Qwen3 Embedding 8B (Venice)

venice standard tier Embedding

Open-weight multilingual embeddings served privately by Venice (no provider-side retention) — the choice for adult-site or otherwise sensitive text. 4096 native dimensions; request dimensions <= 2000 to index in pgvector.

metered
Published price
qwen3-embedding-8b
species_name
2026-11-01
Verified since
Call it

One request, the price in the response.

Pass species_name to pin this model; omit it and Fire uses the default for the endpoint. Every response carries meta.price.usd and meta.call_id.

curl -X POST https://fire.prosaga.net/v1/chat \
  -H "Authorization: Bearer $FIRE_API_KEY" \
  -d '{"species_name":"qwen3-embedding-8b", …}'

Strengths

embeddingsemantic-searchmultilingualprivatelow-cost

Modality

In: text  ·  Out: vector

Lineage

Family alibaba · genus qwen-embedding · served by venice

Capabilities

modality
embedding
dimensions
4096
max input tokens
8192
supports custom dimensions
yes
Similar models

Same job, different trade-offs.

Call Qwen3 Embedding 8B (Venice) with one key.

Free to sign up. Pay only when you top up.