tokenstat
tokenstat

Qwen3 Embedding 8B

Qwen/Qwen3-Embedding-8B · rates as of · Benchmarks · Plans · Calculator

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Cheapest input
$0.01
$/MTok · models.dev
Cheapest output
$0
$/MTok
Context
41K
tokens
Offers
10
3 sources

Offers

Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.

SourceProviderInputOutputCache readContext
models.devcheapestQwen/Qwen3-Embedding-8BHugging Face$0.01$0$032K
models.devQwen/Qwen3-Embedding-8BNebius$0.01$0$033K
OpenRouterqwen/qwen3-embedding-8bOpenRouter$0.01$0$033K
LiteLLMllamagate/qwen3-embedding-8b$0.02$0$0.002
LiteLLMnovita/qwen/qwen3-embedding-8b$0.07$0$0.007
models.devqwen3-embedding-8bScaleway$0.1$0$0.0133K
models.devqwen3-embedding-8bRegolo AI$0.1$0.1$033K
LiteLLMqwen/qwen3-embedding-8b$0.1$0$0.01
LiteLLMqwen3-embedding-8b$0.1$0$0.01
models.devQwen/Qwen3-Embedding-8BEvroc$0.115$0.115$041K

Capabilities

  • Open weights
  • In: text
  • Out: text
  • Out: embeddings
Knowledge cutoff: 2024-12Released: 2026-02-01Family: text-embedding

See what you actually spent

tokenstat prices your local sessions at list rates like these, with the cache split kept honest. Free, open source, runs on your machine.

$ curl -fsSL https://tokenstat.ai/install.sh | bash