Skip to main content

​
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, most 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 utility models for OCR, embeddings, and select image generation. They allow unlimited requests, although there is still spam protection against abuse.
  • Category 2 models can receive 250 messages in 3 hours.
  • Category 3 models allow 100 messages in 3 hours.
  • Category 4 models allow 30 messages in 3 hours.
  • Category 5 models allow 20 messages in 3 hours.
  • Category 6 models allow 5 messages in 3 hours.
  • Category 7 models allow 5 messages per month.

​
Overview

Model categories and limits are subject to change as we update our model offerings. Category 1: Unlimited (with spam protection)
  • Ada v2
  • Azure Document Intelligence
  • FLUX2 [pro]
  • Gemini 2.5 Flash Image 🍌
  • Gemini 3.1 Flash Image (Preview) 🍌
  • Imagen 4
  • Langdock Built-in OCR
  • Mistral OCR
Category 2: 250 messages / 3 hours
  • Codestral
  • Gemini 2.5 Flash
  • GPT-4.1
  • GPT-4o
  • GPT-5
  • GPT-5.1
  • GPT-5.1 Thinking
  • GPT-5.1 Thinking Fast
  • GPT-5 Mini
  • GPT-5 Thinking Fast
  • GPT oss (120b)
  • Haiku 4.5
  • Llama 3.3 70B
  • Llama 4 Maverick
  • Mistral Large 2411
  • Mistral Large 3
  • Mistral Medium
  • o4 Mini
Category 3: 100 messages / 3 hours
  • DeepSeek r1
  • DeepSeek v3.1
  • Gemini 2.5 Pro
  • Gemini 2.5 Pro Reasoning
  • Gemini 3 Flash Preview
  • GPT-5.2
  • GPT-5.2 Thinking
  • GPT-5 Thinking
  • o3
  • Sonnet 4.5
  • Sonnet 4.5 Reasoning
  • Sonnet 4.6
  • Sonnet 4.6 Reasoning
Category 4: 30 messages / 3 hours
  • Gemini 3.1 Pro Preview
Category 5: 20 messages / 3 hours
  • GPT-5.4
  • GPT-5.4 Thinking
  • GPT Image 1.5
  • o3 Pro
  • Opus 4.5
  • Opus 4.5 Reasoning
  • Opus 4.6
  • Opus 4.6 Reasoning
Category 6: 5 messages / month
  • GPT-5 Pro
  • GPT-5.2 Pro
Last updated: March 23, 2026