---
title: "List supported models"
method: GET
path: "/v1/rl/supported-models"
tags: ["RL"]
---

# List supported models

`GET /v1/rl/supported-models`

## Request

- Base URL: `https://api.together.ai`
- URL: `https://api.together.ai/v1/rl/supported-models`
- Auth: HTTP bearer

Returns the models supported by the RL service and their limits for training/sampling operations.

## Response `200`

List of supported RL models

- RLSupportedModelsListResponse: List of base models supported by the RL service
  - `data` RLSupportedModel[], required: Supported base models for RL
    - `base_model` string, required: Base model identifier to pass as base_model when creating a model resource
    - `default_gpu_type` 'B200-SXM', required: GPU type used when model-resource creation omits gpu_type.
    - `compute_configs` RLSupportedModelComputeConfig[]: Validated GPU configurations available for this base model.
      - `gpu_type` 'B200-SXM', required: GPU type this configuration provisions.
      - `trainer_config` RLModelTrainerConfig: Training capabilities and limits for a model on one GPU type. Each sub-mode is present only when the model supports that training mode.
        - `full` RLModelFullModeConfig: Full-weight training config. If present, the model supports full-weight training.
          - `max_batch_size` integer, required: Maximum global batch size accepted by a forward-backward step
          - `max_seq_length` integer, required: Maximum sequence length in tokens
        - `lora` RLModelLoraModeConfig: LoRA training config. If present, the model supports LoRA training.
          - `max_batch_size` integer, required: Maximum global batch size accepted by a forward-backward step
          - `max_seq_length` integer, required: Maximum sequence length in tokens
          - `max_rank` integer, required: Maximum LoRA rank
      - `generator_config` RLModelGeneratorConfig: Inference capabilities and limits for a model on one GPU type. If present, the model can be provisioned with one or more generator replicas.
        - `context_length` integer, required: Maximum tokens in a single inference request (prompt + completion)
        - `sampling_defaults` RLModelSamplingDefaults, required: Default sampling parameters used for a Sample request.
          - `n` integer, required: Number of completions per prompt
          - `max_tokens` integer, required: Maximum tokens generated per completion
          - `temperature` number, required: Sampling temperature
          - `logprobs` integer, required: Number of logprobs to return per token

## Other responses

- `429`: Rate limit exceeded.
- `default`: An unexpected error response.

## Changes

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

[Operation history](https://skmtc.dev/together/apis/together-apis/changes/v1/rl/supported-models/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)