flash
  • Priority support by email
Buy $20

$50 credits

Teams · high volume
$50 one-time
  • ≈ 500M input tokens on Qwen2.5-7B
  • ≈ 166M input tokens on DeepSeek-V4-Flash
  • Best value per token
Buy $50

Or go monthly

One flat price, credits auto-refill on your billing date, cancel anytime.

Most popular

Pro

$9.90 / month
  • 1,000 credits every month (≈ $10 of usage)
  • Auto-refills on your billing date
  • All models + auto routing
  • Usage analytics dashboard
Choose Pro

Max

$29.90 / month
  • 4,000 credits every month (≈ $40 of usage)
  • Auto-refills on your billing date
  • Priority routing capacity
  • Email support
Choose Max

Launch promo: first month 50% off with code PRODUCTHUNT · free tokens credited automatically at sign-up

* $1.00 starting credit, billed at real usage rates (70% input / 30% output mix): up to ≈9M+ tokens on DeepSeek (even more with cache discounts) · 7.5M on Qwen · 3.9M on GLM · 330k on Kimi. Unused credit never expires.

Works everywhere

Plug it into the tools you already use

Cursor Claude Code Cline / Roo / Kilo Continue Open WebUI LibreChat LobeChat Cherry Studio SillyTavern LangChain LlamaIndex n8n
Copy-paste configs for all 12 tools →

Your first call is 60 seconds away

Sign up, claim 500,000 free quota ($1), create a key, change one line of base URL. That's the whole migration.

Create your API key →