Apodex API
Access Apodex instantly with Puter.js, and add AI to any app in a few lines of code without backend or API keys.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain AI like I'm five!", {
model: "apodex/apodex-1.1"
}).then(response => {
console.log(response);
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain AI like I'm five!", {
model: "apodex/apodex-1.1"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Apodex Models
Apodex 1.1
apodex/apodex-1.1
Apodex 1.1 is an agentic AI model from Apodex, built for long-horizon professional work in law, finance, and scientific research. It pairs reasoning with task execution, working directly with files, code, and search tools rather than only generating text. The model uses two training approaches. Environment Scaling expands the diversity of executable file, search, and code environments. Agentic Coordination Scaling trains it to decompose long tasks, delegate parallel work to subagents, and integrate results. A runtime called AgentOS tracks tool calls, file state, and task progress across a session, and lets a user step in mid-task to redirect the work. On Apodex's own benchmarks, Apodex 1.1 with its Agent Team setup scored 38.5 on APEX-Agents, 78.8 on GDPVal, 54.3 on FrontierFinance, and 63.3 on FrontierScience-Research, more than double its predecessor's APEX-Agents score of 16.5. It has a 256K token context window and supports text, images, PDFs, and CSV/Excel input.
ChatApodex 1.1 Mini
apodex/apodex-1.1-mini
Apodex 1.1 Mini is a 35-billion-parameter open-weight model from Apodex, built for long-horizon agentic work such as research, financial analysis, and coding tasks that involve files, search, and code execution rather than single-turn chat. It is a mixture-of-experts model (Qwen3.5-35B-A3B architecture, Apache 2.0 license), the smaller open-weight sibling of the larger hosted Apodex 1.1, and supports a 256K-token context window with text and image input. The model supports native function calling, with tool schemas passed through the standard tools= parameter and results returned in OpenAI-compatible tool_calls format, so it can run in existing agent loops without custom parsing. On Apodex's own benchmarks, using its Agent Team multi-agent setup, Apodex 1.1 Mini scores 50.2 on FrontierFinance, 51.7 on FrontierScience-Research, and 27.7 on APEX-Agents, putting it in the range of larger models like Kimi K2.6 and DeepSeek V4 Flash on the same tests.
Frequently Asked Questions
The Apodex API gives you access to models for AI chat. Through Puter.js, you can start using Apodex models instantly with zero setup or configuration.
Puter.js supports a variety of Apodex models, including Apodex 1.1 and Apodex 1.1 Mini. Find all AI models supported by Puter.js in the AI model list.
With the User-Pays model, users cover their own AI costs through their Puter account. This means you can build apps without worrying about infrastructure expenses.
Puter.js is a JavaScript library that provides access to AI, storage, and other cloud services directly from a single API. It handles authentication, infrastructure, and scaling so you can focus on building your app.
Yes — the Apodex API through Puter.js works with any JavaScript framework, Node.js, or plain HTML. Just include the library and start building. See the documentation for more details.