Upstage AI: Solar Pro 3
upstage/solar-pro-3
Access Solar Pro 3 from Upstage AI using the Puter.js AI API.
Get Started// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms", {
model: "upstage/solar-pro-3"
}).then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms", {
model: "upstage/solar-pro-3"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
Model Card
Solar Pro 3 is a Mixture-of-Experts large language model from Upstage, featuring 102B total parameters with only 12B active per forward pass and a 128K token context window.
The model is built for agentic workflows and complex reasoning, trained using Upstage's proprietary SnapPO reinforcement learning framework. It scores 72.3 on Tau2-all (the comprehensive agentic evaluation), roughly doubling its predecessor's 36.0. It also claims 100% schema compliance for structured output generation.
Solar Pro 3 is particularly strong in Korean, with robust English and Japanese support — making it a standout choice for multilingual teams operating in East Asian markets. It targets enterprise use cases in domains like finance, healthcare, and legal, where reliable instruction following and structured outputs matter most.
Context Window 131K
tokens
Max Output 131K
tokens
Input Cost $0.15
per million tokens
Output Cost $0.6
per million tokens
Release Date Jan 27, 2026
Output Speed 148
tokens / sec
Latency 1.09s
time to first token
Model Playground
Try Solar Pro 3 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Benchmarks
How Solar Pro 3 performs on standard evaluations.
| Benchmark | Score |
|---|---|
| GPQA Diamond Graduate-level science Q&A | 72.4% |
| Humanity's Last Exam Cross-domain reasoning | 10.3% |
| SciCode Scientific programming | 25.5% |
| IFBench Instruction following | 71.2% |
| LCR Long-context reasoning | 32.3% |
| Terminal-Bench Hard Agentic terminal tasks | 7.6% |
| τ²-Bench Tool use / agents | 86.3% |
Scores sourced from Artificial Analysis.
Frequently Asked Questions
You can access Solar Pro 3 by Upstage AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Solar Pro 3 is free to integrate using the Puter.js AI API. With the User-Pays Model, you can add AI to your app for $0, since users cover their own AI usage through their Puter account.
| Price per 1M tokens | |
|---|---|
| Input | $0.15 |
| Output | $0.6 |
Solar Pro 3 was created by Upstage AI and released on Jan 27, 2026.
Solar Pro 3 supports a context window of 131K tokens. For reference, that is roughly equivalent to 262 pages of text.
Solar Pro 3 can generate up to 131K tokens in a single response.
Solar Pro 3 scores 7.8 on the Artificial Analysis Intelligence Index, outperforming 32% of tracked models. On coding, it scores 16.2 (outperforms 17% of models).
Yes — the Solar Pro 3 API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Add Solar Pro 3 to your app for free
Developers can integrate Solar Pro 3 for free using the Puter.js AI API.
With the User-Pays Model, each user covers their own AI usage instead of the developer.