Qwen3 Embedding 8B
by Alibaba
Qwen's large open embedding model.
Qwen3 Embedding 8B outputs 4096 dimensions with instruction support and a long input window, strong on multilingual retrieval and code.
More details
Qwen3 Embedding 8B by Alibaba is a standard-speed text embedding model. Qwen3 Embedding 8B outputs 4096 dimensions with instruction support and a long input window, strong on multilingual retrieval and code. It returns 4096-dimension vectors, up to 32,768 tokens per input, batches of 100 inputs per request, multilingual coverage, instruction prefixes for asymmetric retrieval.
Qwen3 Embedding 8B is priced at $0.02 per million input tokens. A million tokens is roughly 750,000 words, so a corpus of a few thousand pages costs $0.02 to embed once. You can embed text with Qwen3 Embedding 8B on idapt.app alongside 200+ AI models in one workspace.
Pricing
Per 1M input tokens
$0.02
10k texts × 500 tokens
$0.10
Billed on input tokens only - output is vectors
Capabilities
Native dimensions
4096
Max input tokens
32,768
Batch size
100
Tuned for
any
What comes back
A vector of 4096 numbers per input — no text, no file, and nothing to play. A capture records the shape, the norm and a fingerprint so two runs can be compared without shipping the payload:
vector[4096] norm 1.000000 sha256 0f3a91c2… first 8: 0.012, -0.004, …
Illustrative shape, not an embedding of your data.
Qwen3 Embedding 8B questions
Who makes Qwen3 Embedding 8B?
Qwen3 Embedding 8B is made by Alibaba and is served on idapt through the Alibaba API.
How much does Qwen3 Embedding 8B cost?
$0.02 per million input tokens. Embedding is billed on the text you send in, not on the vector you get back, so a few thousand pages typically cost well under a dollar.
How many dimensions does Qwen3 Embedding 8B return?
4096 dimensions. The size is fixed for this model.
How much text can Qwen3 Embedding 8B embed at once?
Each input can be up to 32,768 tokens, and one request can carry up to 100 inputs.
Which languages does Qwen3 Embedding 8B support?
It is multilingual: text in most major languages can be embedded into the same vector space, so you can compare a query in one language against documents in another.
What is Qwen3 Embedding 8B best used for?
It is tuned for general-purpose embedding. Use it to build a vector index for semantic search, retrieval-augmented generation, deduplication, clustering or classification.
Does Qwen3 Embedding 8B take instructions?
Yes. You can prefix the text with a short task instruction (for example, a query intent), which improves asymmetric retrieval where the query and the document are not shaped alike.
Embedding a million tokens - roughly 750,000 words - costs about $0.02 on this model.