---
title: "Inference | Tarka Docs"
description: "Integrate Tarka language and utility models through versioned inference APIs."
url: "https://tarkahq.com/docs/inference/"
---

Available Inference

# Inference

Discover models and use one canonical API for language, document, speech, and voice inference.

Provisioning and management **Use the console or the Control API.**

Manage API keys, model access, and organization limits in the console or through the Control API. Send model requests to the separate Inference API.

[Open console](https://tarkahq.com/console) [Control API reference](https://tarkahq.com/docs/control-api/)

**Available today**

Tarka exposes model discovery, Chat Completions, Responses, OCR, transcription, translation, speech, and voice cloning at canonical`/v1`. Native gRPC exposes the same operations. The old`/v2` REST prefix is a deprecated alias, not a newer API. The machine-readable [OpenAPI 3.1 contracts](https://github.com/TarkaHQ/api/tree/main/openapi)are published in the public, contract-only API repository.

Documentation set

## Choose an integration path

Start with access and authentication, then continue to the modality your application needs.

Start here

### [API access](https://tarkahq.com/docs/inference/api-access/)

Choose the public or Agent Host endpoint, configure credentials, discover models, and handle errors.

[Available→](https://tarkahq.com/docs/inference/api-access/)

Available

### [Language models](https://tarkahq.com/docs/inference/llms/)

Create Chat Completions or Responses and consume token streams with existing OpenAI clients.

[Available→](https://tarkahq.com/docs/inference/llms/)

Available

### [Utility models](https://tarkahq.com/docs/inference/utility-models/)

Use OCR, transcription, translation, speech, and consent-backed custom voices.

[Open utility docs→](https://tarkahq.com/docs/inference/utility-models/)

API boundaries

## Management and runtime traffic are separate

| Surface | Base URL | Use |
| --- | --- | --- |
| **Canonical REST API** | `https://tarka.rest/v1` | OpenAI-compatible language inference plus utility-model routes. |
| **Native gRPC API** | `grpc.tarka.rest:443` | Typed versions of every inference operation. |
| **Agent Host inference** | `http://tarka/v1` | Host-local model requests from Tarka Agent Hosts. |
| **Deprecated REST alias** | `https://tarka.rest/v2` | Temporary compatibility alias for existing integrations. |
| **Control API** | `https://tarka.rest/control/v1` | API keys, access, limits, and provisioned resources. |
| **Console** | `https://tarkahq.com/console` | The web interface for the same management resources. |