# Qwen/Qwen3-Embedding-8B-TEE

> Qwen/Qwen3-Embedding-8B

This file is intended for AI coding agents wiring an application to this specific Chutes model.

## Important URLs

- Model page: https://chutes.ai/app/chute/chutes-qwen-qwen3-embedding-8b-tee
- Model llms.txt: https://chutes.ai/app/chute/chutes-qwen-qwen3-embedding-8b-tee/llms.txt
- Model OpenAPI 3.1 spec (this chute, callable): https://chutes.ai/app/chute/chutes-qwen-qwen3-embedding-8b-tee/openapi.json
- Global Chutes llms.txt: https://chutes.ai/llms.txt
- Full Chutes docs export: https://chutes.ai/llms-full.txt
- Management API OpenAPI (account/billing/keys, NOT this model): https://api.chutes.ai/openapi.json

## Model Identifiers

- Name: `Qwen/Qwen3-Embedding-8B-TEE`
- Chute ID: `21822836-bfa6-5426-b27e-dd5fdda1249e`
- Slug: `chutes-qwen-qwen3-embedding-8b-tee`
- Owner: `chutes`

## Authentication

- Use `Authorization: Bearer $CHUTES_API_KEY` for inference calls.
- Send JSON request bodies with `Content-Type: application/json` unless the endpoint documentation says otherwise.
- The request body is FLAT — send the request fields at the top level (no `input_args`/`args` wrapper).
- This model is served on its own host (`https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai`). Call the endpoint paths listed below directly.
- For base64 media fields, send raw base64 strings in API requests. The web playground may use temporary Blob upload references internally for large files before proxying to Chutes.

## Endpoints

### 1. POST /v1/embeddings

- Base URL: `https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai`
- Output content type: `application/json`

Request fields:

- `input` (string, required)
- `model` (string, optional) Default: null.

Example call:

```bash
curl -X POST "https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai/v1/embeddings" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "input": "Your text here",
  "model": "Qwen/Qwen3-Embedding-8B-TEE",
  "encoding_format": "float"
}'
```

### 2. GET /v1/models

- Base URL: `https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai`
- Output content type: `application/json`

Request fields:


Example call:

```bash
curl -X GET "https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai/v1/models" \
  -H "Authorization: Bearer $CHUTES_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```

## Model Facts

- Parameters: 8B (7.57B in safetensors)
- Architecture: Dense Qwen3 causal transformer used as a text embedding model (36 layers, hidden size 4096, last-token pooling)
- Context length: 40,960 tokens
- Modalities: text in → embedding out
- License: Apache-2.0
- Released: 2025-06
- Embedding dimension: Up to 4096; user-definable from 32 to 4096 (MRL support)
- Sequence length (model card): 32K tokens
- Languages: 100+ (including programming languages)
- Instruction aware: Yes; task instructions on the query side improve retrieval by 1-5% per the model card
- MTEB multilingual: 70.58 mean (task), No.1 on the leaderboard as of June 5, 2025, per model card
- Hugging Face: https://huggingface.co/Qwen/Qwen3-Embedding-8B

## Best For

- Multilingual semantic search and RAG retrieval across 100+ languages
- Code retrieval and cross-lingual retrieval
- Text classification and clustering pipelines built on embeddings
- Reranking-adjacent pipelines paired with Qwen3-Reranker models
- Confidential workloads: embedding proprietary documents inside a TEE

Not ideal for:

- Text generation or chat: this is an embedding model, it returns vectors, not tokens
- Latency-critical edge deployments where a 0.6B or 4B embedding model is sufficient
- Image or audio embedding: input is text only

## FAQ

### How many dimensions do the embeddings have?

Up to 4096. The model supports user-defined output dimensions from 32 to 4096 (MRL support per the model card), so you can truncate vectors to fit your vector database and latency budget with modest quality loss.

### What is the maximum input length?

The Hugging Face config sets max_position_embeddings to 40,960 tokens, and the model card lists a 32K sequence length. For retrieval quality, chunking long documents into passages is still standard practice.

### Do I need to add an instruction to my inputs?

For queries, yes, ideally: format them as 'Instruct: <one-sentence task description>\nQuery: <query>'. The model card reports a 1-5% retrieval improvement from query-side instructions. Documents should be embedded as-is without an instruction.

### Can I call it with the OpenAI SDK?

Yes. Point the SDK at base_url https://chutes-qwen-qwen3-embedding-8b-tee.chutes.ai/v1 with your Chutes API key and call client.embeddings.create(model="Qwen/Qwen3-Embedding-8B-TEE", input="..."). The endpoint follows the OpenAI embeddings contract.

### What does the TEE suffix mean?

The model runs inside a Trusted Execution Environment: confidential-compute hardware that keeps prompts and outputs encrypted in memory and attestable. It is a serving-level property and does not change the embeddings the model produces.

### What license is Qwen3-Embedding-8B under? Can I use it commercially?

Apache-2.0, per the Hugging Face repo Qwen/Qwen3-Embedding-8B. Apache-2.0 permits commercial use, modification, and redistribution with attribution and license notice.

### How good is it compared to other embedding models?

Its model card reports 70.58 mean task score on MTEB multilingual (No.1 on the leaderboard as of June 5, 2025), 75.22 on MTEB English v2, and 73.84 on C-MTEB Chinese, ahead of gte-Qwen2-7B-instruct, NV-Embed-v2, and text-embedding-3-large in the card's comparison tables.


## Model Guide & Sources

- Full model guide: https://chutes.ai/docs/models/chutes-qwen-qwen3-embedding-8b-tee
- Source: https://huggingface.co/Qwen/Qwen3-Embedding-8B
- Source: https://chutes.ai/app/chute/chutes-qwen-qwen3-embedding-8b-tee/llms.txt

## Agent Integration Checklist

- Pick the endpoint path that matches the desired task.
- Set `CHUTES_API_KEY` in the server-side environment only.
- Validate required fields before sending requests.
- For media models, keep file upload, base64 conversion, and output preview/download handling explicit in the app UI.