Reasoning

Pearl Llama 3 8B Instruct Lite

Cost-efficient 8B instruction model at 80% discounted pricing

About model

Pearl Llama 3 8B Instruct Lite is Meta's 8B parameter instruction-tuned model running on Pearl's Proof of Useful Work protocol, delivering identical performance at 80% discounted pricing. Optimized with Together Lite INT4 quantization for maximum cost efficiency, the model is built for high-volume production workloads where cost per token is the primary constraint. The Pearl kernel extracts cryptographic mining proofs during standard inference without affecting model quality or throughput.

Discounted Pricing

80%

Per Million Tokens

$0.02

Input and output at the lowest cost tier

Parameters

INT4 Lite-optimized for maximum throughput

Model key capabilities

80% Discounted Pricing: Powered by Pearl's Proof of Useful Work — mining rewards subsidize inference costs with zero impact on model quality or throughput
Maximum Cost Efficiency: Together Lite INT4 quantization at $0.02 per million tokens for high-volume production workloads
Instruction Following: General-purpose conversational AI, basic coding, and content generation with multilingual support
High Throughput: Optimized for applications with millions of daily requests where latency and cost efficiency are critical

API usage

cURL
Python
Typescript

Endpoint:

meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite

curl -X POST "https://api.together.xyz/v1/chat/completions" \
  -H "Authorization: Bearer $TOGETHER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite",
    "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="meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite",
  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: 'meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite',
  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:
• 8B parameter dense transformer optimized with Together Lite for maximum cost efficiency via INT4 quantization
• 8K token context window
• Instruction-tuned for conversational AI, basic coding, and general-purpose tasks

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 80% discounted pricing
• Zero-knowledge proofs ensure no model weights or user data are exposed

Performance Characteristics:
• Identical performance to standard Llama 3 8B Instruct Lite — all benchmarks and capabilities are preserved
• Together Lite INT4 optimization for maximum capacity and lowest cost per token
• Suitable for high-volume, cost-sensitive production workloads
‍
Prompting
Together AI API Access:
• Access Pearl Llama 3 8B Instruct Lite via Together AI APIs using the endpoint meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite
• Authenticate using your Together AI API key in request headers
• $0.02 per million input tokens / $0.02 per million output tokens (80% discount)
• Available on Together AI serverless infrastructure
‍
Applications & use cases
High-Volume Production:
• Cost-efficient inference for classification, routing, and lightweight generation tasks
• High-capacity serving for applications with millions of daily requests
• Together Lite INT4 optimization for maximum throughput per dollar

Conversational AI:
• General-purpose instruction following for chatbots and assistants
• Quick-response applications where latency matters more than maximum reasoning depth
• Multilingual support for diverse user interactions

Development & Prototyping:
• Rapid prototyping and experimentation at minimal cost
• Basic code generation, explanation, and debugging
• Content generation and summarization for production pipelines
‍

Related models

Model specifications

Model data

Model provider
Meta
Type
Reasoning
Features
Function Calling
Deployment
Serverless
Endpoint
meta-llama/pearl-Meta-Llama-3-8B-Instruct-Lite
Parameters
8B
Context length
8K
Input price
$0.02 / 1M tokens
Output price
$0.02 / 1M tokens
Input modalities
Text
Output modalities
Text

Quantization level
INT4
Category
Chat

Run in Playground

Quickstart docs

Deploy model

Pearl Llama 3 8B Instruct Lite

About model

API usage

Model card

Prompting

Applications & use cases