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.
Inference API
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 · CLI · Python SDK · Models · 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:
export SFERENCE_API_KEY="sk_..."
curl https://api.sference.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $SFERENCE_API_KEY" \
-d '{"model":"Qwen/Qwen3.6-35B-A3B","messages":[{"role":"user","content":"Say hello in one sentence."}]}'Prefer the CLI? Install it and authenticate:
curl -fsSL https://raw.githubusercontent.com/s-ference/sference/main/install.sh | sh
sference auth login --api-key "$SFERENCE_API_KEY"Step-by-step: Quickstart. Prefer Python? See Python SDK.
Quickstart
API key, CLI install, and your first response, curl optional.
Models
How we think about tiers, pinning, and the catalog, and where to look in API Reference.
Custom Models
Bring your own Hugging Face weights: fine-tunes and distilled models on the same API.
Deployments
Dedicated capacity for a base or custom model: pick a performance tier, we run it.
Official clients
Python SDK
sference-sdk on PyPI, plus a copy-paste prompt for Cursor and Claude Code.
CLI
One-line install: curl install.sh | sh. Auth, batches, streams.
Bring your existing client
Anthropic Messages API
POST /v1/messages: point the anthropic SDK at sference and run open models.
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
Realtime and async responses, events, and `/v1/streams` when you want incremental output.
Batch API
Enqueue large jobs on the 24h window: chat or Responses row bodies, poll status, download JSONL.
HTTP 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 and use cases.