---
title: "Estimate price"
method: POST
path: "/fine-tunes/estimate-price"
tags: ["Fine-tuning"]
---

# Estimate price

`POST /fine-tunes/estimate-price`

Estimate the price of a fine-tuning job.

## Request body

- object
  - `training_file` string, required — File-ID of a training file uploaded to the Together API
  - `validation_file` string — File-ID of a validation file uploaded to the Together API
  - `model` string — Name of the base model to run fine-tune job on
  - `n_epochs` integer — Number of complete passes through the training dataset (higher values may improve results but increase cost and risk of overfitting)
  - `n_evals` integer — Number of evaluations to be run on a given validation set during training
  - `training_method` union — The training method to use. 'sft' for Supervised Fine-Tuning or 'dpo' for Direct Preference Optimization.
    - object
      - `method` 'sft', required
      - `train_on_inputs` boolean, required — Whether to mask user messages in conversational data or prompts in instruction data.
    - object
      - `method` 'dpo', required
      - `dpo_beta` number
      - `rpo_alpha` number
      - `dpo_normalize_logratios_by_length` boolean
      - `dpo_reference_free` boolean
      - `simpo_gamma` number
  - `training_type` union — The training type to use. Defaults to LoRA if not provided.
    - object
      - `type` 'Full', required
    - object — LoRA training configuration for a fine-tuning job.
      - `type` 'Lora', required — Identifies this request as a LoRA fine-tune.
      - `lora_r` integer, required — Rank of the LoRA adapter matrices.
      - `lora_alpha` integer, required — Scaling factor applied to the LoRA adapter weights.
      - `lora_dropout` number — Dropout probability applied to LoRA adapter inputs.
      - `lora_trainable_modules` string — Comma-separated LoRA target modules. Use `all-linear` for model defaults; MoE expert modules (`w_up`, `w_gate`, `w_down`) can be combined with attention modules on compatible models. Fine-tunes that target any expert module produce adapter-only output.
  - `from_checkpoint` string — The checkpoint identifier to continue training from a previous fine-tuning job. Format is `{$JOB_ID}` or `{$OUTPUT_MODEL_NAME}` or `{$JOB_ID}:{$STEP}` or `{$OUTPUT_MODEL_NAME}:{$STEP}`. The step value is optional; without it, uses the final checkpoint.

## Response `200`

Price estimated successfully

- union
  - object
    - `estimation_available` true, required — Whether price estimation is available for the requested fine-tune job.
    - `estimated_total_price` number — The price of the fine-tuning job
    - `allowed_to_proceed` boolean — Whether you are allowed to proceed with the fine-tuning job.
    - `user_limit` number — Your credit limit in dollars.
    - `estimated_train_token_count` number — The estimated number of tokens to be trained
    - `estimated_eval_token_count` number — The estimated number of tokens for evaluation
  - object
    - `estimation_available` false, required — Whether price estimation is available for the requested fine-tune job.
    - `unavailable_reason` 'multimodal_dataset' | 'train_file_not_validated' | 'eval_file_not_validated' | 'train_file_invalid' | 'eval_file_invalid', required — Reason price estimation is unavailable for the requested fine-tune job.

## Other responses

- `500` — Internal Server Error

---

[API](https://skmtc.net/together/apis/together-apis.md) · [All operations](https://skmtc.net/together/apis/together-apis/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/together/together-apis/revisions/468edbdc879c/schema)