Point your existing code at our endpoint and start calling Qwen models — same SDK, same tool-calling, no GPU to rent, no servers to run.
Get your API key See pricingPay only for what you use. Prices in USD per 1M tokens.
Need a specific model sooner? Email support@novatoken.dev
The boring things, done right.
Change one line — base_url and API key. Everything else in your stack stays untouched.
Real-time usage dashboard, per-request cost breakdown, no minimum spend, top up anytime.
Served behind Cloudflare with streaming SSE support. Low latency from most regions.
No prompt retention. No training on your data. We only keep billing metadata.
Create an account, grab a key, make your first call in under a minute.
Create free accountYes — chat completions, streaming (SSE), tool/function calling and JSON mode are supported. Set base_url to https://api.novatoken.dev/v1 and use your NovaToken key.
We self-host open-weight models on rented GPU capacity instead of reselling someone else's API. No sales team, no seat licences — the savings go into the price.
Free accounts get a small daily allowance for testing. Paid accounts scale with balance and usage. If you need a higher ceiling, email us.
No. We record timestamps and token counts for billing, and that metadata is purged on a rolling basis. Request bodies are not retained.
Major credit and debit cards worldwide, processed by our payment provider. You are charged in USD.
We run on serverless GPU capacity that scales on demand. If a request fails you are not billed for it. See the Refund Policy for credit refunds.