Essential AI: Rnj 1 Instruct
essentialai/rnj-1-instruct
Access Rnj 1 Instruct from Essential AI using 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: "essentialai/rnj-1-instruct"
}).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: "essentialai/rnj-1-instruct"
}).then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="essentialai/rnj-1-instruct",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "essentialai/rnj-1-instruct",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
Model Card
Rnj-1 Instruct is an 8B-parameter instruction-tuned model built by Essential AI, trained from scratch and optimized for code, STEM reasoning, and agentic workflows. It offers a 32K context window and is released under Apache 2.0.
The model punches well above its weight class in agentic coding, scoring 20.8% on SWE-bench Verified — surpassing Gemini 2.0 Flash and Qwen2.5-Coder 32B Instruct under the same framework. It also posts strong marks across code generation (83.5% HumanEval+, 57.1% BigCodeBench) and function calling (62.2% BFCL v3).
Math and science capabilities are equally competitive: 92.6% on GSM8K, 43.3% on AIME '25, and solid results on GPQA-Diamond. Its post-training was deliberately kept minimal, making it a strong base for further fine-tuning. A great fit for developers building coding agents, tool-use pipelines, or STEM-focused applications on a budget.
Context Window 33K
tokens
Max Output N/A
tokens
Input Cost $0.15
per million tokens
Output Cost $0.15
per million tokens
Release Date Apr 7, 2025
Model Playground
Try Rnj 1 Instruct instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.
Frequently Asked Questions
You can access Rnj 1 Instruct by Essential 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.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Rnj 1 Instruct to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.15 |
| Output | $0.15 |
Rnj 1 Instruct was created by Essential AI and released on Apr 7, 2025.
Rnj 1 Instruct supports a context window of 33K tokens. For reference, that is roughly equivalent to 66 pages of text.
Yes — the Rnj 1 Instruct 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.
Get started with Puter.js
Add Rnj 1 Instruct to your app without worrying about API keys or setup.
Read the Docs View Tutorials