Amara Quick model card

Built for short, frequent exchanges where a fast answer and a low bill matter most.

At a glance

Good for

• Classification, routing and tagging at volume
• Autocomplete and quick rewrites in a product UI
• First-pass triage before a stronger model
• Sub-agents doing routine lookups inside an agent

Consider another model for

• Answers that need several reasoning steps; it will be faster but more often wrong than Amara Deep.
• Long, nuanced writing where Amara S1.2 reads better.

Using it well

The cached-input rate (0.25) makes Quick especially cheap for classification against a long, stable instruction block. Keep the instructions at the start of the prompt so caching applies.

Evaluation results

Syntic publishes benchmark results and safety evaluation summaries for each model on this page when they are complete. Until then, measure on your own task: the method in Choosing a model with 20 to 50 real inputs tells you more about fit than any public benchmark.

Safety and data handling

• Requests pass Syntic’s platform safeguards before reaching the model, and organizations can add their own inference policy hook.
• Prompts and outputs are not used to train models.
• Retention follows your organization’s data retention settings. Check Models overview for whether this model is available to zero-data-retention organizations.

Request

{ "model": "Amara Quick", "messages": [{ "role": "user", "content": "Hello" }] }