score.mojojojo.cc

Tabular Score API

Train a tree ensemble on your rows, then score at up to 570x scikit-learn's single-row speed on Mojo kernels

Live

Pricing

Billed from your mojojojo credits ($0.001 each). Nothing accrues without an API key, and a request is refused once the free allowance is spent and the balance is empty.

Try it

Call it

curl https://score.mojojojo.cc/v1/models \
  -H "Authorization: Bearer $MOJOJOJO_KEY" -H "Content-Type: application/json" \
  -d '{"name":"churn","target":"churned","rows":[{"age":31,"plan":"pro","churned":"no"}, ...]}'

curl https://score.mojojojo.cc/v1/models/churn/predict -H "Authorization: Bearer $MOJOJOJO_KEY" \
  -d '{"rows":[{"age":44,"plan":"free"}]}'

Endpoints

• POST /v1/models
• GET /v1/models
• GET /v1/models/{name}
• POST /v1/models/{name}/predict
• DELETE /v1/models/{name}

Agents: MCP · OpenAPI · llms.txt

Model

scikit-learn HistGradientBoosting + ExtraTrees, exported to the Mojo forest kernel

Limits and measured results

• Binary targets only; up to 200,000 rows and 200 feature columns; training is capped at 120 seconds. Rows with numbers and strings; missing values are imputed.
• Models are private to your account. The response includes a holdout AUC from a 80/20 split when you send at least 100 rows.
• Serving is exact: probabilities match scikit-learn to 1e-15 on the shipped benchmark models.
• Speed versus scikit-learn on 2 cores: 12-570x at batch 1, 2-8x at batch 64-1024, 1.0-4x at batch 8192 (gradient boosting is only 1.03x at large batch).
• Not for credit, hiring, insurance or medical decisions.