PromptFloe Developer Docs
Reference

Models

PromptFloe routes your requests to the best model for each stage of the pipeline. You can override the model for advanced use cases — most users don't need to.

#Default routing

Each pipeline stage uses a model tuned for its job:

FieldTypeDescription
PlannerreasoningLong-context reasoning model. Plans the file manifest.
Files agentfast structuredJSON-mode-tuned model. Emits the file tree.
Code agentcode-specializedPer-file generation. Multiple instances in parallel.
ReviewerreasoningCross-file checks for missing imports, unused symbols.
Critique skillgeneralLong-form markdown reasoning.
Augmentercode-specializedSame model class as code agent — produces strict JSON patches.

#Per-call overrides

Pass modelOverride on the generate or run call to force a specific model. Available aliases:

FieldTypeDescription
fastaliasSmaller, cheaper model. Lower quality, faster turnaround.
balancedaliasDefault. Best price/quality tradeoff.
qualityaliasMost capable model. Higher cost, slower.
reasoningaliasLong-thinking model for complex planning.
await client.apps.generate({
  prompt: '...',
  modelOverride: 'quality',  // use the highest-tier model
});

#Enterprise: bring your own model

Enterprise plans can wire custom inference endpoints — your own fine-tuned models, on-prem inference clusters, or alternate providers — through a proxy contract. Contact sales for setup.

#Where to go next

PromptFloe developer docs