Bytez · Arazzo Workflow
Discover and run a Bytez model
Version 1.0.0
List models for a task, pick one, and run serverless inference.
View Spec
View on GitHub
CompanyArtificial IntelligenceMachine LearningModel InferenceLLMOpen Source AIAPIDevelopersArazzoWorkflows
Provider
Workflows
discoverAndRunModel
Find a chat model via getModels then run it with runModel.
Lists available models for a task, selects the first model id, then runs an inference request against it and returns the model output.
1
listModels
getModels
Retrieve models available for the requested task.
2
runModel
runModel
Run inference on the selected model.