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
List AI models
Lists the admitted catalog; filter by `brand`, `modality`, or `model`.
Lists the admitted catalog; filter by brand, modality, or model.
- Path
GET https://api.sylphx.ai/v1/models— the AI gateway atapi.sylphx.ai, notapi.sylphx.com - Contract address
/v1/ai_models - Scope
ai:read - Effect
read— nothing is written. - Collection ai_models
- Query
page_size,page_token,filter,order_by - Pagination the answer carries
ai_modelsand, when there is more,next_page_token - Publishable key callable
#Request
| Field | Type | What it is |
|---|---|---|
page_size | int32 | At most this many; default 50, clamped to 1000. |
page_token | string | next_page_token of the previous page. |
filter | string | AIP-160 filter over labels and filterable fields. |
order_by | string | AIP-132 ordering over filterable fields. |
#Response
| Field | Type | What it is |
|---|---|---|
ai_models | AiModel[] | The page. |
next_page_token | string | The token of the next page; empty on the last page. |
#AiModel
| Field | Type | What it is |
|---|---|---|
name | string | ai_models/{ai_model}. |
uid | string | aim_<cell><ulid>; never reused. Output only. |
meta | ResourceMeta | Resource metadata. |
model | string | The canonical model id, brand/model, for example anthropic/claude-opus-5. Output only. |
brand | string | The brand, for example anthropic. Output only. |
aliases | string[] | Bare spellings that resolve to this model when unique, for example claude-opus-5. Output only. |
modality | ModelModality | What the model produces. Output only. One of chat, embedding, image, speech, transcription, video, decision. |
input_modalities | InputModality[] | Accepted input modalities, for example text and image. Output only. One of text, image, audio, file, video. |
api_surfaces | ApiSurface[] | Inference encodings the model answers on. Output only. One of responses, messages, chat_completions, embeddings, images, speech, transcription. |
context_window_tokens | int64 | Context window in tokens. Output only. |
max_output_tokens | int64 | Most output tokens per response. Output only. |
release_time | timestamp | The upstream release date. Output only. |
preview | bool | Whether the model is a preview. Output only. |
prices | ModelPrice[] | Sell prices per meter and class; the only prices on an entry. Output only. |
price_identity | string | The price identity usage events carry, for example spv3-.... Output only. |
data_policy | DataPolicy | How request and response data are retained and used. Output only. |
caching | ModelCaching | How long a prompt-cache prefix stays warm on this model, and the longest retention a request may ask for; unset when no serving lane declares it. Output only. |
#ResourceMeta
| Field | Type | What it is |
|---|---|---|
generation | int64 | Increases by one on every change to spec. Output only. |
etag | string | Strong ETag (AIP-154): changes on any change to spec, status, or metadata. Send it back as If-Match or etag to make Update and Delete conditional; a mismatch fails with ABORTED / 409 ETAG_MISMATCH. Output only. |
create_time | timestamp | When the Resource was created. Output only. |
update_time | timestamp | When the Resource last changed. Output only. |
delete_time | timestamp | Set while the Resource is being deleted. Output only. |
labels | map<string, string> | Caller-writable, indexed labels (AIP-122 label rules). |
annotations | map<string, string> | Caller-writable, unindexed annotations. |
display_name | string | Caller-writable human-readable name. |
creator | string | The principal that created the Resource. Output only. |
#ModelPrice
| Field | Type | What it is |
|---|---|---|
meter | string | The meter, for example ai.tokens. Output only. |
price_class | string | The meter dimension class, for example input, cached_input, output, reasoning, cache_write (writing a prompt-cache prefix at the default retention), or cache_write_1h (writing it at the extended retention). Output only. |
unit | string | The unit the price is per, for example 1M tokens or image. Output only. |
currency_code | string | ISO 4217 currency. Output only. |
unit_price | string | The price as a decimal string, for example 1.2; never a float. Output only. |
#DataPolicy
| Field | Type | What it is |
|---|---|---|
retains_prompts | bool | Whether Sylphx or the upstream retains prompts beyond the request. Output only. |
trains_on_prompts | bool | Whether the upstream may train on prompts. Output only. |
response_retention | duration | Stored responses expire after this long (7 days). Output only. |
#ModelCaching
| Field | Type | What it is |
|---|---|---|
ttl | duration | How long a cached prefix stays warm after its last use with the default retention, for example 300 seconds. Output only. |
extended_ttl | duration | The longest retention a request may ask for with prompt_cache_retention: "24h", for example one hour on a lane whose longest native breakpoint is one hour; zero when no longer retention exists. A prefix written at this retention bills at the cache_write_1h price. Output only. |
#Errors
UNAUTHENTICATED— No valid key or token was presented.PERMISSION_DENIED— The key lacks the method's permission.INVALID_FIELD— A field failed validation.PAGE_TOKEN_MISMATCH— A page token was reused with different parameters.
Every error arrives in the body Errors describes.
#Examples
curl "https://api.sylphx.com/v1/ai_models" \
-H "Authorization: Bearer $SYLPHX_API_KEY"