Qwen3 Embedding 8B API

Qwen3 Embedding 8B is an embedding model by Alibaba Qwen, available on the Venice API as text-embedding-qwen3-8b. It runs privately, with zero data retention.

Qwen3 Embedding 8B API pricing

Model ID	Variant	Privacy	Price
`text-embedding-qwen3-8b`	Standard	Private	$0.01 per 1M tokens

Qwen3 Embedding 8B specifications

Spec	Value
Provider	Alibaba Qwen
Released	Apr 17, 2026
Privacy	Private
Open weights	Yes
Dimensions	4,096
Max input	32K tokens

How to use the Qwen3 Embedding 8B API

Send requests to POST https://api.venice.ai/api/v1/embeddings with "model": "text-embedding-qwen3-8b" and your API key.

curl https://api.venice.ai/api/v1/embeddings \
  -H "Authorization: Bearer $VENICE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "text-embedding-qwen3-8b",
    "input": "Private AI for everyone."
  }'

Qwen3 Embedding 8B API FAQ

How much does the Qwen3 Embedding 8B API cost?

$0.013 per 1M input tokens. Prices are in USD and can be paid in DIEM at parity.

What is the Qwen3 Embedding 8B model ID?

Use text-embedding-qwen3-8b as the model parameter.

Is the Qwen3 Embedding 8B API private?

Qwen3 Embedding 8B is private: requests run on infrastructure Venice controls with zero data retention, and prompts and outputs are never stored or used for training.

How many dimensions do Qwen3 Embedding 8B embeddings have?

4,096 dimensions, with up to 32K input tokens per item.

Which endpoint does the Qwen3 Embedding 8B API use?

Call POST /embeddings.

Related models

Qwen3 Embedding 0.6B API: $0.01 per 1M tokens
BGE-EN-ICL API: $0.01 per 1M tokens
Multilingual E5 Large Instruct API: $0.01 per 1M tokens
Nemotron Embed VL 1B v2 API: $0.01 per 1M tokens

Explore

By modality