All models

Qwen3 Embedding 4B

Qwenqwen/qwen3-embedding-4b

Qwen's multilingual text embedding model with 28,672-token inputs, batches of up to 32 items, and configurable vectors from 32 to 2560 dimensions.

1 provider online
Modality
Embeddings
Input
$0.00125
per M tokens
Listed
Sep 17, 2026
Uptime
98.2%
last 3 days, measured

Pricing

Charged per use against a signed receipt. Current price version v20; versions are immutable, so the chart below is the platform's actual pricing record.

Input
$0.00125
per M tokens
$0.00$0.034$0.069Sep 17Today

Trust & routing

Current trust properties and dispatch capacity advertised by the OpenMayhem network.

Registered tiers
T1
Live tiers
T1
Quantizations
bf16
Live routes
1
Live providers
1
Prompt processing
Provider-visible
Context capacity
28.7K
Concurrent requests
64

Routing providers

0116fb2c…bd8b

Activity

What actually ran on the platform, per day over the last 30 days. Settled usage from receipts; nothing synthetic.

50100Aug 19Sep 17
Show as table
Dayinput tokensoutput tokensRequests
Sep 176808
Sep 16006
Sep 15000
Sep 14000
Sep 13000
Sep 12000
Sep 11000
Sep 10000
Sep 9000
Sep 8000
Sep 7000
Sep 6000
Sep 5000
Sep 4000
Sep 3000
Sep 2000
Sep 1000
Aug 31000
Aug 30000
Aug 29000
Aug 28000
Aug 27000
Aug 26000
Aug 25000
Aug 24000
Aug 23000
Aug 22000
Aug 21000
Aug 20000
Aug 19000

Performance

Measured from real, settled requests over the last 30 days. No synthetic benchmarks.

Job duration
3.3 s
median · p95 3.5 s · 6 requests
Success rate
50%
12 finished requests, 30 days

This week: 68 tokens across 6 requests.

Availability

Provider availability polled every minute by the platform itself, replayed hour by hour.

98.2%online over the last 3 days

Tracking since Sep 17, 12 AM

3 days ago online down no dataNow

Providers

Who actually served this model, attributed from signed receipts over the last 30 days.

ProviderRequestsShareTokensAvg latencyLast seen
0116fb2c…bd8b6100%68 (100%)3.3 sSep 17

Supported parameters

From the network's signed model contract; anything else is rejected before a provider runs.

dimensionsencoding_formatinputmodel

Use it

OpenAI-compatible: point an existing SDK at api.openmayhem.ai and use this model ID.

POST /v1/embeddingsEMBEDDINGS · openai_embeddings +

Working request

curl https://api.openmayhem.ai/v1/embeddings \
  -H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
  "model": "qwen/qwen3-embedding-4b",
  "input": [
    "A distributed inference network for open models.",
    "Providers earn for serving verified AI requests."
  ],
  "dimensions": 1536
}'

Parameters

ParameterRequiredTypeDefaultAllowed valuesLimits and shape
inputRequiredstring | arraymin length 1; min items 1; max items 32 JSON array
modelRequiredstringQwen/Qwen3-Embedding-4B
dimensionsOptionalintegermin 32; max 2560
encoding_formatOptionalstringfloatfloat, base64

Agent drop-ins

This is a media endpoint, so it cannot replace the text model that drives a coding agent. Call the request above from the agent’s HTTP or tool layer.

FAQ

What does Qwen3 Embedding 4B cost on OpenMayhem?

Qwen3 Embedding 4B currently costs . There is no subscription: you buy credit and every request settles against a signed receipt for exactly what it used. Prices are versioned, and the full price history is published on this page.

Is Qwen3 Embedding 4B available right now?

Yes. 1 provider serving Qwen3 Embedding 4B right now, and it was online 98.2% of the last 3 days as measured by our own polling.

How do I use Qwen3 Embedding 4B?

Send an OpenAI-compatible request to https://api.openmayhem.ai/v1/embeddings with "model": "qwen/qwen3-embedding-4b" and your API key. Existing OpenAI SDKs work by changing the base URL. Create an account to get a key and starting credit.

Who serves Qwen3 Embedding 4B?

Independent providers on the OpenMayhem network run the model on their own hardware. Over the last 30 days, 1 provider served it; the providers table on this page is attributed from signed receipts, not self-reporting.

Are my prompts stored?

OpenMayhem does not persist prompt or completion text. Requests are proxied to the serving provider and only billing metadata is retained: usage counts, the price applied, and the provider's signed receipt. Generated media files are stored temporarily so you can download them, then expire. The provider that serves a request necessarily processes its content.

More like this