Fair Usage Policy - Docs
Reasoning
Our Fair Usage Policy limits prompts per time frame to allow all users access to all models without a single user negatively impacting the service for others by monopolizing model capacities. It is designed to prevent abuse and ensure reliability and availability for the overall user base.
Implementation
If a user exceeds the allowed limits, they can switch to a different model. However, 99% of all users never hit this limit, and the limit is only temporary. As LLMs have different prices and different demands, we structured them into different categories:
Category 1 includes smaller, faster models. They allow unlimited requests, although there is still spam protection against abuse.
Category 2 models can receive 200 messages in three hours.
Category 3 models allow 100 messages in three hours.
Overview
Category 1: Unlimited (with spam protection)
Ada v2
Azure Document Intelligence
DALL-E 3
FLUX1.1 [pro] Ultra
Gemini 2.5 Flash Image 🍌
Imagen 4
Imagen 4 Fast
Langdock Built-in OCR
Mistral OCR
Category 2: 250 messages / 3 hours
Claude 3.5 Haiku
Codestral
Gemini 2.5 Flash
GPT oss (120b)
GPT-4.1
GPT-4.1 mini
GPT-4.1 nano
GPT-4o
GPT-4o Mini
GPT-5
GPT-5 Mini
GPT-5 Nano
GPT-5 Thinking
Llama 3.3 70B
Llama 4 Maverick
Mistral Large 2411
Mistral Medium
Nova Lite
Nova Pro
Category 3: 100 messages / 3 hours
Claude Sonnet 3.5
Claude Sonnet 3.7
Claude Sonnet 3.7 Reasoning
Claude Sonnet 4
Claude Sonnet 4.5
Claude Sonnet 4.5 Reasoning
Claude Sonnet 4 Reasoning
DeepSeek r1
DeepSeek v3
DeepSeek v3.1
Gemini 2.5 Pro
Gemini 2.5 Pro Reasoning
GPT-5 Chat
o1
o3
o3 Mini
o3 Mini high
o4 Mini
Category 4: 20 messages / 3 hours
Claude Opus 3
GPT Image 1
o3 Pro
Category 5: 5 messages / 3 hours
FLUX.1 Kontext