Pearl Research Labs

Pearl Research Labs: Gemma 4 31B IT (Pearl)

pearl-ai/gemma-4-31b-it

Access Gemma 4 31B IT (Pearl) from Pearl Research 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: "pearl-ai/gemma-4-31b-it"
}).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: "pearl-ai/gemma-4-31b-it"
        }).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="pearl-ai/gemma-4-31b-it",
    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": "pearl-ai/gemma-4-31b-it",
    "messages": [
      {"role": "user", "content": "Explain quantum computing in simple terms"}
    ]
  }'

Model Card

Pearl-ai Gemma-4-31B-it-pearl is an instruction-tuned model from Google's open-weight Gemma 4 family, served by Pearl Research Labs through Together AI's inference platform.

Gemma 4 31B IT is a dense ~31B-parameter model from Google DeepMind, released under the Apache 2.0 license. It is built for reasoning, coding, and agentic workflows, supports native function calling and structured output, and handles 140+ languages.

This Pearl endpoint offers the model at a reduced price, with savings tied to Pearl Research Labs' proof-of-useful-work approach to inference economics.

Choose it if you want a capable, openly licensed mid-size instruction model with tool-calling support and lower per-token cost, suitable for general assistants, coding helpers, and multilingual tasks.

Context Window 32K

tokens

Max Output 32K

tokens

Input Cost $0.28

per million tokens

Output Cost $0.86

per million tokens

Input text

modalities

Tool Use Yes

 

Release Date Apr 2026

 

Model Playground

Try Gemma 4 31B IT (Pearl) instantly in your browser.
This playground uses the Puter.js AI API — no API keys or setup required.

Chat pearl-ai/gemma-4-31b-it
Pearl Research Labs
Chat with Gemma 4 31B IT (Pearl)
Powered by Puter.js

Frequently Asked Questions

How do I use Gemma 4 31B IT (Pearl)?

You can access Gemma 4 31B IT (Pearl) by Pearl Research 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 Gemma 4 31B IT (Pearl) free?

Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Gemma 4 31B IT (Pearl) 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 Gemma 4 31B IT (Pearl)?
Gemma 4 31B IT (Pearl) costs $0.28 per 1M input tokens and $0.86 per 1M output tokens.
Price per 1M tokens
Input$0.28
Output$0.86
Who created Gemma 4 31B IT (Pearl)?

Gemma 4 31B IT (Pearl) was created by Pearl Research Labs and released on Apr 2026.

What is the context window of Gemma 4 31B IT (Pearl)?

Gemma 4 31B IT (Pearl) supports a context window of 32K tokens. For reference, that is roughly equivalent to 64 pages of text.

What is the max output length of Gemma 4 31B IT (Pearl)?

Gemma 4 31B IT (Pearl) can generate up to 32K tokens in a single response.

What types of input can Gemma 4 31B IT (Pearl) process?

Gemma 4 31B IT (Pearl) accepts the following input types: text. It produces: text.

Does Gemma 4 31B IT (Pearl) support tool use (function calling)?

Yes, Gemma 4 31B IT (Pearl) supports tool use (function calling), allowing it to interact with external tools, APIs, and data sources as part of its response flow.

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

Yes — the Gemma 4 31B IT (Pearl) 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 Gemma 4 31B IT (Pearl) to your app without worrying about API keys or setup.

Read the Docs View Tutorials