> ## 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. # Deploy a checkpoint > Deploy a trained model or LoRA adapter from an inference checkpoint to dedicated model inference. To serve a trained model, deploy one of its [inference checkpoints](/docs/post-training/checkpoints#inference-checkpoints) to [dedicated model inference](/docs/dedicated-endpoints/overview). 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`: ```python theme={null} from together import Together client = Together() session = client.post_training.sessions.retrieve("") 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](/docs/post-training/checkpoints#find-a-checkpoint). From the terminal, `tg training ls-checkpoints --type inference --session ` 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](#deploy-a-merged-model) directly. * **`registration.adapter`:** A LoRA session registers only the adapter. [Deploy the adapter](#deploy-a-lora-adapter) on its own deployment, or [attach it to a multi-LoRA deployment](#serve-the-adapter-on-a-multi-lora-deployment). MiniMax-M3 checkpoints aren't registered, so you can't deploy them on Together AI. [Download them](/docs/post-training/checkpoints#download-the-weights) instead. ## Deploy a merged model Deploy a merged model with `tg beta endpoints deploy`: ```bash theme={null} tg beta endpoints deploy "" \ --endpoint my-trained-model \ --config "" \ --project "" ``` For a full-weight session or a LoRA session on custom base weights, `` 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 ""` 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](/docs/dedicated-endpoints/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: ```bash theme={null} tg beta endpoints deploy "" \ --endpoint my-trained-model \ --merge \ --config "" \ --project "" ``` `` 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](#deploy-a-merged-model). To deploy with the SDK, see [Deploy the adapter](/docs/dedicated-endpoints/adapter#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](/docs/post-training/prepare-for-fp4-inference) instead, then [deploy the prepared model](#deploy-a-merged-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](/docs/post-training/multi-lora-deployment#supported-models). 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](#deploy-a-lora-adapter) on its own deployment. [Multi-LoRA deployment](/docs/post-training/multi-lora-deployment) covers attaching adapters with the CLI or the console, calling them, and [comparing candidates](/docs/post-training/multi-lora-deployment#compare-the-candidates). ## Next steps Attach candidate adapters to one deployment and compare them per request. Merge and calibrate a GLM or Kimi-K3 adapter as one FP4 model. The CLI and SDK deploy flow, step by step. Save the inference checkpoints you deploy. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.