Models
Browse the curated list of AI models available through SensAI, powered by OpenRouter.
Available Models
SensAI provides access to a curated selection of AI models from leading providers, all routed through OpenRouter. This means you can switch between models without managing multiple API keys or provider integrations.
The available models are periodically updated and cached on the server to ensure fast response times. Use the GET /api/v1/chat/models endpoint to fetch the current list programmatically.
Model Providers
SensAI currently supports models from the following providers:
OpenAI
- GPT-4o (
openai/gpt-4o) — Multimodal flagship model with 128k context window. Best for complex reasoning, analysis, and creative tasks. - GPT-4o Mini (
openai/gpt-4o-mini) — Lightweight and fast variant optimized for simpler tasks with lower latency and cost.
Anthropic
- Claude 3.5 Sonnet (
anthropic/claude-3.5-sonnet) — Balanced model excelling at coding, analysis, and nuanced instruction following. - Claude 3.5 Haiku (
anthropic/claude-3.5-haiku) — Fast and cost-efficient model suitable for high-throughput applications.
- Gemini 2.0 Flash (
google/gemini-2.0-flash-001) — High-speed model with strong reasoning capabilities and a large context window.
Meta
- Llama 3.3 70B (
meta-llama/llama-3.3-70b-instruct) — Open-weight model offering strong performance across a wide range of tasks.
Choosing the Right Model
When selecting a model for your use case, consider the following factors:
- Latency requirements — For real-time chat applications, smaller models like GPT-4o Mini or Claude 3.5 Haiku provide faster response times.
- Task complexity — For advanced reasoning, code generation, or multi-step analysis, use GPT-4o or Claude 3.5 Sonnet.
- Cost — Smaller models are significantly cheaper per token. Use them for high-volume, straightforward tasks.
- Context length — If your application requires processing long documents, choose models with larger context windows.
Model Updates
The model catalog is managed server-side and may be updated as new models become available or existing ones are deprecated. Always check the /chat/models endpoint for the most current list.