5 min read

Supported LLMs

Vantage supports multiple large language model (LLM) providers through Intuidy AI. You can use the built-in default provider, or connect your own API key to any of the supported providers below.


Provider Overview

ProviderModelsAPI Key RequiredSetup Complexity
Intuidy AIDefault model (GPT-4.1)NoNone — works out of the box
OpenAIGPT-4o, GPT-4.1, GPT-5, o1, o3, o4YesLow
Claude (Anthropic)Claude Sonnet 4, Claude Sonnet 4.6, Claude Opus 4.6YesLow
Gemini (Google)Gemini 2.0 Flash, Gemini 2.5 Flash, Gemini 2.5 ProYesLow
MistralMistral Large, Codestral, Magistral, PixtralYesLow

Provider Details

Intuidy AI (Default)

The built-in AI provider that works with no configuration. Ideal for teams that want to start using AI immediately without managing API keys or provider accounts.


OpenAI

The most widely-used AI provider, offering the GPT family of models.

ModelContext WindowBest For
GPT-4.1128K tokensBest all-around performance
GPT-4.1 Mini128K tokensFast, cost-effective general use
GPT-4o128K tokensVision and multimodal tasks
GPT-4o Mini128K tokensBudget-friendly, simpler tasks
GPT-5128K tokensLatest capabilities
o3200K tokensDeep reasoning and analysis
o4200K tokensAdvanced reasoning

Claude (Anthropic)

Known for detailed, thoughtful responses and strong performance on long-form analysis.

ModelContext WindowBest For
Claude Opus 4.6200K tokensMost capable, deep thinking
Claude Sonnet 4.6200K tokensBest all-around performance
Claude Sonnet 4200K tokensBalanced quality and speed
Claude 3.5 Sonnet200K tokensFast, cost-effective
Claude 3 Haiku200K tokensBudget-friendly

Gemini (Google)

Google's multimodal AI models with strong data analysis capabilities.

ModelContext WindowBest For
Gemini 2.5 Pro1M tokensDeep reasoning, large dataset analysis
Gemini 2.5 Flash1M tokensFast, balanced performance
Gemini 2.0 Flash1M tokensGeneral-purpose tasks
Gemini 2.0 Flash Lite1M tokensBudget-friendly, high-volume
Gemini 1.5 Pro1M tokensLegacy, large context

Mistral

European AI provider offering efficient, high-quality models with a broad model family.

ModelBest For
Mistral LargeComplex analysis, highest quality
Magistral MediumDeep reasoning
Mistral MediumBalanced quality and speed
Mistral SmallFast, cost-effective
CodestralCode generation and analysis
DevstralDeveloper workflows
PixtralVision and multimodal tasks
MinistralLightweight, fast responses

Choosing a Provider

PriorityRecommended Provider
No setup neededIntuidy AI (default)
Best general qualityOpenAI (GPT-4.1) or Claude (Sonnet 4.6)
Deep reasoningOpenAI (o3) or Claude (Opus 4.6)
Long documents / large datasetsGemini (1M token context) or Claude (200K context)
Cost efficiencyOpenAI (GPT-4.1 Mini), Gemini (2.0 Flash Lite), or Mistral (Small)
EU data residencyMistral
Code & technical analysisCodestral or OpenAI (GPT-4.1)
Vision / multimodalOpenAI (GPT-4o), Gemini (2.0 Flash), or Pixtral

Switching Providers

You can switch providers at any time:

  1. Go to Settings → AI Features → Intuidy AI
  2. Select the new provider
  3. Enter API credentials if required
  4. Choose a model
  5. Click Save AI Settings

All AI features — assistant, tile summaries, workflow nodes — will immediately use the new provider.