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

# Choose Your API

> Answers API vs Agent API — pick the right surface in one minute.

Mirobody exposes the same grounded health agent through **two surfaces**. Both answer from the Subject's real, standardized health data with a traceable tool trace — they differ in who orchestrates.

<CardGroup cols={2}>
  <Card title="Answers API" icon="comment-dots" href="/en/api-reference/chat">
    `POST /v1/chat/completions` — a **closed grounded completion**. One shot in, one evidence-backed answer out. No client tools, no state. Perfect as a drop-in OpenAI swap — or as **one tool inside your own agent**.
  </Card>

  <Card title="Agent API" icon="robot" href="/en/api-reference/responses">
    `POST /v1/responses` — the **recommended agent surface** (OpenAI Responses-compatible). Multi-turn state (`store`, `previous_response_id`, `session_id`), **your own function tools** with full handoff, standard `response.*` streaming.
  </Card>
</CardGroup>

## Decision table

| You want to…                                                                                                           | Use                                                                                             |
| ---------------------------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------- |
| Replace an OpenAI chat call with health-grounded answers, zero new concepts                                            | **Answers**                                                                                     |
| Give your existing agent (any framework, any model) a "query this user's health records" capability                    | **Answers**, [wrapped as a tool](/en/api-reference/use-as-a-tool)                               |
| Build a health assistant where **Mirobody is the agent** and calls **your** tools (booking, notifications, EHR writes) | **Agent** ([function calling](/en/api-reference/function-calling))                              |
| Multi-turn conversations without resending history                                                                     | **Agent** (`previous_response_id` / `session_id` — [state](/en/api-reference/state-and-memory)) |
| Use the **openai-agents SDK** as-is (just change `base_url`)                                                           | **Agent**                                                                                       |
| Structured-output / JSON-mode responses                                                                                | Neither — `response_format` is rejected on Answers; put shaping in your outer agent             |

## What's identical on both

* **Grounding** — the same server-side toolset over the same standardized data ([Data Plane](/en/api-reference/data)); evidence in `health_records` / `citations`; server tool trace in the `tool_steps` extension.
* **Models** — `mirobody-flash` / `mirobody-expert` ([Models](/en/api-reference/models)).
* **Tenancy** — the `user` → Subject isolation model ([Overview](/en/api-reference/overview#multi-tenancy-the-user-field)).
* **Usage accounting** — visible input tokens billed to you, platform overhead broken out as `system_tokens`.

## What's different

|                   | Answers (`/v1/chat/completions`)            | Agent (`/v1/responses`)                                        |
| ----------------- | ------------------------------------------- | -------------------------------------------------------------- |
| Protocol          | OpenAI Chat Completions                     | OpenAI Responses                                               |
| State             | Stateless — resend history                  | `store` (default `true`), `previous_response_id`, `session_id` |
| Client tools      | Rejected (`400 unsupported_parameter`)      | `tools` with `function_call` handoff                           |
| Streaming         | `chat.completion.chunk` frames              | `response.*` event protocol                                    |
| Server tool trace | `message.tool_steps` + top-level extensions | top-level `tool_steps` + `response.mirobody_tool_call` event   |

Still unsure? Start with the [Quickstart](/en/api-reference/quickstart) — its final step shows both in \~15 lines.