Amara S1.2 model card

The default model for general work: drafting, analysis, coding help and conversation. When a request names no model, this is the one that answers.

At a glance

Good for

• Customer-facing assistants that need a reliable all-rounder
• Drafting and editing documents, emails and summaries
• Analysis of supplied documents and data
• Coding help in chat, and tool use at moderate depth

Consider another model for

• Tasks that are mostly short, frequent lookups: Amara Quick is cheaper and faster.
• Long multi-step reasoning where correctness matters more than speed: try Amara Deep.
• Sustained software engineering with many tool calls: Syntic Code.

Using it well

Because it is also the fallback for unrecognised model names today, a typo elsewhere in your code ends up here. Log the x-syntic-model-downgraded header and keep model names in configuration.

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 S1.2", "messages": [{ "role": "user", "content": "Hello" }] }