---
title: "POST /v1/generate/{model}"
method: POST
path: "/v1/generate/{model}"
tags: ["inference"]
---

# POST /v1/generate/{model}

`POST /v1/generate/{model}`

SIE-native generation with optional bounded inline images. Omit `stream` or set it to false for a blocking JSON response; set `stream: true` for SIE-native Server-Sent Events terminated by `data: [DONE]`. The model path parameter must use the SIE-safe ID (for example `Qwen__Qwen3-4B-Instruct`); HF-style slashes reject with 400.

## Path parameters

- `model` string, required

## Headers

- `X-SIE-MACHINE-PROFILE` string, nullable
- `X-SIE-Pool` string, nullable
- `X-SIE-SDK-Version` string, nullable

## Request body

- GenerateRequest — SIE-native text-generation request. Set ``stream`` to true for SSE.
  - `frequency_penalty` number, double, nullable
  - `grammar` unknown
  - `images` NativeGenerateImage[], nullable — Optional inline images paired with ``prompt``. When present, the worker renders one user turn through the model's native chat template.
    - `data` string, required — Canonical standard-base64 encoded image bytes, at most 16 MiB decoded. Remote URLs are not accepted.
    - `format` string, nullable — Short media-format hint such as ``png`` or ``jpeg``.
  - `logit_bias` object, nullable — Per-token additive sampler bias. Keys are integer token ids encoded as strings; values are finite numbers in ``[-100, 100]``. At most 1024 entries are accepted.
  - `logprobs` boolean, nullable — Return per-token log probabilities on native SSE chunks. Native blocking responses reject this field because they have no logprob response member.
  - `lora_adapter` string, nullable — Served LoRA adapter name. The gateway validates it against the resolved model before queue dispatch.
  - `max_new_tokens` integer, required
  - `options` unknown
  - `presence_penalty` number, double, nullable
  - `prompt` string, required
  - `prompt_cache_key` string, nullable
  - `routing_key` string, nullable
  - `safety_identifier` string, nullable — Sensitive PII - parsed and dropped, never logged or forwarded.
  - `seed` integer, nullable — Optional signed 64-bit per-request sampling seed. Reproducibility is best effort, not guaranteed, and depends on the active generation backend and deployment configuration. Non-integer or out-of-range values reject with 400 invalid_request.
  - `stop` string[], nullable — Stop sequences for the native generate surface.
  - `stream` boolean, nullable — SSE streaming. When true, the 200 response uses `text/event-stream`; each `data:` event contains a SIE-native `GenerateChunk` JSON object and the stream terminates with `data: [DONE]`. Defaults to false. Non-boolean values reject with 400 invalid_request.
  - `temperature` number, float, nullable
  - `top_logprobs` integer, nullable — Number of alternative tokens per position. Requires ``logprobs: true`` and ``stream: true``.
  - `top_p` number, float, nullable

## Response `200`

Generated text as blocking JSON, or SIE-native SSE `GenerateChunk` events when `stream: true`; SSE terminates with `data: [DONE]`.

- GenerateResponse
  - `attempt_id` string, required
  - `finish_reason` string, required
  - `model` string, required
  - `text` string, required
  - `tpot_ms` number, double, nullable
  - `ttft_ms` number, double, nullable
  - `usage` GenerateUsage
    - `completion_tokens` integer, required
    - `prompt_tokens` integer, required
    - `total_tokens` integer, required

## Other responses

- `400` — Invalid request
- `401` — Missing or invalid bearer token (inference token)
- `404` — Model not found
- `413` — Request body too large
- `500` — Worker emitted malformed response; gateway auth enabled but no tokens configured
- `502` — Terminal model load failure (MODEL_LOAD_FAILED)
- `503` — Provisioning in progress, queue unavailable, or model loading
- `504` — Generation timeout

---

[API](https://skmtc.net/superlinked/apis/sie-gateway.md) · [All operations](https://skmtc.net/superlinked/apis/sie-gateway/llms.txt) · [OpenAPI document](https://skmtc-service-staging.skmtc.workers.dev/v1/apis/superlinked/sie-gateway/versions/06a326e2c3e9/schema)
