The Perceptron Mk1.5 developer documentation is the official technical documentation provided by Perceptron for its Mk1.5 model, primarily aimed at developers who need to integrate multimodal AI capabilities.
[Purpose] This documentation is intended to help developers quickly get started with Perceptron Mk1.5 and implement understanding, tracking, and tool calling capabilities on images, video, and audio.
[Main capabilities] According to the documentation index, Mk1.5 supports the following capabilities: image understanding, video understanding, audio understanding, multi-asset processing, and structured output. It also supports tool calling and tracking.
[How to use] The documentation provides getting-started steps: create an API key, make the first request, and explore the various capabilities. The documentation index can be obtained via /llms.txt, which is used to discover all available pages.
[Applicable scenarios] Suitable for developer scenarios that require multimodal understanding (images, video, audio), such as building intelligent analysis, content recognition, or automated tool calling applications.
[Limitations] Information about the model's specific limitations, pricing, platform support, etc. is not yet provided.
