estimate_training_price
Estimate the Creative Units cost of training a LoRA for a reference set.
Read-only. Resolves and validates the base model the same way start_training would, then prices the run.
Errors: unknown-base-model (id not trainable), unsupported-training-framework (framework not
available for this base model), unsupported-training-parameter (a training_parameters field the
framework does not take), invalid-training-parameter (a training_parameters value the model's
trainer does not accept), model-disabled (base model disabled for this workspace),
invalid-dataset (reference set not found or has no training images).
IMPORTANT: Call tool `get_instructions` first for general platform guidance.
Parameters
| Parameter | Type | Default | Description |
|---|---|---|---|
project_id | string (uuid) | — | Optional project the work would be filed in: the models and defaults answered are those a run in it gets. Use `list_projects` to find project ids. Without it, the answer is for the workspace. |
reference_set_idrequired | string (uuid) | — | The reference set (Style) to price training for. |
base_model_id | string | — | Base model to train. Omit to use the reference set's configured or the workspace's default model. |
training_framework | enum | — | Training framework override. Omit for the server default (see start_training). One of: fal, ai-toolkit, voice-clone, voice-design, voice-import |
training_parameters | TrainingOverrides | — | Settings to price the run with, as start_training takes them. Omit for the saved settings. |
epochs | integer1–300 | — | Number of passes over the training images. |
repeats | integer1–50 | — | Times each image is seen within one epoch, so one epoch is (images x repeats) steps. Offered by the kohya and ai-toolkit frameworks only. |
learning_rate | number≤0.01, >0 | — | Optimizer learning rate. |
lora_rank | integer1–128 | — | LoRA rank (network dimension). |
training_prompt | string1–1000 chars | — | A description of the voice to design: age, accent, tone, pacing. Offered by the voice-design framework only. |
voice_id | string1–64 chars | — | The ElevenLabs voice ID to import: a voice from the public ElevenLabs voice library, or one made on Layer. A voice private to another ElevenLabs account can't be reached, and a voice ID that can't be used fails the run. Offered by the voice-import framework only. |
loudness | number-1–1 | — | Loudness of the designed voice. Offered by ElevenLabs voice-design only. |
guidance_scale | number0–100 | — | How closely the designed voice follows the prompt. Offered by ElevenLabs voice-design only. |
prompt_strength | number0–1 | — | Weight of the prompt against a reference clip, when the reference set holds one. Offered by ElevenLabs voice-design only. |
workspace_idrequired | string (uuid) | — | The user's workspace ID. |