Skip to content

Qwen3 Embedding 8B

Per 1M tokens
$0.0105
Context
33Ktokens
Terminal
curl https://deference.si/v1/embeddings \
  -H "Authorization: Bearer $DEFERENCE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-embedding-8b",
    "input": "The quick brown fox"
  }'
Needs an API keyGet one

Pricing and limits

  • Max output32,000tokens

OpenRouter's price plus OpenRouter's 5% platform fee. Deference adds no markup.