Menu
Platform
AI
App store purchases
Database
Flags
Jobs and cron
Localization
Monitoring
Notifications
Payments
Queues
Sandboxes
Webhooks
Getting Started
Authentication
KV Store
Deploy & Infrastructure
Reference
On this page
AI models, limits and data policy
The catalogue fields, and how to read them before you switch models
The catalogue lists the models Sylphx AI serves. The model pages show it in full — context window, maximum output, data policy and a ready-to-copy request for every model — and read it from the same catalogue this API serves, so the page and the API cannot disagree.
#Listing models
Two doors serve the catalogue: one for your key, one public.
curl https://api.sylphx.ai/v1/models \
-H "Authorization: Bearer $SYLPHX_API_KEY"
# One model document:
curl https://api.sylphx.ai/v1/models/openai/gpt-5.5 \
-H "Authorization: Bearer $SYLPHX_API_KEY"curl https://api.sylphx.ai/v1/public/models
# One public model, including its description:
curl https://api.sylphx.ai/v1/public/models/openai/gpt-5.5| Field | Type | What it is |
|---|---|---|
id | string | The exact string you send as model. Ids are stable product names. |
display_name | string | The human label for pickers and tables. |
pricing | object | input, output, cache_read, currency and unit. Present on the API; the website shows prices only once billing is live. |
limits | object | context_window_tokens and max_output_tokens, null when not published. |
data_policy | object | The default routing posture, below. |
#Switching models
Because model is a field, a switch is a one-line change. The request and
stream shape stay identical.
{
"model": "qwen/qwen3.8-flash",
"input": "Summarise this incident report in three bullets."
}Read the new model's page first: context window, maximum output and data policy can differ. A conversation that used provider-sealed state should stay on the family that produced it; see switching models safely.
#Data policy
Each catalogue row publishes the default routing posture for that model: whether API data may be used for training, and whether zero data retention (ZDR) applies. By default, requests route to zero-data-retention routes.
trainandzdrare booleans describing that default.zdris false when no ZDR route exists for the model.postureisstandardorconsent_trained;sourceismodel_declarationordefault;default_routingiszdr_required.training_opt_inis true when lower-cost options that may train on data exist for the model. They are reached only when the caller sendsx-sylphx-zdr: optional; without that header a request never uses them.- The posture belongs to the model row, not to your key, so switching models can change it. Check it before you move a sensitive workload.
- Retention of stored responses and files is separate; see the privacy policy.