DocuChat Logo
Chatbots

AI Models

Choose an AI model for your chatbot and keep track of your question credits.

Supported Models

DocuChat supports the latest frontier AI models from Anthropic, OpenAI, Mistral, and Meta. Our newest additions are Claude Opus 4.7 and Claude Sonnet 4.6 — Anthropic's most capable models to date, with 1M-token context windows and improved reasoning. You can choose which model you want to use for answering questions with your chatbot.

ModelIntelligenceSpeedCost EfficiencyProviderHosted InAvailable In
Claude Opus 4.7◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◼︎◼︎◻︎◻︎◻︎Anthropic🇪🇺Pro
Claude Sonnet 4.6◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◻︎◻︎Anthropic🇪🇺Pro
Claude Opus 4.5◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◼︎◻︎◻︎◻︎◻︎Anthropic🇪🇺Pro
Claude Sonnet 4.5◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◻︎◻︎Anthropic🇪🇺Pro
Claude Haiku 4.5◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◼︎◻︎◼︎◼︎◼︎◼︎◼︎Anthropic🇪🇺Pro, Essential
GPT-5.2◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◻︎◼︎◻︎◻︎◻︎◻︎OpenAI🇺🇸*Pro
GPT-5◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◻︎◻︎◼︎◻︎◻︎◻︎◻︎OpenAI🇺🇸*Pro
GPT-5 Mini◼︎◼︎◼︎◼︎◻︎◼︎◼︎◼︎◼︎◻︎◼︎◼︎◼︎◼︎◻︎OpenAI🇺🇸*Pro
GPT-5 Nano◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎OpenAI🇺🇸*Pro
GPT-4o mini◼︎◼︎◼︎◼︎◻︎◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◼︎◼︎OpenAI🇺🇸*Pro, Essential
Mistral Large 2◼︎◼︎◼︎◼︎◻︎◼︎◻︎◻︎◻︎◻︎◼︎◼︎◼︎◻︎◻︎Mistral🇪🇺Pro
Llama 4 Scout◼︎◼︎◼︎◻︎◻︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎◼︎Meta🇺🇸Pro

* Hosted in EU when using Azure OpenAI integration in the Enterprise plan, otherwise hosted in US.

Choosing the Right Model

Selecting the appropriate AI model depends on your specific needs:

  • For the highest precision and most advanced capabilities, consider Claude Opus 4.7, GPT-5.2, or GPT-5. Claude Opus 4.7 is Anthropic's most capable model with a 1M-token context window and best-in-class agentic reasoning.
  • For the best combination of speed and intelligence, Claude Sonnet 4.6 is our recommended default — strong reasoning, 1M-token context, and faster than the Opus tier.
  • For balanced performance and cost, consider GPT-5 Mini or Claude Sonnet 4.6 — both offer near-flagship intelligence at lower cost.
  • For speed and cost optimization, GPT-5 Nano provides the fastest responses at the lowest cost among GPT-5 variants.
  • For simple tasks and cost-effective solutions, GPT-4o Mini and Claude Haiku 4.5 are ideal.
  • For fastest response times, Llama 4 Scout is recommended.
  • For EU data residency requirements, all Claude models (Opus 4.7, Sonnet 4.6, Opus 4.5, Sonnet 4.5, Haiku 4.5) and Mistral Large 2 are the best choices as they are hosted in the EU.
  • For organizations requiring OpenAI models with EU data residency, Enterprise plans offer Azure OpenAI integration with EU-based hosting.
Claude Sonnet 4.5 and Claude Opus 4.5 remain available alongside the 4.6 and 4.7 releases. Existing chatbots configured to those versions continue to work and can stay on them as long as you want.