Syntic Code model card
Links on this page to features marked Preview describe designs that are not available yet.
Tuned for software work: reading code, writing patches, and running tool loops through files and shells. It powers the Syntic Code CLI.
At a glance
| Property | Value |
|---|---|
| Model id | Syntic Code (exact string, spaces and capitals included) |
| Family | Syntic Code |
| Context window | 262,144 tokens, prompt and reply together |
| Maximum output | 32,768 tokens |
| Input / cached input / output | 2.50 / 0.25 / 12.50 dollars per million tokens, when paid from usage credits |
| Plan availability | Confirm in GET /v1/models for your organization |
| Input types | Text today; images and documents with Vision and PDF support as they ship |
| Tool calling | Yes, with tools and tool_choice |
| Streaming | Yes, on by default |
| Sampling controls | Fixed today; temperature and top_p are accepted and ignored |
| Prompt caching | Automatic |
| Lifecycle | Active |
Good for
- Coding agents and IDE assistants
- Code review and refactoring
- Tool loops with the text editor and shell tools
- Generating tests and migrations
Consider another model for
- General conversation and non-technical writing, where the Amara models are the better fit.
Using it well
Pair it with the standard tools (syntic_text_editor, syntic_shell): it is trained to use them consistently.
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": "Syntic Code", "messages": [{ "role": "user", "content": "Hello" }] }Was this page helpful?