ReadyGPU TEE

Qwen: Qwen3 Embedding 8B

Model IDqwen/qwen3-embedding-8b

The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. This series inherits the exceptional multilingual capabilities, long-text understanding, and reasoning skills of its foundational model. The Qwen3 Embedding series represents significant advancements in multiple text embedding and ranking tasks, including text retrieval, code retrieval, text classification, text clustering, and bitext mining.

Start building Docs

input

$0.01/M

output

Free/M

context

33K

added

Jan 14, 2026

Supported API shape

input

text · embeddings

output

embeddings

tools

Not listed

json mode

Not listed

Verification

Available evidence. Use a verified client to authenticate the quote, connection, and receipt.

Verify private inference

receipt

signed receipt + hashes

attestation

gateway report

session

attested upstream

serving provider

read from receipt session

Provider

Phala

GPU TEE

input

$0.01/M

output

Free/M

context

33K

Performance comparison

Last 72h · UTC

$ pip install openai

1from openai import OpenAI
2import os
3
4MODEL = "qwen/qwen3-embedding-8b"
5
6client = OpenAI(
7    base_url="https://inference.phala.com/v1",
8    api_key=os.environ["PHALA_AI_API_KEY"],
9)
10
11response = client.embeddings.create(
12    model=MODEL,
13    input="Phala keeps inference data inside a confidential runtime.",
14)
15
16print(response.data[0].embedding[:8])

$ npm install openai

1import OpenAI from "openai"
2
3const MODEL = "qwen/qwen3-embedding-8b"
4
5const openai = new OpenAI({
6  baseURL: "https://inference.phala.com/v1",
7  apiKey: process.env.PHALA_AI_API_KEY,
8})
9
10const response = await openai.embeddings.create({
11  model: MODEL,
12  input: "Phala keeps inference data inside a confidential runtime.",
13})
14
15console.log(response.data[0].embedding.slice(0, 8))

1curl https://inference.phala.com/v1/embeddings \
2  -H "Authorization: Bearer $PHALA_AI_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "qwen/qwen3-embedding-8b",
6    "input": "Phala keeps inference data inside a confidential runtime."
7  }'

More models

Other private inference routes.

View catalog

encrypted

MoonshotAI: Kimi K3.1 Pro

Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D creation, financial research, and end-to-end agentic knowledge work, with native image and video understanding.

context

1.0M

input

$2.00/M

$0.20/M cache read

encrypted

Jared Palmer: Kev 4B

Kev 4B is an open-weight System One model from Jared Palmer, fine-tuned from Qwen3.5 4B Base. It makes fast, structured decisions for software: given a state and typed questions, it returns calibrated answers instead of text, as a yes/no probability (noul), a pick among options (choice), or a level on a scale (score). Call it through POST /v1/systemone, compatible with the TypeSafe SDK; it does not serve chat. Served on Phala in a TDX-attested enclave with an 8,192-token context.

context

input

$0.042/M

encrypted

Phala: Qwen3.8 27B Uncensored (Aggressive)

HauhauCS Qwen3.8-27B Uncensored Aggressive, using the pinned Q8_K_P GGUF and BF16 vision projector. Served with SGLang on a Phala TDX-attested H200, with text and image input and a 262144-token context.

context

262K

input

$0.30/M

$0.05/M cache read

encrypted

Z.ai: GLM 5.3

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context window. Served as a text-only TEE deployment via Phala.

context

1.0M

input

$1.40/M

$0.26/M cache read