> ## Documentation Index > Fetch the complete documentation index at: https://docs.together.ai/llms.txt > Use this file to discover all available pages before exploring further. # List checkpoints > Lists training and inference checkpoints owned by the caller, newest first. Filter by type, session, or base model, for example to recover a checkpoint ID for resume. ## OpenAPI ````yaml openapi.yaml GET /rl/checkpoints openapi: 3.1.0 info: title: Together APIs description: The Together REST API. See https://docs.together.ai for more details. version: 2.0.0 termsOfService: https://www.together.ai/terms-of-service contact: name: Together Support url: https://www.together.ai/contact license: name: MIT url: https://github.com/togethercomputer/openapi/blob/main/LICENSE servers: - url: https://api.together.ai/v1 description: Default environment for APIs - url: https://api-inference.together.ai/v2 description: Optimized environment for inference security: - bearerAuth: [] paths: /rl/checkpoints: get: tags: - RL summary: List checkpoints description: >- Lists training and inference checkpoints owned by the caller, newest first. Filter by type, session, or base model, for example to recover a checkpoint ID for resume. operationId: listCheckpoints parameters: - name: session_id in: query required: false schema: description: Only return checkpoints produced by this training session type: string - name: base_model in: query required: false schema: description: >- Only return checkpoints trained from this base model. Match is exact. type: string - name: limit in: query required: false schema: description: Maximum number of checkpoints to return (1-100) type: integer default: 20 - name: after in: query required: false schema: description: >- Cursor for pagination (ID of the last checkpoint from the previous page) type: string - name: type in: query required: false schema: description: >- Only return checkpoints of this type. CHECKPOINT_TYPE_TRAINING is the full training state (weights and optimizer state), for resuming a training session with its optimizer state; CHECKPOINT_TYPE_INFERENCE is a model ready for serving or download, also added to your models. When set, it must be CHECKPOINT_TYPE_TRAINING or CHECKPOINT_TYPE_INFERENCE; when omitted, checkpoints of both types are returned. enum: - CHECKPOINT_TYPE_TRAINING - CHECKPOINT_TYPE_INFERENCE type: string responses: '200': description: List of checkpoints content: application/json: schema: $ref: '#/components/schemas/RL.CheckpointsListResponse' default: description: An unexpected error response. content: application/json: schema: $ref: '#/components/schemas/ErrorData' components: schemas: RL.CheckpointsListResponse: type: object description: A page of checkpoints required: - data - meta properties: data: type: array items: $ref: '#/components/schemas/RL.Checkpoint' description: Checkpoints in this page meta: $ref: '#/components/schemas/RL.ListMeta' description: Pagination metadata ErrorData: type: object required: - error properties: error: type: object properties: message: type: string nullable: false type: type: string nullable: false param: type: string nullable: true default: null code: type: string nullable: true default: null required: - type - message RL.Checkpoint: type: object description: Metadata for a saved checkpoint required: - id - session_id - base_model - type - step - created_at properties: id: type: string example: 123e4567-e89b-12d3-a456-426614174000 description: Unique identifier for the checkpoint session_id: type: string example: 123e4567-e89b-12d3-a456-426614174000 description: Training session that produced the checkpoint base_model: type: string example: Qwen/Qwen3.5-4B description: Base model the checkpoint was trained from type: $ref: '#/components/schemas/RL.CheckpointType' example: CHECKPOINT_TYPE_TRAINING description: >- Kind of checkpoint. CHECKPOINT_TYPE_TRAINING is the full training state (weights and optimizer state), for resuming a training session with its optimizer state; CHECKPOINT_TYPE_INFERENCE is a model ready for serving or download, also added to your models. step: oneOf: - type: string - type: integer example: '42' description: Training step at time of save lora_rank: type: integer example: 32 description: >- LoRA rank of the session that produced this checkpoint. Absent for full-weight sessions and for checkpoints saved before this field was recorded. created_at: type: string format: date-time example: '2026-01-02T00:00:00Z' description: Timestamp when the checkpoint was created inference_registration: $ref: '#/components/schemas/RL.InferenceCheckpointRegistration' description: >- Model registry artifacts to deploy or download this inference checkpoint from. Absent for training checkpoints and when the checkpoint was not uploaded to the registry. training_registration: $ref: '#/components/schemas/RL.ModelRegistryArtifact' description: >- Model registry artifact holding this training checkpoint's training state, used to resume training rather than to deploy. Absent for inference checkpoints and when the checkpoint was not uploaded to the registry. RL.ListMeta: type: object description: Pagination metadata for list responses properties: limit: type: integer example: 20 description: Maximum number of items returned per page has_more: type: boolean example: true description: Whether more items exist beyond this page next_cursor: type: string example: 123e4567-e89b-12d3-a456-426614174000 description: >- Cursor to use as the 'after' parameter for the next page. Empty when has_more is false. RL.CheckpointType: type: string description: Whether a checkpoint is saved for training resume or inference download. enum: - CHECKPOINT_TYPE_TRAINING - CHECKPOINT_TYPE_INFERENCE RL.InferenceCheckpointRegistration: type: object description: >- Where an inference checkpoint's weights are stored in the Together model registry. At least one of `model` and `adapter` is set. properties: model: $ref: '#/components/schemas/RL.ModelRegistryArtifact' description: >- Full model weights. Set for full-weight training, and for LoRA training on custom base weights, where the merged model is deployed instead of the adapter. adapter: $ref: '#/components/schemas/RL.ModelRegistryArtifact' description: >- LoRA adapter weights, deployed on top of the base model. Set for LoRA training on the base model's own weights. RL.ModelRegistryArtifact: type: object description: A specific revision of a model in the Together model registry required: - id - revision_id properties: id: type: string example: ml_abc123 description: >- ID of the model in the Together model registry, as used by the models API revision_id: type: string example: rv_def456 description: Revision of the model that holds this checkpoint securitySchemes: bearerAuth: type: http scheme: bearer x-bearer-format: bearer x-default: default ```` This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.