Deploy a checkpoint

To serve a trained model, deploy one of its inference checkpoints to dedicated model inference. For production traffic, deploy it on its own deployment. A low-rank adapter (LoRA) is merged into its base model when the deployment starts, so it serves at the base model’s speed and cost.

Find your model’s ID

Each inference checkpoint registers its weights in your project’s model registry, and you deploy by the registry ID. Read it from the checkpoint’s registration:

from together import Together

client = Together()
session = client.post_training.sessions.retrieve("<session_id>")
registration = session.inference_checkpoints[-1].registration
if registration is None:
    print("Not registered. Download the checkpoint instead.")
elif registration.model:
    print("Merged model:", registration.model.id)
elif registration.adapter:
    print("Adapter:", registration.adapter.id)
    print("Revision:", registration.adapter.revision_id)

To look up a checkpoint’s IDs without the session, see Find a checkpoint. From the terminal, tg training ls-checkpoints --type inference --session <session_id> lists each inference checkpoint’s registry ID in its Model column. What you deploy depends on which ID your checkpoint registers:

registration.model: A full-weight session, or a LoRA session on custom base weights, registers a merged model. Deploy its ID directly.
registration.adapter: A LoRA session registers only the adapter. Deploy the adapter on its own deployment, or attach it to a multi-LoRA deployment.

MiniMax-M3 checkpoints aren’t registered, so you can’t deploy them on Together AI. Download them instead.

Deploy a merged model

Deploy a merged model with tg beta endpoints deploy:

tg beta endpoints deploy "<MODEL_ID>" \
  --endpoint my-trained-model \
  --config "<CONFIG_ID>" \
  --project "<PROJECT_ID>"

For a full-weight session or a LoRA session on custom base weights, <MODEL_ID> is registration.model.id. For an uploaded or prepared model, it’s that model’s ID. List the model’s deployment configs with tg beta models configs "<MODEL_ID>" and pick one whose accelerator_type is nvidia-b200-180gb and adapter_mode is disabled. If the model has more than one config and you omit --config, deploy fails with Multiple configs found for model. Run tg whoami to find your project ID. Pass --project, or set TOGETHER_PROJECT_ID, even for your default project. Without either, the CLI resolves a private model ID to its base model and deploys that instead. deploy creates the endpoint and routes all traffic to the new deployment. The dedicated model inference quickstart walks through the rest of the flow, from choosing a config to calling the endpoint. Scale the deployment to zero or delete the endpoint when you’re done.

Deploy a LoRA adapter

To serve a LoRA adapter for production traffic, deploy the adapter’s ID with --merge. There’s no merge job or upload. Each replica merges the adapter into its base model’s weights when it starts, then serves the merged model at the base model’s speed and cost:

tg beta endpoints deploy "<ADAPTER_ID>" \
  --endpoint my-trained-model \
  --merge \
  --config "<CONFIG_ID>" \
  --project "<PROJECT_ID>"

<ADAPTER_ID> is registration.adapter.id. To find a B200 config for --config, list the serving base model’s profiles:

Training base model	Serving base model	Base model ID
Qwen3.5 9B	`Qwen/Qwen3.5-9B-BF16`	`ml_CbuqU8KKAtoGrowco4nqK`
Qwen3.6 35B A3B	`Qwen/Qwen3.6-35B-A3B-FP8`	`ml_CbSJsoXB4sHXmSRLUm9es`
Qwen3.8 27B	`Qwen/Qwen3.8-27B-FP8`	`ml_CeGmEZ22uUuWLHSKj43rJ`

Run tg beta models configs with the base model ID above. Choose a profile whose accelerator_type is nvidia-b200-180gb and adapter_mode is disabled, then pass its config ID to --config. For Qwen3.6 35B A3B, cr_Ceh96pLTPcNatioB4YfHe is a single-B200 profile. The profile’s accelerator_count sets the GPUs per replica. If no B200 profile is listed, contact your account team for B200 serving support. Pass --project, or set TOGETHER_PROJECT_ID, as for a merged model. To deploy with the SDK, see Deploy the adapter. The merge adds to the time each replica takes to start, including replicas that autoscaling adds later. A new deployment can take 20 minutes or more to become ready. Adapters from a model’s single-session variant register against the same base model as the default model, so they deploy the same way. GLM-5.3 and Kimi-K3 adapters can’t deploy with --merge. Prepare them for FP4 inference instead, then deploy the prepared model.

Serve the adapter on a multi-LoRA deployment

Instead of deploying a LoRA adapter on its own, you can attach it to a running deployment of its base model, if the base model supports multi-LoRA deployment. Attaching takes about a minute, with no extra job or upload. Each request does extra work for the adapter, and a deployment holds a limited number of adapters. Use it to compare candidates and to serve adapters with low or mixed traffic. For production traffic, deploy the adapter on its own deployment. Multi-LoRA deployment covers attaching adapters with the CLI or the console, calling them, and comparing candidates.

Next steps

Multi-LoRA deployment

Attach candidate adapters to one deployment and compare them per request.

Prepare for FP4 inference

Merge and calibrate a GLM or Kimi-K3 adapter as one FP4 model.

Dedicated model inference quickstart

The CLI and SDK deploy flow, step by step.

Manage checkpoints

Save the inference checkpoints you deploy.

GET STARTED

SERVERLESS

INFERENCE APIS

DEDICATED MODEL INFERENCE

DEDICATED CONTAINER INFERENCE

POST-TRAINING

FINE-TUNING

GPU CLUSTERS

CODE EXECUTION

ADMINISTRATION

Find your model’s ID

Deploy a merged model

Deploy a LoRA adapter

Serve the adapter on a multi-LoRA deployment

Next steps

Multi-LoRA deployment

Prepare for FP4 inference

Dedicated model inference quickstart

Manage checkpoints

​Find your model’s ID

​Deploy a merged model

​Deploy a LoRA adapter

​Serve the adapter on a multi-LoRA deployment

​Next steps

Multi-LoRA deployment

Prepare for FP4 inference

Dedicated model inference quickstart

Manage checkpoints

Find your model’s ID

Deploy a merged model

Deploy a LoRA adapter

Serve the adapter on a multi-LoRA deployment

Next steps