Models · Embeddings
Qwen3-Embedding-8B
by Qwen
Embedding model for semantic search, retrieval, clustering, and ranking pipelines.
Our verdict
We have not reviewed Qwen3-Embedding-8B yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Qwen3-Embedding-8B
Embedding model for semantic search, retrieval, clustering, and ranking pipelines.
Best for
Multilingual text retrieval
Notes
Qwen3-Embedding-8B is listed in the EDNA Models directory, sourced from models.dev.
Pros
- Embedding a multilingual collection with task instructions
- text input; embeddings output on the listed OpenRouter route
Cons
- Treating an embedding model as a chat generator
- Assuming multilingual benchmark coverage proves domain recall
- Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Key facts
What we have checked
- Price on deepinfra
- $0.010 per million input tokens
- Price on deepinfra
- $0 per million output tokens
- Price on nebius
- $0.010 per million input tokens
- Price on nebius
- $0 per million output tokens
- Price on siliconflow
- $0.040 per million input tokens
- Price on siliconflow
- $0 per million output tokens
- Latest version
- qwen/qwen3-embedding-8b
- Tokens served on OpenRouter in a day
- 28B (for 10 Nov 2026)
- Tool calls on OpenRouter in a day
- 0 (for 10 Nov 2026)
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
API access
How to call it
Call via other with model id `Qwen/Qwen3-Embedding-8B`.
- other ·
Qwen/Qwen3-Embedding-8B
OpenRouter id: qwen/qwen3-embedding-8b
Price
What Qwen3-Embedding-8B costs, over time
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| deepinfraInput | $0.010 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraOutput | $0 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusInput | $0.010 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| nebiusOutput | $0 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| siliconflowInput | $0.040 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| siliconflowOutput | $0 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Usage
How much Qwen3-Embedding-8B is used
18.7B to 28B
Sources
Where this comes from
- OpenRouter models APIRegistry
- OpenRouter models APIThird party
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
No changes recorded yet. Releases, price changes and deprecations appear here, with their dates, once we track them for this record.
USAGE / OPENROUTER
How much Qwen3-Embedding-8B is used
Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.
- Tokens, last 7 days
- 260B ▲17.7%
- Requests, last 7 days
- 78.3M
- Tool calls, last 7 days
- —
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Qwen3-Embedding-8B.
Specifications reviewed; no EDNA task evaluation has been run. Sources checked 2026-11-07. Hosting routes and app features can differ.
qwen/qwen3-embedding-8b- Tool calling
- Not established
- Structured output
- Not established
- Reasoning controls
- Not established
- Availability
- available
- Price basis
- token
- Licence verification
- Apache 2.0, open weights
- Context length
- 41K tokens
- Knowledge cutoff
- Not established
- Developer release date
- Not established
- First seen in the catalogue
- 28 Oct 2025
- Listed retirement date
- Not established
Base text-token rates exclude other modalities, tools, caching, retries and any hosting-specific charges. Check actual usage before comparing cost per successful task.
Consider it for
- Embedding a multilingual collection with task instructions
- Testing query/document representations for semantic search
Watch for
- Treating an embedding model as a chat generator
- Assuming multilingual benchmark coverage proves domain recall
PRACTICAL EXERCISE / NOT RUN BY ENTERPRISE DNA
Try the model on a small, checkable task.
Encode an English query about annual leave and three documents: a Spanish leave policy, an English cafeteria menu and an English leave policy. Use the model-card retrieval instruction and rank results.
Check the result: Verify finite equal-dimension vectors and whether both leave policies rank above the menu.
Inspect the sources and their scope
Developer documentation for model family or task. OpenRouter route-specific properties remain catalogue claims; EDNA has not executed a task evaluation.
Checked 2026-10-19qwen/qwen3-embedding-8b: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-11-07Source for first seen, context length, input, output.
Checked 2026-11-07Licence declared in the Qwen/Qwen3-Embedding-8B model repository on Hugging Face, which holds the weights files. Read the licence terms before use.
Checked 2026-11-07FROM SPECIFICATIONS TO YOUR WORK
Is this the right model for your job?
Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.
What would it cost?
Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.
Enter a whole number of runs from 1 to 100,000,000.
Working out the cost...
Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗
Check the source
Price date: 20 Oct 2026, from the models.dev listing. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.
Model source & availability ↗Understand the evidence
Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.