---
title: "OpenAI-compatible model inference for agents and apps | Tarka"
description: "Call GLM-5.3 Flash, DeepSeek V4.1 Flash, Kimi K3 and speech, OCR, and voice models through Tarka’s OpenAI-compatible API."
url: "https://tarkahq.com/inference/"
---

OpenAI-compatible inference

# Use the models you need without rewriting your application.

GLM-5.3 Flash, DeepSeek V4.1 Flash, and Kimi K3 are live on the public API. Speech, OCR, document-layout, and voice models use the same account.

[Open console](https://tarkahq.com/console) [Read docs](https://tarkahq.com/docs/inference/) [Model catalog](https://tarkahq.com/inference/#language-models)

- OpenAI-compatible API
- 1M-token context
- Tool calling
- No training on prompts or outputs

```python
from openai import OpenAI
 
client = OpenAI(
    base_url="https://tarka.rest/v1",
    api_key="tk_live_xxx",
)
 
response = client.chat.completions.create(
    model="<model-id>",
    messages=[{"role": "user", "content": "Hello"}],
)
```

```javascript
import OpenAI from "openai";
 
const client = new OpenAI({
  baseURL: "https://tarka.rest/v1",
  apiKey: "tk_live_xxx",
});
 
const response = await client.chat.completions.create({
  model: "<model-id>",
  messages: [{ role: "user", content: "Hello" }],
});
```

```bash
curl https://tarka.rest/v1/chat/completions \
  -H "Authorization: Bearer tk_live_xxx" \
  -H "Content-Type: application/json" \
  -d '{"model": "<model-id>",
       "messages": [{"role": "user", "content": "Hello"}]}'
```

```dotenv
OPENAI_BASE_URL=https://tarka.rest/v1
OPENAI_API_KEY=tk_live_xxx
```

## Language models for agents and applications.

Compare model capabilities below. Status shows what the public API serves today.

| Model | Context | Parameters | Model IDs | Status |
| --- | --- | --- | --- | --- |
| [GLM-5.3 Flash](https://tarkahq.com/inference/glm-5-3-flash/)<br>Z.ai's efficient open model for high-volume chat and extraction. | 1M | 320B, 18B active | `glm-5.3-flash` `glm-5.3-flash-eu` | Available |
| [DeepSeek V4.1 Flash](https://tarkahq.com/inference/deepseek-v4-1-flash/)<br>DeepSeek's fast open model for everyday chat, tool use, and coding. | 1M | 552B backbone | `deepseek-v4.1-flash` `deepseek-v4.1-flash-eu` | Available |
| [Kimi K3](https://tarkahq.com/inference/kimi-k3/)<br>Moonshot AI's flagship open model, for coding agents and long, multi-step tasks. | 1M | 2.8T, 104B active | `kimi-k3` | Available |
| [GLM 5.3](https://tarkahq.com/inference/glm-5-3/)<br>GLM 5.3 through Tarka's OpenAI-compatible API. | 1M | — | `glm-5.3` | Available |
| [Qwen 3.8 Flash Next](https://tarkahq.com/inference/qwen-3-8-flash-next/)<br>A free, self-hosted language model through Tarka's API. | 256K | — | `qwen3.8-flash-next` | Available |

[Language model docs](https://tarkahq.com/docs/inference/llms/) [Nepali-language models](https://tarkahq.com/ai-for-nepal/)

## Speech, documents and voice.

Transcribe audio, read documents and generate speech through the same account and API family as your language models. Open a model to see what it returns and when to pick it.

| Type | Model | Languages | License | Model IDs | Status |
| --- | --- | --- | --- | --- | --- |
| Speech to text | [Whisper Large v3](https://tarkahq.com/utilities/whisper-large-v3/)<br>Multilingual speech-to-text — 99 languages, including Nepali. | 99 languages | MIT (OpenAI Whisper open release) | `whisper-large-v3` | Available |
| Speech to text | [Qwen3-ASR](https://tarkahq.com/utilities/qwen3-asr/)<br>Apache 2.0 speech recognition with Qwen3-ASR 1.7B. | 30 languages | Apache 2.0 | `qwen3-asr` | Available |
| OCR | [GLM-OCR](https://tarkahq.com/utilities/glm-ocr/)<br>Document vision for receipts, PDFs, screenshots, forms. | General multilingual + Nepali fine-tune | MIT base; fine-tune not declared | `glm-ocr` `glm-ocr-nepali` | Available |
| OCR | [PaddleOCR-VL 1.6](https://tarkahq.com/utilities/paddleocr-vl-1-6/)<br>Compact multilingual document OCR for text, tables, formulas, charts, and seals. | Multilingual | Apache 2.0 (PaddlePaddle) | `paddleocr-vl-1.6` | Available |
| Document layout | [PP-DocLayoutV3](https://tarkahq.com/utilities/pp-doclayout-v3/)<br>Layout analysis for text, titles, tables, formulas, figures, charts, and curved pages. | Language-independent geometry | Apache 2.0 (PaddlePaddle) | `pp-doclayout-v3` | Available |
| Text to speech | [Qwen3-TTS](https://tarkahq.com/utilities/qwen3-tts/)<br>Apache 2.0 text to speech with consent-backed voice cloning. | 10 languages | Apache 2.0 | `qwen3-tts` | Available |
| Text to speech | [Kokoro](https://tarkahq.com/utilities/kokoro/)<br>Small, fast TTS — built for low-latency agent loops. | English on the current alias | Apache 2.0 | `kokoro` | Available |
| Text to speech | [Piper](https://tarkahq.com/utilities/piper/)<br>CPU-friendly English TTS with a pinned, predictable voice. | English on the current alias | GPL-3.0 runtime; voice licenses vary | `piper` | Available |

[Speech and document model docs](https://tarkahq.com/docs/inference/utility-models/)

## Keep one integration as your model needs change

Use the OpenAI SDK or any compatible HTTP client you already have. Change the base URL, pick a model ID, and switch models later without rewriting your application.

### What you get

- **OpenAI-compatible chat endpoints** for SDKs and HTTP clients that already speak the OpenAI API format, with streaming and tool calls.
- **Per-request usage records** expose model, route, and token totals through the console so teams can audit workload behavior.
- **No training on your prompts or outputs.**

### Compare partner models

Three partner models are live on the public API.

- **GLM-5.3 Flash** for high-volume chat, extraction, and classification.
- **DeepSeek V4.1 Flash** for fast, general-purpose chat, tool use, and coding.
- **Kimi K3** for coding agents and long, multi-step tasks.

Open a model card to review its context window, parameter count, and model ID before you integrate it. Only models returned by `GET /v1/models` for your key can be called.

## Create an account and call a model.

Sign up, then request the products you need from the console.

[Create an account](https://tarkahq.com/console?auth=signup) [Read the inference docs](https://tarkahq.com/docs/inference/)