Qwen3-Embedding 4B
Try Qwen3-Embedding 4B on us. Starter credit covers your first requests, then one key reaches this route and every other model in the catalog.
qwen/qwen3-embedding-4b
| Publisher | Alibaba Cloud Model Studioalibaba |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Context | 32,768 tokens |
| Providers | |
| Credits routes | 1 provider route |
| Modes | embeddings open weights |
| Billing | Credits |
Current route evidence
Live leaderboardRecent provider-route uptime spans not enough data across 1 route and 1 provider. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.
Providers serving this model
Sorted by lowest combined prompt and completion price. Use
"provider": {"sort": "throughput"} in the request body
(or append :nitro to the model id) to route to the
fastest provider instead.
Trust boundary: TR router attestation verifies the TrustedRouter gateway only. Provider policy separately describes the upstream model host's retention, confidential compute, and E2EE posture. Company country is separate from inference location. Weight formats are source-backed declarations, not per-request proofs.
| Provider | Input | Cached input | Output | Weight format | Provider policy | Company / inference location | Measured speed |
|---|---|---|---|---|---|---|---|
| Privatemodeprivatemode | $0.161189/1M | Not published | selected route | Unknown |
Confidential
ZDR
Retention detailsRequests and responses are encrypted between TrustedRouter's enclave and release-pinned Privatemode workloads after attestation verification. Verification failures reject the request; there is no plaintext fallback. Privatemode explicitly states that prompts and responses are not stored after a request completes and are not used for training. Transient inference state may remain in a salt-isolated, in-memory prompt cache inside confidential workers until eviction. Operational metadata is retained for up to 90 days; per-key token usage is retained permanently for billing. Cache-routing metadata is visible to the provider edge. ZDR describes prompt/output retention, not metadata. |
Operator country: DE
Location detailsHeadquarters / registered office: Not verified. Inference: EU-hosted inference, provider-declared; country and individual worker location unspecified. Privatemode declares EU hosting for its inference service. This does not establish an individual worker's country. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. |
TTFT: insufficient data
Speed: insufficient data
Last sample:
|
Speed is the median (p50) from TR's recent measured requests for this exact model and provider, refreshed from the cached leaderboard. At least two timing samples are required; workload and network conditions affect results. Performance details
Endpoint JSON: https://api.trustedrouter.com/v1/models/qwen/qwen3-embedding-4b/endpoints
Compare Qwen3-Embedding 4B
All comparisons- MiniMax: MiniMax M3 vs Qwen3-Embedding 4B15 combined provider routes
Questions
What model ID should I use for Qwen3-Embedding 4B?
Use qwen/qwen3-embedding-4b as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve Qwen3-Embedding 4B?
TrustedRouter currently lists Privatemode for Qwen3-Embedding 4B. Provider availability and routing eligibility can change as catalog and health data update.
How much does Qwen3-Embedding 4B cost through TrustedRouter?
The current lowest Credits input price is $0.161189/1M and the lowest Credits output price is selected route. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for Qwen3-Embedding 4B?
Set provider.min_privacy to zdr on the request. TrustedRouter considers only routes with a recorded zero-data-retention posture and fails closed if no eligible route remains.