Free to start

DeepSeek

Try DeepSeek on us. Starter credit covers your first requests, then one key reaches all 4 DeepSeek models, with the privacy posture shown on every route.

DeepSeekdeepseek

No provider claim

All providers

These privacy labels describe DeepSeek, the upstream model provider. Confidential requires all three: verified provider compute, end-to-end encryption and explicit zero data retention. Account and billing metadata are outside the content-retention claim.

Provider	DeepSeek
API operator country	CN Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://www.deepseek.com/
Models	4 public models
Credits routes	4
Zero data retention	no
Verified confidential inference	Not verified
Policy note	Not ZDR. DeepSeek's published privacy policy says prompts/inputs may be collected and personal data may be used to train or improve machine learning models and algorithms. Policy source

Inference locations

Provider API declarations are also available on each model's endpoint API. Direct chat and Responses replies separate advertised availability from serving location in usage.inference_location; the actual serving region remains unknown when not reported.

usage.provider_usage.gateway_region identifies the TrustedRouter gateway, not the provider's inference location. A value such as europe-west4 does not mean the model ran in Europe. usage.inference_location.serving_region remains null when the provider has not reported it. Older gateways may return the gateway-only field as provider_usage.region.

Where the upstream GPUs execute the model, not the provider's headquarters, API ingress, or data storage. ZDR and confidential inference do not by themselves restrict geography.

Declared countries or regions: Not verified
No inference-location declaration has been verified for this provider.
Can locations change?: Not verified. Do not assume that the serving location is fixed.
Provider region pinning: Not verified.
Pinning through TrustedRouter: No verified provider-specific location pin documented here.
Infrastructure declaration: Inference location not verified; no country-specific residency commitment.
Evidence: Not yet reviewed.

Provider selection alone is not a region pin. TrustedRouter's US provider filter selects company jurisdiction, not GPU location. A regional gateway hostname does not pin a downstream GPU. For a binding residency requirement, confirm the model, region, failover scope and enforced controls before sending sensitive data.

Measured performance

28 samples

Continuously sampled across DeepSeek's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.

p50 TTFT	1497 ms
Effective throughput	115 tok/s n=2
Uptime	100.00%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
deepseek/deepseek-v4-pro	1638 ms	—	100.00%	—	13
deepseek/deepseek-v4-flash	1479 ms	115 tok/s n=2	100.00%	—	9
deepseek/deepseek-flash	1497 ms	—	100.00%	—	6

DeepSeek performance history · Full provider & model leaderboard.

Provider models

Models served by DeepSeek.

Each row links to pricing, provider, benchmark, and API pages for the model.

Model	AI IQ	Context	Input	Cached input	Output
`deepseek/deepseek-flash` DeepSeek V4.1 Flash (rolling)	—	1,048,576	$0.15825/1M	$0.01/1M	$0.633/1M
`deepseek/deepseek-v4-flash` DeepSeek: DeepSeek V4 Flash 0423 benchmarks	IQ 121#39	1,048,576	$0.15825/1M	$0.01/1M	$0.633/1M
`deepseek/deepseek-v4-pro` DeepSeek: DeepSeek V4 Pro 0423 benchmarks	IQ 123#31	1,048,576	$0.15825/1M	$0.01/1M	$0.633/1M
`deepseek/fetch` DeepSeek Fetch	—	0	$0.000792 / successful request	Not applicable	Included

Questions

Does DeepSeek have zero data retention?

TrustedRouter does not currently mark DeepSeek as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.

Is DeepSeek end-to-end encrypted?

TrustedRouter does not currently mark DeepSeek as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.

Which DeepSeek models are available through TrustedRouter?

This page currently lists 4 public DeepSeek models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.