> For the complete documentation index, see [llms.txt](https://docs.meganova.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.meganova.ai/api-reference/inference-models.md).

# Inference API (OpenAI Compatible)

The Inference API provides OpenAI-compatible endpoints for running generative AI inference (text, vision, image, video, audio, embeddings) using MegaNova's serverless infrastructure.

* **BASE URL:** `https://api.meganova.ai/v1`
* **ENTERPRISE BASE URL:** `https://enterprise.api.meganova.ai/v1` — [dedicated enterprise deployments](/enterprise/enterprise-endpoint.md) instead of the shared pool, for a subset of the catalog. Same model ids, same API key, same request and response shapes. Serves `/chat/completions`, `/embeddings`, `/rerank` and `/models`; every other endpoint below stays on the standard base URL and returns `404` if called here.
* **OpenAI Compatible:** Use OpenAI SDKs and tools with this API.

Use this API for all inference operations, such as text generation, image generation, video generation, audio synthesis, and embeddings.

> **Migration note:** The previous base URL `https://inference.meganova.ai/v1` is deprecated. Existing integrations pointed at that host continue to work for backwards compatibility, but new code and SDK configuration should use `https://api.meganova.ai/v1`.

## Endpoints

The **Enterprise** column marks the endpoints also served on the enterprise base URL.

| Endpoint                             | Method | Description                                                            | Enterprise |
| ------------------------------------ | ------ | ---------------------------------------------------------------------- | :--------: |
| `/v1/chat/completions`               | POST   | Text generation (chat completions)                                     |      ✅     |
| `/v1/models`                         | GET    | List models — on the enterprise base URL, only the models served there |      ✅     |
| `/v1/images/generations`             | POST   | Image generation (text-to-image, image-to-image)                       |            |
| `/v1/images/edits`                   | POST   | Image editing                                                          |            |
| `/v1/videos/generations`             | POST   | Video generation (text-to-video, image-to-video)                       |            |
| `/v1/videos/generations/{id}`        | GET    | Check video generation status                                          |            |
| `/v1/videos/generations/{id}/stream` | GET    | Stream generated video                                                 |            |
| `/v1/audio/speech`                   | POST   | Text-to-Speech                                                         |            |
| `/v1/audio/transcriptions`           | POST   | Speech-to-Text                                                         |            |
| `/v1/audio/voices`                   | GET    | List available voices                                                  |            |
| `/v1/audio/voices/clone`             | POST   | Clone a voice                                                          |            |
| `/v1/audio/voices/design`            | POST   | Design a new voice                                                     |            |
| `/v1/embeddings`                     | POST   | Generate embeddings                                                    |      ✅     |
| `/v1/rerank`                         | POST   | Rerank documents against a query                                       |      ✅     |

## Guides by modality

Each endpoint has a walkthrough with runnable examples, under **Core Services**:

* [Model List](/inference-models/model-list.md) — the catalog, with prices and per-tier limits
* [Text Generation](/inference-models/text-generation.md)
* [Text Generation (Vision)](/inference-models/vision.md)
* [Image Generation](/inference-models/image-generation.md)
* [Video Generation](/inference-models/video-generation.md)
* [Audio Generation](/inference-models/audio-generation.md)
* [Embedding Generation](/inference-models/embedding-generation.md)

## See Also

* [Enterprise Endpoint](/enterprise/enterprise-endpoint.md) — the same models on dedicated deployments
* [Errors & Response Conventions](/api-reference/platform-api/errors.md)
* [Glossary](/resources/glossary.md)