Introducing the Reeva AI Models API: unlimited tokens, one flat price
By Reeva Team · October 2, 2026 · Updated October 15, 2026
Today we’re launching something new: the Reeva AI Models API. It gives your apps, scripts and tools three AI models through one OpenAI-compatible API, with unlimited tokens at a flat monthly price.
It is a product of its own, on its own subscription. You don’t need a Reeva mail account to use it, and buying it gets you the API and nothing else.
Three models, one endpoint
Every plan includes all three models. You switch between them by changing the model name in your request.
- DeepSeek v4.1 (
deepseek-v4.1-flash): a fast general-purpose model for chat, summaries, drafting, translation, code, agents, and pulling data out of documents and emails. It takes the full request size your plan allows, so long documents and large codebases belong here. - Qwen-Image (
qwen-image): image generation and editing, on the standard/v1/images/generationsand/v1/images/editspaths. - Qwen 3.6 (
qwen3.6-35b-a3b): a smaller model for light, quick tasks such as short replies, rewording and translation. It takes up to 32k tokens per request, prompt and answer together.
Chat requests go to /v1/chat/completions, the same path the OpenAI API uses. A tool that
already works with OpenAI works with Reeva once you change the base URL and the API key.
What “unlimited tokens” means
There is no monthly token cap and no per-token billing. You pay one flat price a month, and the bill doesn’t change with how many tokens you use.
What a plan does set is pace: a limit on requests per minute, a limit on requests running at once and a maximum size for a single request.
Fair use: heavy use slows your requests down, image generation included. Only extreme use sustained over a full day is paused until it eases.
Plans
| Mini | Starter | Pro | Scale | |
|---|---|---|---|---|
| Price | $5 / month | $29 / month | $59 / month | $119 / month |
| Tokens | Unlimited | Unlimited | Unlimited | Unlimited |
| Requests per minute | 5 | 20 | 60 | 120 |
| Requests at once | 1 | 2 | 4 | 8 |
| Largest single request | 32k tokens | 128k tokens | 128k tokens | 256k tokens |
Qwen 3.6 has its own, smaller request limit on every plan: 32k tokens, prompt and answer together.
Prices are in USD, billed monthly through PayPal. There is no commitment: cancel any time in the control panel, and your key keeps working until the end of the period you’ve paid for.
Need more than Scale? The Enterprise option offers a dedicated instance, custom rate limits and contractual privacy terms. Talk to us.
A key for every tool
Your first API key is issued as soon as your PayPal payment clears. In the control panel you can create up to 10 keys, give each one a name and an optional expiry date, and revoke any of them on its own.
Give your code editor one key, your website another and your scripts a third. If one of them leaks, revoke that key and the others keep working.
What you can do with it
- Turn a long email thread into a few bullets and a next step.
- Draft replies to customers in your tone, for you to approve and send.
- Turn invoices, quotes and forms into clean JSON for your software.
- Write, review and complete code in opencode, Cline, Continue and Aider.
- Generate banners and campaign images.
- Translate between languages, in a marketing or formal tone.
Get started
Choose a plan, create a key and paste it into your tool. It takes a few minutes, and our setup guide walks through Python, Node.js, curl and the coding tools. All the details are on the AI Models API page.