Ship a Full-Stack App with One Prompt

Copy this prompt into your AI coding agent, or open it in one below.

Give this to your AI Create a to-do list app using Puter.js

Coding manually? see the guide

AI21 Labs

AI21 Labs: Jamba Large 1.7

ai21/jamba-large-1.7

Access Jamba Large 1.7 from AI21 Labs 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: "ai21/jamba-large-1.7"
}).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: "ai21/jamba-large-1.7"
        }).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="ai21/jamba-large-1.7",
    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": "ai21/jamba-large-1.7",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Jamba Large 1.7 is AI21 Labs' flagship open-weight language model, built on a hybrid SSM-Transformer (Mamba-Transformer) architecture with a Mixture of Experts design — 398B total parameters with 94B active during inference.

Its standout feature is a 256K-token context window, making it well suited for processing lengthy documents, contracts, and knowledge bases. The model supports function calling, JSON mode, and nine languages including English, Spanish, French, German, and Arabic.

Jamba Large 1.7 emphasizes grounding and instruction-following, delivering contextually faithful responses with strong steerability. It generates output at roughly 69 tokens per second via the AI21 API. It targets enterprise workflows in domains like finance, healthcare, and legal — where long-context accuracy and data control matter most.

Context Window 256K

tokens

Max Output 4K

tokens

Input Cost $2

per million tokens

Output Cost $8

per million tokens

Release Date Aug 8, 2025

 

Output Speed 58

tokens / sec

Latency 0.87s

time to first token

Model Playground

Try Jamba Large 1.7 instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat ai21/jamba-large-1.7
AI21 Labs
Chat with Jamba Large 1.7
Powered by Puter.js

Benchmarks

How Jamba Large 1.7 performs on standard evaluations.

Artificial Analysis
Intelligence Index
5.0
Better than 16% of tracked models
Artificial Analysis
Math Index
2.3
Better than 3% of tracked models
BenchmarkScore
GPQA Diamond Graduate-level science Q&A
39.0%
Humanity's Last Exam Cross-domain reasoning
3.7%
LiveCodeBench Recent coding problems
18.1%
SciCode Scientific programming
18.8%
MATH-500 Competition math
60.0%
AIME 2024 Advanced math exam
5.7%
AIME 2025 Advanced math exam
2.3%
IFBench Instruction following
35.2%
LCR Long-context reasoning
18.3%
Terminal-Bench Hard Agentic terminal tasks
2.3%
τ²-Bench Tool use / agents
13.5%

Scores sourced from Artificial Analysis.

Frequently Asked Questions

How do I use Jamba Large 1.7?

You can access Jamba Large 1.7 by AI21 Labs 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.

Is Jamba Large 1.7 free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Jamba Large 1.7 to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.

What is the pricing for Jamba Large 1.7?
Jamba Large 1.7 costs $2 per 1M input tokens and $8 per 1M output tokens.
Price per 1M tokens
Input$2
Output$8
Who created Jamba Large 1.7?

Jamba Large 1.7 was created by AI21 Labs and released on Aug 8, 2025.

What is the context window of Jamba Large 1.7?

Jamba Large 1.7 supports a context window of 256K tokens. For reference, that is roughly equivalent to 512 pages of text.

What is the max output length of Jamba Large 1.7?

Jamba Large 1.7 can generate up to 4K tokens in a single response.

How does Jamba Large 1.7 perform on benchmarks?

Jamba Large 1.7 scores 5.0 on the Artificial Analysis Intelligence Index, outperforming 16% of tracked models. On math, it scores 2.3 (outperforms 3% of models).

Does it work with React / Vue / Vanilla JS / Node / etc.?

Yes — the Jamba Large 1.7 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 Jamba Large 1.7 to your app without worrying about API keys or setup.

Read the Docs View Tutorials