Alibaba Cloud: Qwen3.7 Text Embedding
qwen3.7-text-embedding- Input / Output
- $0.0735 / $0.00
- Context
- 128K
- Modalities
- Embedding
About Qwen3.7 Text Embedding
Qwen3.7 Text Embedding is Alibaba's flagship text embedding model, turning multilingual text into vectors for retrieval and clustering. Alibaba documents very long single inputs, output sizes from 256 to 2560 dimensions, task instructions, and sparse vectors. It is the full-size option, while Qwen3.7 Text Embedding Flash is the lighter one.
Where it works well
- Accepts very long single inputs, which suits whole-document embedding instead of chunking.
- Output sizes of 256 to 2560 dimensions let you tune index size against detail.
- An instruct parameter lets you describe the retrieval task, such as searching documentation.
- Supports sparse vector output beside dense vectors for hybrid search, according to Alibaba.
When to choose another model
- Higher dimensions cost more index storage, so the Flash version suits very large collections better.
- It embeds text only; images and video need Qwen3-VL-Embedding.
Getting started
Create API key
Create a key in Console, then use it with every model on the platform.
Send your first request
Copy the example for your language and run it against the endpoint.
EmbeddingTokenLab endpointPOST/v1/embeddingscurl -X POST "https://api.tokenlab.sh/v1/embeddings" \ -H "Authorization: Bearer sk-xxx" \ -H "Content-Type: application/json" \ -d '{ "model": "qwen3.7-text-embedding", "input": "The quick brown fox jumps over the lazy dog." }'
Parameters
Embedding
| Parameter | Values and limits | Default | Notes |
|---|---|---|---|
dimensions | 256, 512, 768, 1024, 1536, 2048, 2560 | Not provided | Not provided |
encoding_format | float | Not provided | Not provided |
input | Inputs: ≥ 1, ≤ 20 | Not provided | Each input row is limited to 128000 tokens. |
user | Not provided | Not provided | Not provided |
TokenLab exposes this model through the OpenAI-compatible /v1/embeddings route.
Pricing
The Verified price applies to Verified, which costs less on most models. The Official price is the model maker's published price and applies to the more reliable Official route. Auto bills the route that completes the request.
Pricing
per 1M tokens- Verified price
- —
- Official price
- Input$0.0735per 1M tokensOutput$0.00per 1M tokens
| Official priceper 1M tokens | Verified priceper 1M tokens | Discount | |
|---|---|---|---|
| Input | $0.0735 | — | — |
| Output | $0.00 | — | — |
Usage & activity
Success rate is the share of requests that completed. Latency is how long a full response takes; P95 means 95% of requests finished within that time.
Usage & availability
Last 24 hours- Requests
- Success rate
- P95 latency
- Total tokens
Data is based on aggregate user requests, excluding status checks.
Open in Console
Open Qwen3.7 Text Embedding in Console with a prompt ready to edit or send.
Help me try qwen3.7-text-embedding with text-embedding at /v1/embeddings. Show the result and cost.
Use cases
Long-document retrieval
Embed lengthy reports or manuals as single items and search them without aggressive chunking.
Hybrid search
Combine dense and sparse vectors to catch both meaning and exact keywords.
Multilingual knowledge bases
Search a company wiki written in many languages using queries in any of them.
Prompt examples
Embed this 60-page policy document as one item for later retrieval.
Embed the query 'how do I rotate API keys' with an instruction describing a help-centre search task.
Embed these multilingual support articles at 1024 dimensions for clustering.
Cost calculator
FAQ
What dimensions does Qwen3.7 Text Embedding offer?
2560, 2048, 1536, 1024 (default), 768, 512, and 256. Pick lower values when index storage or search speed matters more than the last bit of accuracy.
How much text fits in one item?
Alibaba documents very long single inputs, far longer per item than text-embedding-v4 accepts, so whole documents often fit without chunking. Separately, one request can carry up to 20 items.
What is the instruct parameter?
A short instruction describing the task, for example a search query against documentation. Alibaba reports a gain of 1 to 5 percent from using it.
Should I choose Qwen3.7 or text-embedding-v4?
Qwen3.7 accepts far longer inputs and larger vectors. text-embedding-v4 has smaller dimension choices down to 64. Choose by document length and storage budget, then test recall on your own documents with each.
How much does Qwen3.7 Text Embedding cost?
On TokenLab, Qwen3.7 Text Embedding costs Input $0.0735 / Output $0.00 per 1M tokens. The pricing table above shows the full breakdown.
Which endpoint should Qwen3.7 Text Embedding use?
Use https://api.tokenlab.sh/v1/embeddings for Qwen3.7 Text Embedding. The request example below shows the matching code shape.
Which operations does Qwen3.7 Text Embedding support?
Qwen3.7 Text Embedding supports Embedding. Select an operation above to see its endpoint and request example.
Compare Qwen3.7 Text Embedding
Sources
Reviewed Oct 2, 2026
