Skip to main content

Available models

All models are available on the free tier with daily usage limits. Switch between models using the model selector in the chat header.

Azure models

GPT-4o Mini (Azure)

Provider: Azure OpenAIFast and affordable with full tool calling support. Great balance of speed and capability for everyday crypto queries.Supports: File upload, tool calling

GPT-4.1 (Azure)

Provider: Azure OpenAIThe most capable model available. Handles complex reasoning, multi-step analysis, and deep research tasks.Supports: File upload, tool calling, advanced reasoning

Mistral models

Pixtral Large

Provider: MistralMistral’s flagship model with image understanding. Strong at reasoning, writing, and multimodal analysis.Supports: File upload, tool calling

Mistral Large

Provider: MistralOptimized for chat. A fast option for everyday conversations and quick questions.Supports: Tool calling

Devstral Small

Provider: Mistral (via OpenRouter)Optimized for coding tasks. Use this for code generation, debugging, and programming questions.Supports: Tool calling

Google models

Gemini 3.1 Flash Lite

Provider: GoogleGoogle’s fastest Gemini model. 2.5x faster than previous versions with 1M token context window. Best for high-volume, quick-response tasks.Supports: File upload, tool calling

Gemma 3n E2B

Provider: Google (via OpenRouter)Lightweight and efficient. Good for everyday chat and creative tasks.Free tier

OpenAI models

GPT-4o Mini

Provider: OpenAI (via OpenRouter)Same GPT-4o Mini model accessed through OpenRouter. Useful as a fallback when Azure is at capacity.Supports: File upload, tool calling

GPT-OSS 120B

Provider: OpenAI (via OpenRouter)Open-source 120B parameter model with strong reasoning and generation capabilities.Free tier

Other models

Hunter Alpha

Provider: OpenRouterOpenRouter’s custom model optimized for fast, intelligent conversations.Free tier

Step 3.5 Flash

Provider: StepFun (via OpenRouter)Fast and efficient for quick responses and everyday tasks.Free tier

How to choose a model

Use caseRecommended model
Quick price checks and simple questionsGemini 3.1 Flash Lite
Complex analysis with multiple toolsGPT-4.1 (Azure)
General daily usageGPT-4o Mini (Azure)
Image/chart analysisPixtral Large
Code-related questionsDevstral Small
Casual conversationAny free tier model
The default model is Gemini 3.1 Flash Lite — it offers the best speed-to-quality ratio for most crypto queries.