Developer platform

APIs and hosted AI infrastructure for developers

Build on OCR, embeddings, vector database hosting, RAG, CPU LLM endpoints, and upcoming GPU LLM services with API keys, logs, and usage metering.

Developer Pricing Contact Sales

CPU

OCR API

Document text extraction API for builders who want to embed OCR into their own applications.

/api/v1/ocrContact Sales

CPU

Embedding API

Generate embeddings for search, retrieval, matching, recommendations, and document pipelines.

/api/v1/embeddingsContact Sales

Storage + CPU

Vector DB Hosting

Provision managed vector collections with API keys, storage metering, and query usage tracking.

/api/v1/vector-db/queryContact Sales

Storage + CPU

RAG API

Build retrieval-augmented generation workflows with hosted retrieval, context assembly, and inference.

/api/v1/rag/queryContact Sales

CPU

CPU LLM API

Run CPU-friendly local models and quantized LLM endpoints with REST access.

/api/v1/models/llama-cpp/inferContact Sales

GPU

GPU LLM API

GPU-backed LLM endpoints for higher-throughput workloads. Post coming soon.

/api/v1/models/gpu-llm/inferContact Sales

Developer API pattern

curl -X POST http://datalyrixai.host/api/v1/models/tinyllm/infer \
  -H "Authorization: Bearer $DATALYRIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"Summarize this document"}'

Planning CPU/GPU endpoints or vector database capacity?

Contact Sales