Skip to main content

API Endpoints

This page summarizes the primary public REST endpoints exposed by LLMTune’s API. All paths below are relative to the base URL:
https://api.llmtune.io/v1

Inference

Run completions against hosted or deployed models.
MethodEndpointDescription
POST/models/{modelId}/inferenceRun inference against a deployed model.
POST/playground/inferenceMirror of the UI playground for quick tests.
POST/batch/inferenceSubmit a batch of up to 100 inference requests.

Example – Single Inference

curl https://api.llmtune.io/v1/models/meta-llama/Llama-3.3-70B-Instruct/inference \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "prompt": "Summarize LLMTune in one sentence.",
    "temperature": 0.7,
    "maxTokens": 200
  }'

Fine-Tuning

Launch and monitor fine-tuning jobs.
MethodEndpointDescription
POST/fine-tuneSubmit a fine-tune job.
GET/fine-tune/{jobId}Fetch job status, metrics, and errors.

Example – Submit Fine-Tune

curl https://api.llmtune.io/v1/fine-tune \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "baseModel": "meta-llama/Llama-3.3-70B-Instruct",
    "dataset": "s3://your-bucket/dataset.jsonl",
    "trainingMethod": "sft",
    "hyperparameters": {
      "learningRate": 0.0001,
      "epochs": 3,
      "batchSize": 64
    },
    "webhookUrl": "https://app.yourdomain.com/fine-tune-callback"
  }'

Webhooks

Receive lifecycle events for fine-tunes and deployments. LLMTune sends signed POST requests to your configured webhook URL with payloads like:
POST https://your-app.com/webhooks/llmtune

{
  "event": "training.completed",
  "data": {
    "jobId": "job-uuid",
    "baseModel": "meta-llama/Llama-3.3-70B-Instruct",
    "artifact": "ionet-finetune-model-id"
  },
  "deliveredAt": "2025-11-08T14:22:31Z"
}
Common events:
  • training.started
  • training.completed
  • training.failed
  • model.deployed
Configure webhook URLs from the LLMTune dashboard and test them using the Send test event action.

Error Handling

All endpoints return a standard error schema on failure:
{
  "error": {
    "message": "Invalid API key",
    "code": "UNAUTHORIZED",
    "details": null
  }
}
Typical status codes:
  • 401 – Invalid or missing API key
  • 402 – Insufficient credits
  • 404 – Model or job not found
  • 429 – Rate limited
  • 500 – Unexpected server error