displayNamestring
Human-readable display name of the model. e.g. "My Model"
Must be fewer than 64 characters long.
descriptionstring
The description of the model. Must be fewer than 1000 characters long.
createTimestring date-time
The creation time of the model.
state'STATE_UNSPECIFIED' | 'UPLOADING' | 'READY'
- UPLOADING: The model is still being uploaded (upload is asynchronous).
- READY: The model is ready to be used.
kind'KIND_UNSPECIFIED' | 'HF_BASE_MODEL' | 'HF_PEFT_ADDON' | 'HF_TEFT_ADDON' | 'FLUMINA_BASE_MODEL' | 'FLUMINA_ADDON' | 'DRAFT_ADDON' | 'LIVE_MERGE' | 'CUSTOM_MODEL' | 'EMBEDDING_MODEL' | 'SNAPSHOT_MODEL'
- HF_BASE_MODEL: An LLM base model.
- HF_PEFT_ADDON: A parameter-efficent fine-tuned addon.
- HF_TEFT_ADDON: A token-eficient fine-tuned addon.
- FLUMINA_BASE_MODEL: A Flumina base model.
- FLUMINA_ADDON: A Flumina addon.
- DRAFT_ADDON: A draft model used for speculative decoding in a deployment.
- LIVE_MERGE: A live-merge model.
- CUSTOM_MODEL: A customized model
- EMBEDDING_MODEL: An Embedding model.
- SNAPSHOT_MODEL: A snapshot model.
githubUrlstring
The URL to GitHub repository of the model.
huggingFaceUrlstring
The URL to the Hugging Face model.
teftDetailsGatewayTEFTDetails
publicboolean
If true, the model will be publicly readable.
contextLengthinteger
The maximum context length supported by the model.
supportsImageInputboolean
If set, images can be provided as input to the model.
supportsToolsboolean
If set, tools (i.e. functions) can be provided as input to the model,
and the model may respond with one or more tool calls.
importedFromstring
The name of the the model from which this was imported. This field is empty
if the model was not imported.
fineTuningJobstring
If the model was created from a fine-tuning job, this is the fine-tuning
job name.
defaultDraftModelstring
The default draft model to use when creating a deployment. If empty,
speculative decoding is disabled by default.
defaultDraftTokenCountinteger
The default draft token count to use when creating a deployment.
Must be specified if default_draft_model is specified.
clusterstring
The resource name of the BYOC cluster to which this model belongs.
e.g. accounts/my-account/clusters/my-cluster. Empty if it belongs to
a Fireworks cluster.
calibratedboolean
If true, the model is calibrated and can be deployed to non-FP16 precisions.
tunableboolean
Deprecated: V1 training stack only — LoRA only, limited architecture support.
If the model has use_training_v2=true, use supervised_lora_tunable and
supervised_full_parameter_tunable instead.
supportsLoraboolean
Whether this model supports LoRA.
useHfApplyChatTemplateboolean
If true, the model will use the Hugging Face apply_chat_template API to apply the chat template.
updateTimestring date-time
The update time for the model.
defaultSamplingParamsobject
A json object that contains the default sampling parameters for the model.
rlTunableboolean
Deprecated: V1 training stack only — LoRA only, limited architecture support.
If the model has use_training_v2=true, use rl_lora_tunable and
rl_full_parameter_tunable instead.
trainingContextLengthinteger
The maximum context length supported by the model.
snapshotType'FULL_SNAPSHOT' | 'INCREMENTAL_SNAPSHOT'
supportsServerlessboolean
If true, the model has a serverless deployment.
useTrainingV2boolean
If true, SFT jobs for this base model use service-mode (StatefulSet +
orchestration sidecar) instead of the legacy batch Job path.
supervisedLoraTunableboolean
V2 only. Whether the model supports LoRA supervised fine-tuning and DPO (lora_rank > 0).
True when a validated LORA_TRAINER training shape exists.
supervisedFullParameterTunableboolean
V2 only. Whether the model supports full-parameter supervised fine-tuning and DPO (lora_rank = 0).
True when a validated POLICY_TRAINER training shape exists.
rlLoraTunableboolean
V2 only. Whether the model supports LoRA reinforcement learning (lora_rank > 0).
True when a validated LORA_TRAINER training shape exists plus a deployment shape.
rlFullParameterTunableboolean
V2 only. Whether the model supports full-parameter reinforcement learning (lora_rank = 0).
True when validated POLICY_TRAINER + LORA_TRAINER training shapes exist plus a deployment shape.
encryptionState'ENCRYPTION_STATE_UNSPECIFIED' | 'ENCRYPTION_STATE_PLAINTEXT' | 'ENCRYPTION_STATE_CMEK'
EncryptionState is the authoritative, per-resource CMEK marker: the single
source of truth for whether a resource's customer-data artifacts are
encrypted. It is stamped at resource creation from the owning account's CMEK
config and is immutable for the resource's life, so a resource always reads
back with the state it was created under regardless of the account's current
flag. The encrypt-on-write / decrypt-on-read decision for the resource's
data keys off this field.
- ENCRYPTION_STATE_UNSPECIFIED: Unstamped/legacy rows that predate CMEK. Treated as PLAINTEXT.
- ENCRYPTION_STATE_PLAINTEXT: Customer-data artifacts are stored as plaintext (Fireworks-owned, no CMEK).
- ENCRYPTION_STATE_CMEK: Customer-data artifacts are CMEK-encrypted; reads MUST decrypt (fail-closed).