Models
Choose a Mixedbread specialized model for knowledge tasks based on your needs.
Available models
Specialized search model
Toast 1
Built for knowledge-intensive questions, multi-step retrieval, and evidence synthesis. Toast 1 can work with any backend exposed through function calling.
Model ID
toast-1- Input
- Text
- Output
- Text
- Context window
- 131K tokens
- Max output
- 4K tokens
The context window includes input messages, tool definitions, tool results, and
generated output. Use max_output_tokens with the Responses API or
max_completion_tokens with Chat Completions to limit generated output.
The Responses API and Chat Completions default to toast-1 when model is
omitted.