Sapiens AI API
Access Sapiens AI 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: "sapiens-ai/agnes-1.5-pro"
}).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: "sapiens-ai/agnes-1.5-pro"
}).then(response => {
console.log(response);
});
</script>
</body>
</html>
List of Sapiens AI Models
Agnes 1.5 Flash
sapiens-ai/agnes-1.5-flash
Agnes 1.5 Flash is a chat model from Sapiens AI, the Singapore-based lab behind the Agnes AI platform. It sits below Agnes 1.5 Pro in the same 1.5 series. It shares Agnes 1.5 Pro's 256K token context window but caps output at roughly 65K tokens, versus Pro's 256K. Pricing is $0.07 per million input tokens and $0.15 per million output tokens, well below Pro's $0.16 and $0.80. Sapiens AI has said the Agnes 1.5 series, evaluated on the PinchBench benchmark, performed competitively against models including Gemini 3.1 Pro, Qwen3.5, and Claude 4.5 Sonnet, though the task-by-task scores it published were specifically for the Pro variant. Agnes 1.5 Flash is aimed at high-volume, latency-sensitive chat and production workloads where per-token cost and response speed matter more than a large output budget.
ChatAgnes 1.5 Pro
sapiens-ai/agnes-1.5-pro
Agnes 1.5 Pro is a flagship chat model from Sapiens AI, positioned for demanding analysis, coding, and production agent workflows. It offers a 256K token context window and can generate up to 256K output tokens, several times the output ceiling of the smaller Agnes 1.5 Flash. Sapiens AI has reported PinchBench scores of 100% on writing tasks, 91% on comprehension, 89% on complex tasks, and 85% on synthesis tasks, and says the Agnes 1.5 series outperformed Gemini 3.1 Pro, Qwen3.5, and Claude 4.5 Sonnet across those dimensions. Pricing is $0.16 per million input tokens and $0.80 per million output tokens. Agnes 1.5 Pro fits workloads that need long-form reasoning or large output budgets, where the higher per-token cost is offset by needing fewer follow-up calls.
ChatAgnes 2.0 Flash
sapiens-ai/agnes-2.0-flash:free
Agnes 2.0 Flash is a chat model from Sapiens AI, built for high-frequency production use such as agent workflows, tool calling, coding, multi-turn conversations, reasoning, and image understanding. Sapiens AI reports a Pass^3 score of 60.9% on Claw-Eval, a benchmark for autonomous agents, placing Agnes 2.0 Flash among the top 10 models on the benchmark's general leaderboard alongside labs including Anthropic, OpenAI, and Google. The model supports tool calling, streaming responses, image URL inputs, and a thinking mode for harder requests. Agnes 2.0 Flash is offered at no cost for both input and output tokens, part of Sapiens AI's push to keep its models free indefinitely with no waitlist. That makes it worth trying for agentic or tool-using applications that need to run frequent API calls without per-token charges, though its 65.5K token output cap is smaller than Agnes 1.5 Pro's.
Frequently Asked Questions
The Sapiens AI API gives you access to models for AI chat. Through Puter.js, you can start using Sapiens AI models instantly with zero setup or configuration.
Puter.js supports a variety of Sapiens AI models, including Agnes 1.5 Flash, Agnes 1.5 Pro, and Agnes 2.0 Flash. 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 Sapiens AI 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.