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

# Introduction

> Run open-weight models through OpenAI- and Anthropic-compatible endpoints.

Prism is an inference API for coding agents. Use the OpenAI client already in
your application, change its base URL, and select a Prism model.

> [!NOTE]
>
> **Zero data retention on every request.** Prism does not store API inputs or
> outputs after processing or use them for model training. [See exactly what
> ZDR covers](https://docs.prisminference.com/zero-data-retention.md).

```text theme={"theme":{"light":"github-light","dark":"github-dark"}}
OpenAI base URL: https://api.prisminference.com/v1
```

Prism currently serves DeepSeek-V4.1-Flash and Gemma 4 31B. The same API key
works across the supported wire formats.

## API formats

| Endpoint | Format | Purpose |
| - | - | - |
| `POST /v1/chat/completions` | OpenAI Chat Completions | Generate from text or images, stream tokens, call tools, and return structured output. |
| `POST /v1/responses` | OpenAI Responses | Use stateless Responses clients, tools, image input, and typed streams. |
| `POST /v1/messages` | Anthropic Messages | Use Anthropic clients, content blocks, tools, images, and streaming. |
| `POST /v1/messages/count_tokens` | Anthropic Messages | Count text and tool input tokens before inference. |
| `GET /models` | OpenAI Models | List available models. |
| `GET /models/{model}` | OpenAI Models | Retrieve one available model by ID. |
| `GET /health` | JSON | Check API availability. |
| `GET /` | JSON | Read API metadata and discovery links. |

DeepSeek-V4.1-Flash and Gemma 4 31B accept text and image input. See
[Models](https://docs.prisminference.com/models.md) for the current capability matrix.

## OpenAI-compatible request

```typescript theme={"theme":{"light":"github-light","dark":"github-dark"}}
import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.PRISM_API_KEY,
  baseURL: "https://api.prisminference.com/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
    { role: "user", content: "Find the race condition in this worker: ..." },
  ],
});

console.log(response.choices[0].message.content);
```

Keep API keys on your server. Do not put them in browser code, client bundles,
or public repositories.

## Start building

> [card] [Get an API key](https://cal.com/team/prismai/demo)
>
> Ask the workspace owner for a key, or talk to sales for access.

> [card] [Quickstart](https://docs.prisminference.com/quickstart.md)
>
> Send a request with cURL, TypeScript, or Python.

> [card] [Models](https://docs.prisminference.com/models.md)
>
> Compare model IDs, context windows, and intended workloads.

> [card] [Chat Completions](https://docs.prisminference.com/api-reference/chat-completions.md)
>
> Read the OpenAI-compatible request and response contract.

> [card] [Streaming](https://docs.prisminference.com/guides/streaming.md)
>
> Process incremental Chat Completions output.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.