Mixedbread releases Toast 1: Beats Fable 5 in deep search, slashes pricing
bclavie · x · 2026-08-18
Mixedbread AI has launched a new model, Toast 1, claiming it outperforms Fable 5 in deep search tasks and helps users save tokens. The model is now available on the Mixedbread API with significantly reduced launch pricing: input is down to $0.30/1M, output to $0.72/1M, and cached input to $0.036/1M. The API is OpenAI-compatible, and new signups receive $5 in credits.
More from Models
- Qwen 3.8 and DeepSeek V4 Signal End of Compute Wealth Gap — AccBalanced · 2026-08-18
- User reports Codex usage draining unusually fast compared to Ultracode — StewartalsopIII · 2026-08-18
- Grok 4.6 tops agentic benchmark, halves cost vs Claude rival — elonmusk · 2026-08-18
- Qwen 2.5 27B Runs at 100+ tok/s on RTX 5090 — Hesamation · 2026-08-18
- Conspiracy Theory: OpenAI Adds Artifacts to Thwart Model Distillation — flowersslop · 2026-08-18
- Qwen 72B runs on RTX 5090 at 115 tokens/sec, BF16 weights 55.6GB — AccBalanced · 2026-08-18