---
title: "Get model limits"
method: GET
path: "/v1/fine-tunes/models/limits"
tags: ["Fine-tuning"]
---

# Get model limits

`GET /v1/fine-tunes/models/limits`

## Request

- Base URL: `https://api.together.ai`
- URL: `https://api.together.ai/v1/fine-tunes/models/limits`
- Auth: HTTP bearer

Get model limits for a specific fine-tuning model.

## Query parameters

- `model_name` string, required: The model name to get limits for.

## Response `200`

Model limits.

- FineTuneModelLimits: Model limits for fine-tuning.
  - `model_name` string, required: The name of the model.
  - `full_training` object: Limits for full training.
    - `max_batch_size` integer, required: Maximum batch size for SFT full training.
    - `max_batch_size_dpo` integer, required: Maximum batch size for DPO full training.
    - `min_batch_size` integer, required: Minimum batch size for full training.
  - `lora_training` object, required: Limits for LoRA training.
    - `max_batch_size` integer, required: Maximum batch size for SFT LoRA training.
    - `max_batch_size_dpo` integer, required: Maximum batch size for DPO LoRA training.
    - `min_batch_size` integer, required: Minimum batch size for LoRA training.
    - `max_rank` integer, required: Maximum LoRA rank.
    - `default_rank` integer, required: Default LoRA rank applied when a fine-tune request omits training_type.
    - `target_modules` string[], required: Available target modules for LoRA.
  - `max_num_epochs` integer, required: Maximum number of training epochs.
  - `max_num_evals` integer, required: Maximum number of evaluations.
  - `max_learning_rate` number, required: Maximum learning rate.
  - `min_learning_rate` number, required: Minimum learning rate.
  - `supports_full_training` boolean, required: Whether the model supports full (non-LoRA) fine-tuning. When false, only LoRA fine-tuning is available and the full_training limits are reported as zero.
  - `supports_vision` boolean, required: Whether the model supports vision/multimodal inputs.
  - `supports_tools` boolean, required: Whether the model supports tool/function calling.
  - `supports_reasoning` boolean, required: Whether the model supports reasoning.
  - `merge_output_lora` boolean, required: Whether a merged checkpoint (the base model with the trained LoRA adapter fused in) is produced for LoRA fine-tunes of this model, in addition to the standalone adapter.
  - `default_gradient_accumulation_steps` integer, required: Default gradient accumulation steps used when a fine-tune request omits the value or sets it to 0.
  - `max_num_checkpoints` integer, required: Maximum number of checkpoints that can be saved during a fine-tuning job.
  - `min_max_seq_length` integer, required: Minimum value allowed for the max_seq_length hyperparameter.
  - `max_seq_length_sft` integer, required: Maximum sequence length supported for SFT training.
  - `max_seq_length_dpo` integer, required: Maximum sequence length supported for DPO training.

## Other responses

- `404`: Model not found or not supported for fine-tuning.

## Changes

- **2026-10-22** `bb5257b3173a`: 1 info
  - endpoint added

[Operation history](https://skmtc.dev/together/apis/together-apis/changes/v1/fine-tunes/models/limits/get.md)

---

[API](https://skmtc.dev/together/apis/together-apis.md) - [All operations](https://skmtc.dev/together/apis/together-apis/llms.txt) - [OpenAPI document](https://skmtc.dev/together/apis/together-apis/revisions/93438ddac711?raw)