Tutorial — Multi-modal AI

Forecast with TimesFM

TimesFM 2.5 is a 200M-parameter timeseries foundation model. Tenzro exposes it through the forecast runtime — point it at a context window and get back a horizon of point or quantile predictions.

Level: Beginner
Time: ~10 min
Prerequisites: Tenzro CLI installed
Stack: CLI · JSON-RPC

Load the model on a provider

The forecast catalog ships under the Permissive license tier — load once per provider.

curl -X POST https://rpc.tenzro.network -H 'content-type: application/json'   -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_loadForecastModel","params":["timesfm-2.5"]}'

Prepare your input series

Provide context as a flat array of floats. Horizon length is your forecast window.

cat > input.json <<'JSON'
{"context":[101.2,102.5,103.1,104.0,103.7,105.2,106.0,107.1]}
JSON

Run a forecast

Call tenzro_forecast over JSON-RPC. (No top-level CLI wrapper yet.)

curl -X POST https://rpc.tenzro.network \
  -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_forecast","params":{
    "model_id":"timesfm-2.5",
    "context":[/* float series */],
    "horizon":64
  }}'

Call from JSON-RPC for production use

The same runtime is reachable as a typed JSON-RPC method, returning point or quantile outputs.

curl -s https://rpc.tenzro.network -H 'content-type: application/json' \
  -d '{"jsonrpc":"2.0","id":1,"method":"tenzro_forecast","params":{"model":"timesfm-2.5","context":[101.2,102.5,103.1],"horizon":32}}'

Open the docs →Browse all tutorials

← All tutorials