Worried about surprise charges on a tight budget?

Spending stays capped. AI Services will draw on your prepaid {brand} balance, so spending is capped by what you top up. Per-key limits and budget alerts are planned.

How quick are the responses for live work?

Measure it yourself. The list includes fast "Flash" models for code completion, live translation and agent loops. Early access lets you test latency on your own workload before you commit.

What happens to my prompts and outputs?

We do not train on them. {brand} does not use your prompts or outputs to train models and does not sell them. Upstream retention terms will be published before general availability; a zero-retention option is planned.

Want to run your workloads on your own server?

Use a {brand} cloud server. Create a {brand} cloud server, install your app or agent and call the API with your key. A server image with the runtime preinstalled is on our roadmap.

Cloudj AI Model Services, Slash Your Bill by 80%+ Today

High–Value — Open–Source Model APIs for Every Workload.

Get API Key See pricing

Why Pay Closed-Model Prices for Every Task?

Leading open-source models are strong enough , and handle most of the work your team sends them. At 1/{n} the cost or less.

Game Prototype

Prototype a two-player Snake game

Large Refactor

Port and clean up a large codebase

Bulk Translation

Translate 100 research papers into English

Image Tasks

Write alt text and descriptions for 1,000 product photos

Ticket Triage

Tag 1,000 support tickets and draft replies

Examples: same token volume for both sides × official list price per 1M tokens of the models named (checked 2026-10-29). Newer closed models may cost less; batch discounts are not included.

Start Saving Today

Run Open-Source Here — Save Up To

API Price Comparison

Input Price: Billing Unit: 1M Tokens
Cache Hit: Billing Unit: 1M Tokens
Output Price: Billing Unit: 1M Tokens

Billing Type Same Open Models — at a Lower Price.

Other providers: official price pages checked 2026-10-29 (select a name to open the source). Peak = peak-hour list price; DeepSeek and Alibaba Cloud charge 50% less off-peak, below Cloudj prices at those hours. — = no published cache price. Alibaba Cloud and Tencent Cloud: Singapore region. Product names are trademarks of their owners; Cloudj is not affiliated with them.

Judge Each Model Yourself. Request a Key and Compare.

Benchmarks are a starting point. Your own results matter more. Early-access customers get an API key for the models listed here. Try chat, code, reasoning, long context and images yourself.