---
title: "Sync"
method: POST
path: "/v1/inference"
tags: ["Inference v2"]
---

# Sync

`POST /v1/inference`

Synchronous inference endpoint (OpenAI-compatible path).

Submits an inference request and polls for results up to 30 seconds.
If stream=true, returns SSE text/event-stream with token deltas.

## Request body

- V1InferenceRequest — OpenAI-compatible inference request for /v1/inference.
  - `model` string, required — Model name or HuggingFace repo
  - `inputs` union, required — Text input(s) for inference
    - string[]
    - string
  - `max_tokens` integer
  - `temperature` number
  - `stream` boolean — Stream response via SSE

## Response `200`

Successful Response

- unknown

## Other responses

- `422` — Validation Error

---

[API](https://skmtc.net/aabiro/apis/xcelsior.md) · [All operations](https://skmtc.net/aabiro/apis/xcelsior/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/aabiro/xcelsior/revisions/b4f5ef136e6a/schema)