--- title: Prime Intellect: INTELLECT 3 | Text Generation | ModelsLab description: 106B MoE LLM (12B active) with 131K context excels in math (90.8% AIME), code (69.3% LiveCodeBench), science & reasoning, outperforming larger models.[1][3][4] url: https://modelslab.com/models/prime-intellect/prime-intellect-intellect-3.md canonical: https://modelslab.com/models/prime-intellect/prime-intellect-intellect-3.md type: product component: Playground/LLM/Index generated_at: 2026-04-15T02:04:10.871336Z --- Prime Intellect: INTELLECT-3 --- [LLMs.txt](https://modelslab.com/models/open_router/prime-intellect-intellect-3/llms.txt) [.md](https://modelslab.com/models/prime-intellect/prime-intellect-intellect-3.md) prime-intellect-intellect-3 prime-intellect Closed Source Model $0.650000 / call Prime Intellect: INTELLECT-3 --- Choose a prompt below to get started or type your own message Explain quantum computing in simple terms Write a Python function to sort a list Create a marketing email for a SaaS product Compare REST vs GraphQL APIs Send ### Prime Intellect: INTELLECT-3 prime-intellect prime-intellect-intellect-3 Copy model ID PricingInput $0.20 / 1M tokens Output $1.10 / 1M tokens API EndpointsOpenAI Compatible `https://modelslab.com/api/v7/llm/chat/completions`Endpoint Anthropic Compatible `https://modelslab.com/api/v7/llm/v1/messages`Messages `https://modelslab.com/api/v7/llm/v1/messages/count_tokens`Count Tokens `https://modelslab.com/api/v7/llm/v1/models`Models Use with Claude Code cURL Example ParametersSystem MessageYou are a helpful AI assistant specialized in providing accurate and detailed responses. Temperature0.7 Max Tokens1000 Top P0.9 Frequency Penalty0 Presence Penalty0 Model Info Support Related Models --- Discover similar models you might be interested in [View all LLM Models](https://modelslab.com/models?feature=llmaster) [N8](https://modelslab.com/models/together_ai/nim-mistralai-mixtral-8x7b-instruct-v01)[Together AI](https://modelslab.com/models/together_ai) [nim/mistralai/mixtral-8x7b-instruct-v01 Closed Source Model](https://modelslab.com/models/together_ai/nim-mistralai-mixtral-8x7b-instruct-v01) [DV](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2)[Together AI](https://modelslab.com/models/together_ai) [Deepseek V3.2 Closed Source Model](https://modelslab.com/models/together_ai/deepseek-ai-DeepSeek-V3.2) [OG](https://modelslab.com/models/open_router/openai-gpt-oss-120b-free)[Open Router](https://modelslab.com/models/open_router) [OpenAI: gpt-oss-120b (free) Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-oss-120b-free) [SM](https://modelslab.com/models/together_ai/sarvamai-sarvam-m)[Together AI](https://modelslab.com/models/together_ai) [Sarvam M Closed Source Model](https://modelslab.com/models/together_ai/sarvamai-sarvam-m) [QQ](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b)[Open Router](https://modelslab.com/models/open_router) [Qwen: Qwen3 30B A3B Closed Source Model](https://modelslab.com/models/open_router/qwen-qwen3-30b-a3b) [ML](https://modelslab.com/models/open_router/meta-llama-Llama-3-8b-chat-hf)[Open Router](https://modelslab.com/models/open_router) [Meta Llama 3 8B Instruct Reference Closed Source Model](https://modelslab.com/models/open_router/meta-llama-Llama-3-8b-chat-hf) [![GPT-5-mini](https://images.stablediffusionapi.com/?Image=https://assets.modelslab.ai/generations/0bda788d-705d-4cbd-9c9d-dcdaa12b9493.webp)](https://modelslab.com/models/openai/gpt-5-mini)[Open Ai](https://modelslab.com/models/openai) [GPT-5-mini Closed Source Model](https://modelslab.com/models/openai/gpt-5-mini) [DC](https://modelslab.com/models/open_router/deepcogito-cogito-v2.1-671b)[Open Router](https://modelslab.com/models/open_router) [Deep Cogito: Cogito v2.1 671B Closed Source Model](https://modelslab.com/models/open_router/deepcogito-cogito-v2.1-671b) [QV](https://modelslab.com/models/qwen/Qwen-Qwen2-VL-72B-Instruct)[ModelsLab](https://modelslab.com/models/qwen) [Qwen2-VL (72B) Instruct Closed Source Model](https://modelslab.com/models/qwen/Qwen-Qwen2-VL-72B-Instruct) [Q3](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-3B-Instruct)[Together AI](https://modelslab.com/models/together_ai) [Qwen2.5 3B Instruct Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen2.5-3B-Instruct) [ML](https://modelslab.com/models/open_router/mistralai-mistral-large)[Open Router](https://modelslab.com/models/open_router) [Mistral Large Closed Source Model](https://modelslab.com/models/open_router/mistralai-mistral-large) [OG](https://modelslab.com/models/open_router/openai-gpt-4o-extended)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-4o (extended) Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-4o-extended) [GG](https://modelslab.com/models/open_router/google-gemini-3.1-pro-preview)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 3.1 Pro Preview Closed Source Model](https://modelslab.com/models/open_router/google-gemini-3.1-pro-preview) [QC](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-Next-FP8)[Together AI](https://modelslab.com/models/together_ai) [Qwen3 Coder Next Fp8 Closed Source Model](https://modelslab.com/models/together_ai/Qwen-Qwen3-Coder-Next-FP8) [OG](https://modelslab.com/models/open_router/openai-gpt-5.3-codex)[Open Router](https://modelslab.com/models/open_router) [OpenAI: GPT-5.3-Codex Closed Source Model](https://modelslab.com/models/open_router/openai-gpt-5.3-codex) [GG](https://modelslab.com/models/open_router/google-gemini-3-flash-preview)[Open Router](https://modelslab.com/models/open_router) [Google: Gemini 3 Flash Preview Closed Source Model](https://modelslab.com/models/open_router/google-gemini-3-flash-preview) [OO](https://modelslab.com/models/open_router/openai-o4-mini-high)[Open Router](https://modelslab.com/models/open_router) [OpenAI: o4 Mini High Closed Source Model](https://modelslab.com/models/open_router/openai-o4-mini-high) [GG](https://modelslab.com/models/open_router/google-gemma-4-26b-a4b-it-free)[Open Router](https://modelslab.com/models/open_router) [Google: Gemma 4 26B A4B (free) Closed Source Model](https://modelslab.com/models/open_router/google-gemma-4-26b-a4b-it-free) About Prime Intellect: 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,... ### Technical Specifications Model IDprime-intellect-intellect-3CategoryLLM ModelsTaskText GenerationPrice$0.650000 per million tokensAddedFebruary 20, 2026 ### Key Features - Chat completion and multi-turn conversation API - Streaming response with token-by-token output - Function calling and tool use support - System prompts and role-based messaging - JSON mode and structured output ### Quick Start Integrate Prime Intellect: INTELLECT-3 into your application with a single API call. Get your API key from the [pricing page](https://modelslab.com/pricing) to get started. PythonJavaScriptcURLPHP ``` import requests import json url = "https://modelslab.com/api/v7/llm/chat/completions" headers = { "Content-Type": "application/json" } data = { "model_id": "prime-intellect-intellect-3", "messages": [ { "role": "user", "content": "Hello!" } ], "max_tokens": 1000, "key": "YOUR_API_KEY" } try: response = requests.post(url, headers=headers, json=data) response.raise_for_status() # Raises an HTTPError for bad responses (4XX or 5XX) result = response.json() print("API Response:") print(json.dumps(result, indent=2)) except requests.exceptions.HTTPError as http_err: print(f"HTTP error occurred: {http_err} - {response.text}") except Exception as err: print(f"Other error occurred: {err}") ``` View the [full API documentation](https://modelslab.com/models/prime-intellect/prime-intellect-intellect-3/api) for SDKs, code examples in Python, JavaScript, and more. ### Pricing Prime Intellect: INTELLECT-3 API costs $0.650000 per million tokens. Pay only for what you use with no minimum commitments. [View pricing plans](https://modelslab.com/pricing) ### Use Cases - AI chatbots and virtual assistants - Code generation and developer tools - Content writing and copywriting automation - Data analysis, summarization, and extraction [Learn more about Prime Intellect: INTELLECT-3](https://modelslab.com/prime-intellect-intellect-3) [Browse LLM Models](https://modelslab.com/models?feature=llmaster) [More from Prime Intellect](https://modelslab.com/models/open_router) [View Pricing](https://modelslab.com/pricing) Prime Intellect: INTELLECT-3 FAQ --- ### What is Prime Intellect: 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,... ### How do I use the Prime Intellect: INTELLECT-3 API? You can integrate Prime Intellect: INTELLECT-3 into your application with a single API call. Sign up on ModelsLab to get your API key, then use the model ID "prime-intellect-intellect-3" in your API requests. We provide SDKs for Python, JavaScript, and cURL examples in the API documentation. ### How much does Prime Intellect: INTELLECT-3 cost? Prime Intellect: INTELLECT-3 costs $0.650000 per million tokens. ModelsLab uses pay-per-use pricing with no minimum commitments. A free tier is available to get started. ### What is the Prime Intellect: INTELLECT-3 model ID? The model ID for Prime Intellect: INTELLECT-3 is "prime-intellect-intellect-3". Use this ID in your API requests to specify this model. ### Does Prime Intellect: INTELLECT-3 have a free tier? Yes, ModelsLab offers a free tier that lets you try Prime Intellect: INTELLECT-3 and other AI models. Sign up to get free API credits and start building immediately. --- *This markdown version is optimized for AI agents and LLMs.* **Links:** - [Website](https://modelslab.com) - [API Documentation](https://docs.modelslab.com) - [Blog](https://modelslab.com/blog) --- *Generated by ModelsLab - 2026-04-15*