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

> ## Agent Instructions
> To act on Atlan objects, use the Atlan MCP server at https://api.atlan.com/mcp or the SDK. To install or publish skills from a terminal, use the `aireg` CLI; `aireg --map json` prints its command map. The `atlanai` CLI is deprecated. Run a read-only identity check before any write.
> The docs MCP server at /mcp searches these docs only. It cannot read or change Atlan objects.
> SDK packages: Python `atlanai` (PyPI) and TypeScript `@atlanai/sdk` (npm). Show Python first, then TypeScript.
> These docs cover Atlan AI Registry, Atlan's hosted product. The AI registry specification and aireg CLI are maintained separately. /open-source lists publicly reachable signed installers and explains that the source repository and hosted CLI reference currently require GitHub access. Do not claim the repository or its reference docs are publicly accessible. Use these docs for Atlan-specific setup such as the adapter, sign-in and workspaces.

# Model API compatibility

> Check the model endpoints, naming rules, and request limits served by Model Gateway.

Use the OpenAI or Anthropic dialect supported by your client. The gateway translates requests onto a provider protocol that can serve the selected model and operation.

| Client surface | Endpoint | Support |
| - | - | - |
| Model catalog | `GET /openai/v1/models` | Lists models visible to the caller. Supports `modality` and `is_provider_disabled_included` filters. |
| Model lookup | `GET /openai/v1/models/<provider>/<model>` | Resolves one model without inference; `modality` can validate its intended use. |
| Chat completions | `POST /openai/v1/chat/completions` | Unary and streaming; client-executed tool calls. |
| Responses | `POST /openai/v1/responses` | Stateless requests. Retrieve, delete, and cancel are unavailable. |
| Legacy completions | `POST /openai/v1/completions` | Translates onto a chat model. |
| Messages | `POST /anthropic/v1/messages` | Unary and streaming for models that support the Anthropic dialect. |
| Embeddings | `POST /openai/v1/embeddings` | Requires an embedding model. |
| Decisions | `POST /openai/v1/decisions` | Requires a compatible classifier model and provider decision protocol. |
| Images | `POST /openai/v1/images/generations`, `/images/edits`, `/images/variations` | Provider and model dependent. |
| Speech and transcription | `POST /openai/v1/audio/speech`, `/audio/transcriptions` | Provider and model dependent. |
| Realtime | `GET /openai/v1/realtime` | WebSocket upgrade; requires a compatible realtime model. |
| Rerank and moderation | `POST /openai/v1/rerank`, `/moderations` | Requires a provider and model that serve the operation. |

A route's existence does not establish support for every provider. Check the model's modality and test the request shape your application uses.

## Model names

Send the exact qualified model `id`, such as `openai-prod/<model-name>`, returned by the catalog. The provider prefix selects the configured connection. A bare upstream name can fail to resolve or become ambiguous when more than one connection serves it.

Disabled or archived models cannot route. Disabled or archived providers also prevent their models from routing. Catalog queries can include models behind disabled providers when requested, with `is_routable: false`.

## Tools and conversation state

Tool definitions and tool results travel in the client's request dialect. Your application executes client-side tools and sends their results in a later request. Hosted tools such as provider-run web search are unavailable through the Responses compatibility surface.

The gateway does not provide the Assistants API, vector stores, batches, fine-tuning, or Anthropic token counting. Responses requests must carry the conversation state they need. Anthropic `metadata` is accepted and ignored; unsupported conversation-editing `context_management` is refused.

## Provider-specific requests

Reasoning effort, structured output, images, audio, cache controls, and provider-specific parameters depend on the model family and provider. A parameter your client accepts may still be refused for the selected model. Use the returned error's field and reason to adjust the request.

For Vertex image generation, Gemini image models use Gemini's native image API. Responses return base64 image data in PNG or JPEG. Unsupported size ratios, URL responses, and transparent backgrounds are refused. See the [image constraints](/gateway/model/how-tos/connect-a-client#supported-operations) before using OpenAI image options with Vertex.

See [Model Gateway errors](/gateway/model/troubleshooting) for resolution, compatibility, throttling, and upstream errors.


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