Datablocks API

Train, manage, and deploy datablocks for efficient long-context inference.

Overview

The Datablocks API allows you to create, train, and manage pre-computed context blocks. Datablocks dramatically reduce inference costs and latency by pre-processing large amounts of context into compact KV cache representations.

Training Datablocks

POST /api/v1/datablocks/train

Train a new datablock from your documents. The training process compresses your context into a highly efficient KV cache format.

Managing Datablocks

List Datablocks

GET /v1/datablocks

Get Datablock

GET /v1/datablocks/{datablock_id}

Delete Datablock

DELETE /v1/datablocks/{datablock_id}

Best Practices

Optimize Document Size

For best results, train datablocks with 10K-100K tokens of context per document.

Reuse Datablocks

Once trained, datablocks can be reused across millions of queries with zero additional cost.

import requests

# Train a new datablock
response = requests.post(
    "/api/v1/datablocks/train",
    headers={
        "Content-Type": "application/json",
        "Authorization": "Bearer YOUR_API_KEY"
    },
    json={
        "documents": [
            "Your document text here...",
            "Another document..."
        ],
        "model": "qwen",
        "name": "my-datablock"
    }
)

data = response.json()
print(f"Datablock ID: {data['id']}")