Dynamic Model Catalog & Fallback Cascade
Runtime LLM routing, wholesale-to-retail pricing margins, and automated fallback sequence.
Amazon Bedrock Nova Pro
PRIMARY ROUTEProvider: AWS Bedrock • ID: amazon/bedrock-nova-pro
Wholesale (In/Out)$0.80 / MTok / $3.20 / MTok
Retail (In/Out)$1.50 / MTok / $6.00 / MTok
Latency: 380msSpeed: 110 tok/s
Claude 3.7 Sonnet
Provider: Anthropic • ID: anthropic/claude-3-7-sonnet
Wholesale (In/Out)$3.00 / MTok / $15.00 / MTok
Retail (In/Out)$5.00 / MTok / $25.00 / MTok
Latency: 620msSpeed: 85 tok/s
Google Gemini 2.5 Pro
Provider: Google Cloud • ID: google/gemini-2-5-pro
Wholesale (In/Out)$1.25 / MTok / $5.00 / MTok
Retail (In/Out)$2.50 / MTok / $10.00 / MTok
Latency: 440msSpeed: 130 tok/s
OpenAI GPT-4o
Provider: OpenAI • ID: openai/gpt-4o
Wholesale (In/Out)$2.50 / MTok / $10.00 / MTok
Retail (In/Out)$5.00 / MTok / $20.00 / MTok
Latency: 710msSpeed: 90 tok/s