Skip to Content
DocumentationModelsModels

Models

Stacknet provides access to models through Model Layers, fine tuned pools of models and capabilities. Models are served by nodes operated by aISPs.

Available Model Layers

Layers are the canonical names you should pass as model in /v1/chat/completions. The network picks a member model that best fits your prompt + content type.

ModelModalitiesCapabilitiesContext
previewText, Image → TextFunction calling, Structured output, Reasoning128K+
duceText, Image → Text, Image → Image, Text → Video, Image → Video, Video → Video, Text → Music, Music → Music, TTSSOTA music, Function calling, Reasoning, MoM128K+
magmaText, Image → Text, Image → Image, Text → Video, Image → Video, Video → Video, Text → Music, Music → Music, TTSSOTA video, Function calling, Reasoning, MoM1m

Capability aliases

/v1/models also returns four capability-scoped aliases. They’re lower-level than the layers above — each maps directly to a specific underlying model rather than a routing tier. Use them when you need a fixed capability shape without layer-routing semantics.

AliasCapabilityNotes
stack-chatText → Text chatConversational completion.
stack-codeCode generation / repairOptimised for code edits and tool-use loops.
stack-polyMultimodal in/outVision + audio understanding; text/image/audio output.
stack-embedEmbeddingsUse against /v1/embeddings, not /v1/chat/completions.

If you’re starting fresh, prefer the layer names — the layer router handles routing decisions for you and inherits any future capability gains. The stack-* aliases are kept for backwards-compatibility with earlier integrations.

Creating a Model Layer

Anyone on the network can create network wide supported model layers and earn every time the model layer is used. A model layer will qualify and propagate if the following requirements are met:

  • 90% network support (can run on the hardware of the network. Making hardware targeting moot. Real network-wide performance is the bar.)
  • 40% different composition from the leading model layer
  • 2.5%+ better benchmark than the leading model layer
  • (Cumulative model parameters x 10 ) + Network Benchmark tokens = Token Cost
  • Written and compiled in Lode Language 

Try a Model Layer

Visit the Chat API playground to test model layers interactively.

Last updated on