# Overview

> Low-latency European inference behind an OpenAI-compatible surface: realtime first, with flex and async windows for background work. Quickstart, models, and full HTTP reference.

Source: https://sference.com/docs

**sference** exposes European inference behind an **OpenAI-compatible** HTTP API, tuned first for **realtime** traffic, the sync path you use when a user is waiting, where most traffic runs. Two further modes share the same endpoint and the same GPU fleet when work does not have to block: **flex** (discounted sync at lower scheduling priority, via `service_tier: "flex"`) and **async** (background responses, streams, and batches on a **24h** completion window). Pin model versions and keep a compliance-grade trail, without replatforming how your team already calls models.

[Quickstart](https://sference.com/docs/quickstart) · [CLI](https://sference.com/docs/cli) · [Python SDK](https://sference.com/docs/sdk) · [Models](https://sference.com/docs/models) · [API Reference](https://sference.com/docs/api-reference)

## Developer quickstart

Export an API key and make a realtime request. It is OpenAI-shaped, so an existing client needs only a new base URL and model id:

```bash
export SFERENCE_API_KEY="sk_..."
curl https://api.sference.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SFERENCE_API_KEY" \
  -d '{"model":"Qwen/Qwen3.6-35B-A3B","messages":[{"role":"user","content":"Say hello in one sentence."}]}'
```

Prefer the CLI? Install it and authenticate:

```bash
curl -fsSL https://raw.githubusercontent.com/s-ference/sference/main/install.sh | sh
sference auth login --api-key "$SFERENCE_API_KEY"
```

Step-by-step: **[Quickstart](https://sference.com/docs/quickstart)**. Prefer Python? See **[Python SDK](https://sference.com/docs/sdk)**.

- [Quickstart](https://sference.com/docs/quickstart): API key, CLI install, and your first response, curl optional.
- [Models](https://sference.com/docs/models): How we think about tiers, pinning, and the catalog, and where to look in API Reference.

- [Custom Models](https://sference.com/docs/custom-models): Bring your own Hugging Face weights: fine-tunes and distilled models on the same API.
- [Deployments](https://sference.com/docs/deployments): Dedicated capacity for a base or custom model: pick a performance tier, we run it.

## Official clients

- [Python SDK](https://sference.com/docs/sdk): sference-sdk on PyPI, plus a copy-paste prompt for Cursor and Claude Code.
- [CLI](https://sference.com/docs/cli): One-line install: curl install.sh | sh. Auth, batches, streams.

## Bring your existing client

- [Anthropic Messages API](https://sference.com/docs/anthropic): POST /v1/messages: point the anthropic SDK at sference and run open models.
- [Claude Code](https://sference.com/docs/anthropic/claude-code): One command to run Claude Code on open models, with hybrid routing.

OpenAI-shaped clients need only a base-URL change: `/v1/chat/completions`, `/v1/responses`, and `/v1/embeddings` are OpenAI-compatible.

## Choose a workload

- [Responses & streams](https://sference.com/docs/guides/responses): Realtime and async responses, events, and `/v1/streams` when you want incremental output.
- [Batch API](https://sference.com/docs/guides/batches): Enqueue large jobs on the 24h window: chat or Responses row bodies, poll status, download JSONL.
- [HTTP reference](https://sference.com/docs/api-reference): Every path and schema generated from our OpenAPI spec, including control plane routes.

## Product & compliance

For positioning, regulation, and workloads, use the [marketing site](https://sference.com/) and [use cases](https://sference.com/#use-cases).