Create Model

ID of the model.

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.

Human-readable display name of the model. e.g. "My Model" Must be fewer than 64 characters long.

The description of the model. Must be fewer than 1000 characters long.

The creation time of the model.

• UPLOADING: The model is still being uploaded (upload is asynchronous).
• READY: The model is ready to be used.

• 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.

The URL to GitHub repository of the model.

The URL to the Hugging Face model.

If true, the model will be publicly readable.

The maximum context length supported by the model.

If set, images can be provided as input to the model.

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.

The name of the the model from which this was imported. This field is empty if the model was not imported.

If the model was created from a fine-tuning job, this is the fine-tuning job name.

The default draft model to use when creating a deployment. If empty, speculative decoding is disabled by default.

The default draft token count to use when creating a deployment. Must be specified if default_draft_model is specified.

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.

If true, the model is calibrated and can be deployed to non-FP16 precisions.

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.

Whether this model supports LoRA.

If true, the model will use the Hugging Face apply_chat_template API to apply the chat template.

The update time for the model.

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.

The maximum context length supported by the model.

If true, the model has a serverless deployment.

If true, SFT jobs for this base model use service-mode (StatefulSet + orchestration sidecar) instead of the legacy batch Job path.

V2 only. Whether the model supports LoRA supervised fine-tuning and DPO (lora_rank > 0). True when a validated LORA_TRAINER training shape exists.

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.

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.

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 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).