Deploy an interactive-job checkpoint

POST

https://api.fastino.ai

training

jobs

{job_id}

checkpoints

sampler_weights

{name}

deploy

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints/sampler_weights/step-000100/deploy" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model_name": "support-replies-v1"}'

{
  "model_id": "MODEL_ID",
  "job_id": "SESSION_ID:train:0",
  "checkpoint_id": "sampler_weights/step-000100",
  "base_model": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
  "project_id": null,
  "status": "deploying"
}

POST /v1/training/jobs/{job_id}/checkpoints/sampler_weights/{name}/deploy Serves one of the job’s sampler checkpoints as a trained model. Call it with POST /v1/chat/completions and "model": "<model_id>". Deployment is available for supported base models; other bases return 400. The model’s status is deploying until the serving engine has loaded it, then deployed. Deploying the same checkpoint again returns the same model and its current status, so you can repeat the call to check progress. If an earlier attempt failed, the repeat call retries it.

Request

string

required

Your Fastino API key.

string

required

Interactive job ID.

string

required

Name of a sampler checkpoint saved with save-weights-for-sampler.

string

Up to 64 letters, digits, hyphens, and underscores, starting and ending with a letter or digit. Derived from the checkpoint name when omitted. The body is optional.

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints/sampler_weights/step-000100/deploy" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model_name": "support-replies-v1"}'

Response

string

The trained model’s ID. Pass it as model for inference.

string

The interactive job that saved the checkpoint.

string

sampler_weights/<name>.

string

The model’s base model.

string | null

The job’s project, if it has one.

string

deploying or deployed.

{
  "model_id": "MODEL_ID",
  "job_id": "SESSION_ID:train:0",
  "checkpoint_id": "sampler_weights/step-000100",
  "base_model": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
  "project_id": null,
  "status": "deploying"
}

Status	Meaning
`400`	Serving isn’t available yet for the job’s base model, or the checkpoint isn’t a PEFT adapter the serving engine accepts.
`404`	The job or sampler checkpoint doesn’t exist, belongs to another team, or has no files.
`409`	Another model already uses `model_name`, or the model served from this checkpoint was deleted. Save the weights under a new name to deploy them again.
`422`	`model_name` is invalid or the body has an unknown field.

⌘I

curl -X POST "https://api.fastino.ai/v1/training/jobs/$TRAINING_JOB_ID/checkpoints/sampler_weights/step-000100/deploy" \
  -H "X-API-Key: $FASTINO_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model_name": "support-replies-v1"}'

{
  "model_id": "MODEL_ID",
  "job_id": "SESSION_ID:train:0",
  "checkpoint_id": "sampler_weights/step-000100",
  "base_model": "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
  "project_id": null,
  "status": "deploying"
}

Inference

Training

Deploy an interactive-job checkpoint

Request

Response

​Request

​Response

Request

Response