Gemma-4-31B-it-Pearl

Reasoning with thinking mode at 25% discounted pricing

About model

Gemma 4 31B-it-Pearl is Pearl Research Labs' instruction-tuned checkpoint of Google's Gemma 4 31B, optimized for the Pearl Network's Proof of Useful Work protocol. It delivers capabilities similar tothe base Gemma 4 31B — text input, 256K context, function calling, JSON mode — at a 25%+ discount through Together AI's exclusive Pearl Network integration.

Learn more in our announcement blog.

Discounted Pricing

25%

Context Window

256K

With hybrid attention for long-context optimization

AIME 2026

89.20%

Mathematical reasoning without tools

Model key capabilities

25% Discounted Pricing: Powered by Pearl's Proof of Useful Work — mining rewards subsidize inference costs with zero impact on model quality or throughput
Configurable Thinking: Built-in reasoning mode for step-by-step problem solving with 85.35% GPQA Diamond
Native Function Calling: Structured tool use with JSON mode for agentic workflows

Performance benchmarks

Model	AIME 2025	GPQA Diamond	HLE	LiveCodeBench	MATH500	SWE-bench verified
Gemma-4-31B-it-Pearl	89.20%	85.35%	19.50%	80.00%
Related open-source models
Competitor closed-source models
Claude Opus 4.6		90.5%	34.2%			78.7%
OpenAI o3		83.3%	24.9%		99.2%	62.3%
OpenAI o1		76.8%			96.4%	48.9%
GPT-4o		49.2%	2.7%	32.3%	89.3%	31.0%

API usage

cURL
Python
Typescript

Endpoint:

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

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "pearl-ai/gemma-4-31b-it-pearl",
    "messages": [
      {
        "role": "user",
        "content": "What are some fun things to do in New York?"
      }
    ]
}'

from together import Together

client = Together()

response = client.chat.completions.create(
  model="pearl-ai/gemma-4-31b-it-pearl",
  messages=[
    {
      "role": "user",
      "content": "What are some fun things to do in New York?"
    }
  ]
)
print(response.choices[0].message.content)

import Together from 'together-ai';
const together = new Together();

const completion = await together.chat.completions.create({
  model: 'pearl-ai/gemma-4-31b-it-pearl',
  messages: [
    {
      role: 'user',
      content: 'What are some fun things to do in New York?'
     }
  ],
});

console.log(completion.choices[0].message.content);

Model card
Architecture Overview:
• 30.7B parameter dense transformer with hybrid attention (interleaved local sliding window + full global attention)
• 256K token context window with proportional RoPE for long-context optimization
• Configurable thinking mode for step-by-step reasoning before generating answers
• Native function calling and structured JSON output for agentic workflows
• INT8 quantization

Pearl Proof of Useful Work:
• This endpoint runs on Pearl's Proof of Useful Work (PoUW) protocol, which extracts cryptographic mining proofs as a side effect of standard AI inference
• Model quality and throughput are preserved — the Pearl kernel operates at the matrix multiplication level without affecting model outputs
• Mining rewards flow back as a direct subsidy, enabling 25% discounted pricing
• Zero-knowledge proofs ensure no model weights or user data are exposed
‍
Prompting
Together AI API Access:
• Access Pearl Gemma 4 31B via Together AI APIs using the endpoint pearl-ai/gemma-4-31b-it-pearl
• Authenticate using your Together AI API key in request headers
• Supports thinking mode, function calling, and JSON mode
• Available on Together AI serverless infrastructure
‍
Applications & use cases
Reasoning & Coding:
• Mathematical reasoning with configurable thinking mode
• Code generation, completion, and correction across multiple languages

Agentic Workflows:
• Native function calling with structured JSON output for tool orchestration
• System prompt support for structured multi-turn conversations
• 256K context for processing large codebases and documentation
‍

Related models

Model specifications

Model data

Model provider
Pearl AI
Type
Reasoning
Main use cases
Reasoning
Features
Function Calling
JSON Mode
Deployment
Serverless
Endpoint
pearl-ai/gemma-4-31b-it-pearl
Parameters
31B
Context length
256K
Input price
$0.28 / 1M tokens
Output price
$0.86 / 1M tokens
Input modalities
Text
Output modalities
Text

Quantization level
INT8
Category
Chat

Run in Playground

Quickstart docs

Deploy model

Gemma-4-31B-it-Pearl

About model

API usage

Model card

Prompting

Applications & use cases