--- title: Classification Models --- This document describes the `/v1/classify` API endpoint in SGLang, which is compatible with vLLM's classification API format. ## Overview The classification API allows you to classify text inputs using classification models. This implementation follows the same format as vLLM's 0.7.0 classification API. ## API endpoint ```text Output POST /v1/classify ``` ## Request format ```json Config { "model": "model_name", "input": "text to classify" } ``` ### Parameters The name of the classification model to use. The text to classify. User identifier for tracking. Request ID for tracking. Request priority. ## Response format ```json Config { "id": "classify-9bf17f2847b046c7b2d5495f4b4f9682", "object": "list", "created": 1745383213, "model": "jason9693/Qwen2.5-1.5B-apeach", "data": [ { "index": 0, "label": "Default", "probs": [0.565970778465271, 0.4340292513370514], "num_classes": 2 } ], "usage": { "prompt_tokens": 10, "total_tokens": 10, "completion_tokens": 0, "prompt_tokens_details": null } } ``` ### Response fields Unique identifier for the classification request. Always `"list"`. Unix timestamp when the request was created. The model used for classification. Array of classification results. Index of the result. Predicted class label. Array of probabilities for each class. Total number of classes. Token usage information. Number of input tokens. Total number of tokens. Number of completion tokens (always `0` for classification). Additional token details (optional). ## Example usage ```bash Command curl -v "http://127.0.0.1:8000/v1/classify" \ -H "Content-Type: application/json" \ -d '{ "model": "jason9693/Qwen2.5-1.5B-apeach", "input": "Loved the new café—coffee was great." }' ``` ```python Example import requests import json # Make classification request response = requests.post( "http://127.0.0.1:8000/v1/classify", headers={"Content-Type": "application/json"}, json={ "model": "jason9693/Qwen2.5-1.5B-apeach", "input": "Loved the new café—coffee was great." } ) # Parse response result = response.json() print(json.dumps(result, indent=2)) ``` ## Supported models The classification API works with any classification model supported by SGLang, including:
Model Type
`LlamaForSequenceClassification` Multi-class classification
`Qwen2ForSequenceClassification` Multi-class classification
`Qwen3ForSequenceClassification` Multi-class classification
`BertForSequenceClassification` Multi-class classification
`Gemma2ForSequenceClassification` Multi-class classification
The API automatically uses the `id2label` mapping from the model's `config.json` file to provide meaningful label names instead of generic class names. If `id2label` is not available, it falls back to `LABEL_0`, `LABEL_1`, etc., or `Class_0`, `Class_1` as a last resort.
Model Type
`InternLM2ForRewardModel` Single reward score
`Qwen2ForRewardModel` Single reward score
`LlamaForSequenceClassificationWithNormal_Weights` Special reward model
The `/classify` endpoint in SGLang was originally designed for reward models but now supports all non-generative models. The `/v1/classify` endpoint provides a standardized vLLM-compatible interface for classification tasks. ## Error handling The API returns appropriate HTTP status codes and error messages:
Status code Meaning
`400 Bad Request` Invalid request format or missing required fields
`500 Internal Server Error` Server-side processing error
Error response format: ```json Config { "error": "Error message", "type": "error_type", "code": 400 } ``` ## Implementation details Handles routing and request/response models in `sgl-model-gateway/src/protocols/spec.rs`. Implements the actual endpoint in `python/sglang/srt/entrypoints/http_server.py`. Handles the classification logic in `python/sglang/srt/entrypoints/openai/serving_classify.py`. ## Testing Use the provided test script to verify the implementation: ```bash Command python test_classify_api.py ``` ## Compatibility This implementation is compatible with vLLM's classification API format, allowing seamless migration from vLLM to SGLang for classification tasks.