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

# Serverless Inference

Run text, vision, image, video, embedding, and reranking models on managed OpenAI-compatible endpoints.

Serverless Inference gives you managed endpoints for state-of-the-art models — no GPUs to provision, no weights to load, no scaling to manage. Sign in, create a key, and call the API.

The endpoint is **OpenAI-compatible** and lives at `https://inference.nebulablock.com/v1`, so any OpenAI SDK or tool works by changing the base URL.

## What you can do

|                                                            | Guide                                                                  |
| ---------------------------------------------------------- | ---------------------------------------------------------------------- |
| Chat and text generation, including tool use and streaming | [Text Generation](/products/serverless-inference/text-generation.md)   |
| Send images to a model and ask about them                  | [Vision](/products/serverless-inference/vision.md)                     |
| Generate and edit images                                   | [Image Generation](/products/serverless-inference/image-generation.md) |
| Generate video from text or an image                       | [Video Generation](/products/serverless-inference/video-generation.md) |
| Turn text into vectors for search and RAG                  | [Embeddings](/products/serverless-inference/embeddings.md)             |
| Reorder retrieved documents by relevance                   | [Reranking](/products/serverless-inference/reranking.md)               |

The [Model Catalog](/products/serverless-inference/model-catalog.md) lists every model currently served, grouped by what it does.

## Prerequisites

* A [Nebula Block account](https://console.nebulablock.com/register)
* An [API key](/account/api-keys.md)
* Credit on your account — most models are capped at 0 requests per day on Tier 1, so a $5 deposit (Tier 2) is what opens up the catalog. See [Tiers and Rate Limits](/account/tiers-and-limits.md).

## Key features

* **OpenAI compatible.** Point the OpenAI Python, Node, or any compatible client at the base URL above.
* **One key, every modality.** Text, vision, image, video, embedding, and reranking models share the same authentication and the same base URL.
* **Pay as you go.** Billed on usage, metered per token — or per image or per second for some media models. See the [pricing page](https://www.nebulablock.com/pricing/serverless-ai).
* **Try before you integrate.** Every model has a playground in the console under [Serverless](https://console.nebulablock.com/serverless).
* **Canadian-hosted options.** Models marked 🇨🇦 in the catalog run in Canada for data-residency requirements.

## Rate limits

Two limits apply to every call: your account-wide rate limit (RPM, TPM, RPD) and a per-model daily cap that varies by tier. Both are documented in [Tiers and Rate Limits](/account/tiers-and-limits.md), and your account's current numbers are shown under [Limits](https://console.nebulablock.com/limits) in the console.

## See also

* [Quickstart](/getting-started/get-started/quickstart.md)
* [Inference API reference](/api-reference/inference-api.md)
* [Glossary](/resources/glossary.md)