Tolka Edge SymbolTolka Edge WordmarkDocs
One-click AI Model Deployments

Build with Tolka Edge

Deploy private, dedicated AI Rigs for Qwen3-14B in one click. Zero infrastructure, transparent billing, and fully OpenAI-compatible.

Deploy your first Rig API Reference

One-Click AI Rigs

Provision private inference for Qwen3-14B on demand. Get your own dedicated GPU instances with zero infrastructure overhead.

OpenAI-compatible

Drop-in replacement for the OpenAI SDK. Just change the base URL to your Rig's endpoint and your existing code works instantly.

Uncompromising Performance

Powered by vLLM with continuous batching and AWQ quantization. Benchmarked at ~82 tok/s single-stream on an RTX 3090.

Transparent & Private

Your data never leaves your dedicated Rig. Every response carries exact cost headers metered cleanly in paise.

Explore the docs

Quick Start

Deploy your first Rig and make a request.

API Reference

Endpoints, parameters, and error codes.

Dedicated GPU

Manage your private AI instances.