ModelList

objectObject (string)

Constant value: list

Default value: list

data object[]required

Array [

idId (string)required

objectObject (string)

Default value: model

createdCreated (integer)

owned_byOwned By (string)

Default value: skulk

hugging_face_idHugging Face Id (string)

Default value:

nameName (string)

Default value:

descriptionDescription (string)

Default value:

context_lengthContext Length (integer)

Default value: 0

tagsstring[]

Default value: []

storage_size_megabytesStorage Size Megabytes (integer)

Default value: 0

supports_tensorSupports Tensor (boolean)

Default value: false

tasksstring[]

Default value: []

is_customIs Custom (boolean)

Default value: false

familyFamily (string)

Default value:

quantizationQuantization (string)

Default value:

base_modelBase Model (string)

Default value:

source_revision object

Immutable Hugging Face source commit used for this model's qualified artifacts, or null when the card follows mutable main.

anyOf

• string
• null

string

Possible values: Value must match regular expression ^[0-9a-f]{40}$

capabilitiesstring[]

Coarse catalog capability labels such as text, vision, thinking, or embedding.

reasoning object

Optional declarative reasoning controls from the model card.

anyOf

• ReasoningCapabilitySection
• null

supports_toggle object

anyOf

• boolean
• null

boolean

supports_budget object

anyOf

• boolean
• null

boolean

format object

anyOf

• string
• null

string

default_effort object

anyOf

• string
• null

string

Possible values: [none, minimal, low, medium, high, xhigh]

disabled_effort object

anyOf

• string
• null

string

Possible values: [none, minimal, low, medium, high, xhigh]

modalities object

Optional declarative modality support details from the model card.

anyOf

• ModalitiesCapabilitySection
• null

supports_audio_input object

anyOf

• boolean
• null

boolean

supports_native_multimodal object

anyOf

• boolean
• null

boolean

audio object

Optional declarative speech-serving metadata from the model card.

anyOf

• AudioCapabilitySection
• null

kind object

Speech serving kind declared by the card: tts or stt.

anyOf

• string
• null

string

default_response_format object

Default encoded audio response format for TTS requests.

anyOf

• string
• null

string

response_formatsstring[]

Encoded audio response formats declared for TTS requests.

supports_streaming object

Whether the card declares streaming speech support after runtime validation.

anyOf

• boolean
• null

boolean

supports_realtime object

Whether the model declares realtime audio session support.

anyOf

• boolean
• null

boolean

supports_voice_listing object

Whether the model declares voice-listing support.

anyOf

• boolean
• null

boolean

default_voice object

Stable voice used when a request omits an explicit voice.

anyOf

• string
• null

string

voicesstring[]

Stable built-in or bundled-reference voice identifiers.

supports_reference_audio object

Whether the model accepts managed reference audio.

anyOf

• boolean
• null

boolean

supports_translation object

Whether the model declares speech translation support.

anyOf

• boolean
• null

boolean

sample_ratesinteger[]

Declared input or output sample rates in hertz.

tooling object

Optional declarative tool-calling metadata from the model card.

anyOf

• ToolingCapabilitySection
• null

supports_tool_calling object

anyOf

• boolean
• null

boolean

builtin_tools object

anyOf

• string[]
• null

Array [

string

]

tool_call_format object

anyOf

• string
• null

string

runtime object

Optional declarative runtime integration hints from the model card.

anyOf

• RuntimeCapabilitySection
• null

prompt_renderer object

anyOf

• string
• null

string

output_parser object

anyOf

• string
• null

string

mtp_sidecar_repo object

Repo of this model's MTP sidecar (prediction heads), when it declares one. The sidecar is a companion loaded alongside the base model, not an independently placeable model. Lets clients mark the sidecar repo as a companion rather than a launchable entry.

anyOf

• string
• null

string

assistant_model_repo object

Repo of this model's speculative-decoding assistant (drafter), when it declares one. A companion loaded with the base model, not independently placeable.

anyOf

• string
• null

string

served_spec_draft_repo object

Repo of this model's served-engine draft GGUF, when it declares a separate one. A companion loaded with the base model, not independently placeable.

anyOf

• string
• null

string

resolved_capabilities object

Normalized runtime capabilities resolved from the model card and model-family defaults for the default tool-free request path. Request-specific options such as tools may change some resolved values.

anyOf

• ResolvedModelCapabilities
• null

familyFamily (string)

Resolved model family used for runtime behavior decisions.

Default value:

supports_thinkingSupports Thinking (boolean)

Whether the runtime expects the model to expose a reasoning or thinking mode.

Default value: false

supports_thinking_toggleSupports Thinking Toggle (boolean)

Whether thinking can be explicitly enabled or disabled for requests.

Default value: false

supports_thinking_budgetSupports Thinking Budget (boolean)

Whether the runtime expects the model to accept a thinking or reasoning budget control.

Default value: false

default_reasoning_effortDefault Reasoning Effort (string)

Reasoning effort used when thinking is enabled without an explicit effort override.

Possible values: [none, minimal, low, medium, high, xhigh]

Default value: medium

disabled_reasoning_effortDisabled Reasoning Effort (string)

Reasoning effort used when thinking is explicitly disabled.

Possible values: [none, minimal, low, medium, high, xhigh]

Default value: none

thinking_formatThinking Format (string)

Resolved reasoning marker format expected from this model family.

Default value: none

supports_image_inputSupports Image Input (boolean)

Whether the runtime should treat the model as accepting image inputs.

Default value: false

supports_audio_inputSupports Audio Input (boolean)

Whether the runtime should treat the model as accepting audio inputs.

Default value: false

supports_speech_synthesisSupports Speech Synthesis (boolean)

Whether the runtime should treat the model as a text-to-speech model.

Default value: false

supports_transcriptionSupports Transcription (boolean)

Whether the runtime should treat the model as a speech-to-text model.

Default value: false

supports_speech_translationSupports Speech Translation (boolean)

Whether the runtime should treat the model as supporting speech translation.

Default value: false

supports_audio_outputSupports Audio Output (boolean)

Whether the runtime should expect this model to produce audio output.

Default value: false

supports_realtime_audioSupports Realtime Audio (boolean)

Whether the runtime should expect this model to expose realtime audio sessions.

Default value: false

default_audio_response_format object

Default encoded audio response format for speech synthesis, when declared.

anyOf

• string
• null

string

audio_response_formatsstring[]

Encoded audio response formats the model can produce.

supports_tool_callingSupports Tool Calling (boolean)

Whether the runtime expects the model to support structured tool calling.

Default value: false

builtin_toolsstring[]

Builtin platform tool contracts that Skulk may expose to this model family.

tool_call_formatTool Call Format (string)

Resolved tool-call output format family used for parsing.

Default value: generic

prompt_rendererPrompt Renderer (string)

Resolved prompt renderer strategy used to prepare requests for this model.

Default value: tokenizer

output_parserOutput Parser (string)

Resolved output parser strategy used to interpret model responses.

Default value: generic

supports_native_multimodalSupports Native Multimodal (boolean)

Whether the runtime can use a native multimodal execution path for the model.

Default value: false

]

ModelList

{
  "object": "list",
  "data": [
    {
      "id": "string",
      "object": "model",
      "created": 0,
      "owned_by": "skulk",
      "hugging_face_id": "",
      "name": "",
      "description": "",
      "context_length": 0,
      "tags": [
        "string"
      ],
      "storage_size_megabytes": 0,
      "supports_tensor": false,
      "tasks": [
        "string"
      ],
      "is_custom": false,
      "family": "",
      "quantization": "",
      "base_model": "",
      "source_revision": "string",
      "capabilities": [
        "string"
      ],
      "reasoning": {
        "supports_toggle": true,
        "supports_budget": true,
        "format": "string",
        "default_effort": "none",
        "disabled_effort": "none"
      },
      "modalities": {
        "supports_audio_input": true,
        "supports_native_multimodal": true
      },
      "audio": {
        "kind": "string",
        "default_response_format": "string",
        "response_formats": [
          "string"
        ],
        "supports_streaming": true,
        "supports_realtime": true,
        "supports_voice_listing": true,
        "default_voice": "string",
        "voices": [
          "string"
        ],
        "supports_reference_audio": true,
        "supports_translation": true,
        "sample_rates": [
          0
        ]
      },
      "tooling": {
        "supports_tool_calling": true,
        "builtin_tools": [
          "string"
        ],
        "tool_call_format": "string"
      },
      "runtime": {
        "prompt_renderer": "string",
        "output_parser": "string",
        "mtp_sidecar_repo": "string",
        "assistant_model_repo": "string",
        "served_spec_draft_repo": "string"
      },
      "resolved_capabilities": {
        "family": "",
        "supports_thinking": false,
        "supports_thinking_toggle": false,
        "supports_thinking_budget": false,
        "default_reasoning_effort": "medium",
        "disabled_reasoning_effort": "none",
        "thinking_format": "none",
        "supports_image_input": false,
        "supports_audio_input": false,
        "supports_speech_synthesis": false,
        "supports_transcription": false,
        "supports_speech_translation": false,
        "supports_audio_output": false,
        "supports_realtime_audio": false,
        "default_audio_response_format": "string",
        "audio_response_formats": [
          "string"
        ],
        "supports_tool_calling": false,
        "builtin_tools": [
          "string"
        ],
        "tool_call_format": "generic",
        "prompt_renderer": "tokenizer",
        "output_parser": "generic",
        "supports_native_multimodal": false
      }
    }
  ]
}