Introducing Toast 1

	Introducing Toast 1(mixedbread.com)
	216 points by mplappert 7 days ago \| 66 comments
	tl;dr: Mixedbread has released Toast 1, a specialized search subagent designed to offload retrieval work from frontier models like GPT-5.6 and Claude Opus 5, claiming comparable search quality at up to 10× lower cost and 12× faster speeds. On benchmarks like OfficeQA Pro V2 and Harvey's Law Firm Knowledge, pairing Toast 1 with a frontier model improved accuracy while cutting token usage by 3.5×. It works with any retrieval backend, is priced at $0.30/M input and $0.72/M output tokens, and is accessible via Mixedbread's API.
	HN Discussion: ↑Enthusiasm for specialized search LLMs as a compelling and obvious use case •Interest in the tool but wanting comparisons to competitors like Perplexity, Gemini, or Voyage AI ~Skepticism or confusion about when to use this vs simpler RAG or smaller models ↓Disappointment that it's closed/proprietary rather than open weights or on-prem ~Questions about benchmark methodology and unclear article explanations