# Model inference

Start by [listing callable models](../models.md) to obtain an inference model identifier, then select an API supported by the model.

## Choose a task

| Task | Page | Description |
| --- | --- | --- |
| List callable models | [List callable models](../models.md) | List the Genesis models available to the current credential and obtain their identifiers, capabilities, and prices. |
| Chat generation (Chat Completions) | [Chat generation (Chat Completions)](../text-generation/index.md) | Use the Chat Completions API to generate a reply from input messages. The creation endpoint describes streaming requests and event handling. |
| Message generation (Messages) | [Message generation (Messages)](../messages/index.md) | Use the Anthropic Messages protocol to generate a reply. Before generation, you can count the tokens in the input messages with the token-counting endpoint, which does not generate a reply. |
| Response generation and management (Responses) | [Response generation and management (Responses)](../responses/index.md) | Use the Responses API to generate content. With a personal access token and a model that supports stateful requests, you can also save generation records, then retrieve their inputs and results or delete them. |
| Manage local conversations | [Conversation management](../conversations/index.md) | Maintain local conversation metadata and item summaries; your application maintains message bodies and model request context. |
| Embeddings | [Embeddings](../text-embeddings/index.md) | Convert input content into vectors. |
| Document reranking | [Document reranking](../text-reranking/index.md) | Rank candidate documents by their relevance to a query. |

```{toctree}
:hidden:
:maxdepth: 1

List callable models <../models>
Chat generation (Chat Completions) <../text-generation/index>
Message generation (Messages) <../messages/index>
Response generation and management (Responses) <../responses/index>
Conversation management <../conversations/index>
Embeddings <../text-embeddings/index>
Document reranking <../text-reranking/index>
```