# Responses & streams

> Realtime and async responses, flex processing, server-sent events, and streaming IDs under /v1/responses and /v1/streams.

Source: https://sference.com/docs/guides/responses

Inference on sference is modeled as a **response** resource: you create it, observe status, and read structured **output** (text, optional reasoning, errors). A response can be **realtime** (blocking, returns when inference finishes) or **async** (`background: true`, polled or streamed to completion). When you need **incremental** delivery, pair responses with **streams** and the events API.

> **Where to read schemas**
>
> Open **API Reference** in the sidebar → **Inference** → **Inference API** for `POST/GET /v1/responses` and **`/v1/responses/events`**. Everything is generated from the same OpenAPI document as production.

## Mental model

1. **`POST /v1/responses`**: enqueue work (`model`, `input[]`, optional sampling knobs, metadata).
2. **`GET /v1/responses/{id}`**: poll `status`, `output`, and `error` until the job reaches a terminal state.
3. **`GET /v1/responses/events`**: cursor through **SSE-style** event history when you want a feed instead of polling the full document every time.
4. **Streams** (via the [Python SDK](https://sference.com/docs/sdk) / [CLI](https://sference.com/docs/cli)): allocate a **stream id** to group related responses and fan out chunks independently of the JSON document.

If you are coming from the [OpenAI Responses API](https://developers.openai.com/api/docs/guides/text), the verbs should feel familiar; sference adds async windows and European residency guarantees on the infrastructure side.

## When to use streams

Use **streams** when:

- UX demands **partial tokens** or progressive rendering.
- Downstream systems already speak **chunked HTTP** or SSE.
- You want to decouple **transport** from the final aggregated response record.

For **massive static backfills**, prefer [Batch inference](https://sference.com/docs/guides/batches); it is cheaper, simpler to retry, and easier to reconcile in compliance exports.

## Processing modes

- **realtime**: sync `/v1/chat/completions`, [`/v1/messages`](https://sference.com/docs/anthropic), or blocking `POST /v1/responses` (no window field). Deadline = now; the connection waits for the result.
- **flex**: `/v1/chat/completions` or `POST /v1/responses` with `service_tier: "flex"`: discounted tokens in exchange for lower scheduling priority. (`/v1/messages` has no `service_tier` field and always runs realtime.) Flex requests may queue significantly longer than realtime (up to 30 minutes), so raise client timeouts; a flex request that cannot complete in time fails with **408** (OpenAI SDKs retry automatically). Flex is enabled per account; [contact us](mailto:hello@sference.com) to turn it on.
- **async (24h)**: background responses (`background: true`, optionally `metadata.completion_window: "24h"`, the only window value), SDK/CLI streams, and batches (`window` on create). Queued work scheduled to complete within the window.

All three modes share the same models, endpoints, and request shapes; only scheduling priority and price differ. Responses echo the tier actually served in `service_tier`.

## Next steps

- [Quickstart](https://sference.com/docs/quickstart): API key, CLI install, and your first response.
- [Models](https://sference.com/docs/models): Choosing and pinning checkpoints.
- [API Reference](https://sference.com/docs/api-reference): Exact request and response bodies.