Skip to main content
Sort the returned models server-side. Prefer this over fetching the full list and sorting client-side. Options: pricing-low-to-high, pricing-high-to-low (average prompt/completion price), context-high-to-low (context length), throughput-high-to-low, latency-low-to-high (recent median performance), most-popular, top-weekly (tokens processed in the last week), newest (creation date), <index>-high-to-low for each Artificial Analysis index (the coding and agentic sorts are deprecated: Artificial Analysis has retired those indexes), design-arena-elo-high-to-low (best Design Arena ELO across arenas). Models without a score for the chosen benchmark are placed last. The decision sort ranks decision models, so pass output_modalities=decisions or all with it. When omitted, the existing default ordering is preserved.

Example Usage

Values

This is an open enum. Unrecognized values will not fail type checks.
  • "most-popular"
  • "newest"
  • "top-weekly"
  • "pricing-low-to-high"
  • "pricing-high-to-low"
  • "context-high-to-low"
  • "throughput-high-to-low"
  • "latency-low-to-high"
  • "intelligence-high-to-low"
  • "coding-high-to-low"
  • "agentic-high-to-low"
  • "finance-and-accounting-high-to-low"
  • "strategy-and-ops-high-to-low"
  • "legal-high-to-low"
  • "healthcare-and-medical-high-to-low"
  • "engineering-high-to-low"
  • "economics-high-to-low"
  • "cyber-high-to-low"
  • "openness-high-to-low"
  • "multilingual-high-to-low"
  • "decision-high-to-low"
  • "design-arena-elo-high-to-low"