INTELLECT-3

About INTELLECT-3

INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math, code, science, and general reasoning, consistently outperforming many larger frontier models. Designed for strong multi-step problem solving, it maintains high accuracy on structured tasks while remaining efficient at inference thanks to its MoE architecture.

Model Specifications

💰 Real-World Cost Examples

Estimated monthly costs for common use cases

Other Model Lineup

Compare all models from Other to find the best fit

Similar Models from Other Providers

Cross-brand alternatives with similar capabilities

Gemma 2 27B

Google

Input: $0.65

Output: $0.65

Context: 8k

Qwen3 Coder 480B A35B (exacto)

Alibaba Qwen

Input: $0.30

Output: $1.00

Context: 262k

MiniMax-01

MiniMax

Input: $0.20

Output: $1.10

Context: 1.0M

Qwen3.6 Flash

Alibaba Qwen

Input: $0.19

Output: $1.13

Context: 1.0M

💡 Cheaper Alternatives

Same Brand (Other)

Cross Brand

🚀 Quick Start

Get started with INTELLECT-3 API

from openai import OpenAI

client = OpenAI(
    base_url="https://api.provider.com/v1",
    api_key="YOUR_API_KEY"
)

response = client.chat.completions.create(
    model="prime-intellect/intellect-3-20251126",
    messages=[
        {"role": "user", "content": "Hello!"}
    ]
)
print(response.choices[0].message.content)

Continue Your Decision