---
title: "OpenAI compatibility"
slug: "clovastudio-openaicompatibility"
updated: 2026-09-17T09:35:47Z
published: 2026-09-17T09:35:47Z
canonical: "api.ncloud-docs.com/clovastudio-openaicompatibility"
---

> ## Documentation Index
> Fetch the complete documentation index at: https://api.ncloud-docs.com/llms.txt
> Use this file to discover all available pages before exploring further.

# OpenAI compatibility

Available in Classic and VPC

The CLOVA Studio service provides compatibility with OpenAI API for major APIs, including Chat Completions and Embedding.

## Compatible APIs

The list of APIs compatible with OpenAI API in CLOVA Studio is as follows:

| API | Method | URI |
| --- | --- | --- |
| Chat Completions, Chat Completions v3 | POST | `/chat/completions` |
| Embedding, Embedding v2 | POST | `/embeddings` |
| Get model. | GET | `/models` |

## Usage method

The following describes the request format and response format of the OpenAI-compatible APIs.

### Request

By adjusting some of the request items in the CLOVA Studio API, you can use the OpenAI official library (SDK) and REST API.

#### API key

Use the test or service API key issued by the CLOVA Studio service.

              Caution

              

The OpenAI-compatible APIs can only be used with a test API key or service API key issued from **[API key]** in CLOVA Studio.

#### API URL

The request API URL is as follows:

```
https://clovastudio.stream.ntruss.com/v1/openai/
```

#### Model

Enter the model name provided by the CLOVA Studio service as the model name in the request body.

#### Naming rule

The naming rule for request fields follows snake_case notation.

              Note

              

Note that it differs from CLOVA Studio's Chat Completions (including V3), Embedding API field naming convention, which follows camelCase notation. For the list of supported/unsupported fields, see [Compatibility information](/docs/en/clovastudio-openaicompatibility#%ED%98%B8%ED%99%98%EC%A0%95%EB%B3%B4).

### Response

It supports response results with the same structure and format as the OpenAI API.

## SDK examples

The following is an example of using the CLOVA Studio service by utilizing the official OpenAI library.

### Python

The example written in Python is as follows:

```
from openai import OpenAI

client = OpenAI(
    api_key="CLOVA_STUDIO_API_KEY",  # CLOVA Studio API key
    base_url="https://clovastudio.stream.ntruss.com/v1/openai"  # CLOVA Studio OpenAI-compatible API URL 
)

# Chat Completions
response = client.chat.completions.create(
    model="HCX-005",  # CLOVA Studio supported model name
    messages=[
        {"role": "system", "content": "You're a skilled AI assistant."},
        {"role": "user", "content": "Please explain artificial intelligence."}
    ]
)

print(response.choices[0].message.content)

# Embeddings
embedding = client.embeddings.create(
    model="bge-m3", # CLOVA Studio supported model name (embedding)
    input="Thank you for using CLOVA Studio.",
    encoding_format="float" # Must be set when using embedding with the OpenAI Python SDK (Base64 not supported).
    )
    
print(embedding.data[0].embedding)
```

              Caution

              

If you want to use embedding with the official OpenAI Python library, `encoding_format="float"` is a required setting.

### TypeScript/JavaScript (Node.js)

The example written in TypeScript/JavaScript (Node.js) is as follows:

```
import OpenAI from "openai";

const openai = new OpenAI({
    baseURL: "https://clovastudio.stream.ntruss.com/v1/openai", // CLOVA Studio OpenAI-compatible API URL
    apiKey: "YOUR_API_KEY",
    }); // CLOVA Studio API key

// Chat Completions
const completion = await openai.chat.completions.create({
    model: "HCX-005",   // CLOVA Studio supported model name
    messages: [
        {"role": "system", "content": "You're a skilled AI assistant."},
        {"role": "user", "content": "Please explain artificial intelligence."}
    ]
});

console.log(completion.choices[0].message);

// Embedding
const embedding = await openai.chat.completions.create({
    model: "bge-m3",   // CLOVA Studio supported model name (embedding)
    input: "Thank you for using CLOVA Studio."    
});

console.log(embedding.data[0].embedding);
```

              Note

              

You can use CLOVA Studio through open source frameworks implemented with OpenAI's official SDK and compatible APIs in various languages.

## Compatibility information

This section provides detailed compatibility information for each API compatible with the OpenAI API. For the input format and scope of supported fields and CLOVA Studio-specific fields, see the relevant API guide.

### Chat Completions/Chat Completions v3

The OpenAI compatibility information for Chat Completions API and Chat Completions v3 API is as follows:

| Supported field | Unsupported field | CLOVA Studio-specific field |
| --- | --- | --- |
| - `messages` - `messages[].name` - `model` - `stream` - `max_completion_tokens` (default: 512) - `max_tokens` (default: 512) - `n` - `temperature` - `tools` - `tool_choice` - `parallel_tool_calls` - `reasoning_effort` \| `reasoning.effort` - `response_format` - `top_p` - `stop` - `seed` | - `audio` - `frequency_penalty` - `logit_bias` - `logprobs` - `metadata` - `modalities` - `prediction` - `presence_penalty` - `prompt_cache_key` - `safety_identifier` - `service_tier` - `store` - `stream_options` - `top_logprobs` - `user` - `web_search_options` | - `top_k` - `repeat_penalty` - `repetition_penalty` |

              Note

              

The following fields provide compatibility to the extent supported by CLOVA Studio.

- `n`: `1` (valid value, default)
- `tool_choice`: `auto` (default) | `none` | object (call specific tools)
- `parallel_tool_calls`: `true` (valid value, default)
- `reasoning_effort` (or `reasoning.effort`): `none` | `low` | `medium` | `high`
- `response_format.type`: `json_schema` (valid value)
- `response_format.json_schema.name`: Optional support (input not recognized)
- `response_format.json_schema.strict`: Optional support (input not recognized)

### Embedding, Embedding v2

The OpenAI compatibility information for the Embedding API and Embedding v2 API is as follows:

| Supported field | Unsupported field | CLOVA Studio-specific field |
| --- | --- | --- |
| - `input` - `model` - `dimensions` - `encoding_format` | - `user` | - |

              Note

              

The following fields provide compatibility to the extent supported by CLOVA Studio.

- `dimensions`: `1024` (valid value, default)
- `encoding_format`: `float` (valid value, default)