Free to start

Maple

Try Maple on us. Starter credit covers your first requests, then one key reaches the Maple model, with its privacy posture shown on the route.

Maplemaple

Confidential ZDR · TR-funded

All providers

Encrypted inference using Maple Transport V2 inside TrustedRouter's measured gateway. The dedicated uncensored DeepSeek checkpoint is separate from stock DeepSeek.

These privacy labels describe Maple, 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	Maple
API operator country	Not verified Legal home of the API operator, not an inference-location guarantee.
Headquarters	Not verified
Routing status	Active
Provider website	https://maple.ai/
Models	1 public model
Credits routes	1
Zero data retention	yes Reviewed TR-funded routes only; check each model
Verified confidential inference	Verified
Policy note	The managed uncensored DeepSeek route uses Maple Transport V2 from inside TrustedRouter's measured enclave. Each request verifies a pinned Nitro image, which enforces the reviewed dedicated GPU worker and immutable model weights. Unexpected measurements fail closed; there is no plaintext fallback. API prompt/response zero retention was confirmed for TrustedRouter's account on October 28, 2026. Account and billing metadata are separate from prompt/response content. These guarantees do not cover Maple saved chats, other models or BYOK. Policy source

Documentation and policy sources

Maple Confidential API

Use your TrustedRouter API key and Credits. This request selects only Maple's dedicated uncensored DeepSeek route, requires Confidential, and disables alternate-provider fallback. If the qualified route is unavailable or verification fails, the request fails closed.

curl --fail-with-body --no-buffer https://api.trustedrouter.com/v1/chat/completions \
  -H "Authorization: Bearer ${TRUSTEDROUTER_API_KEY:?Set your TrustedRouter API key}" \
  -H 'Content-Type: application/json' \
  -H 'X-OpenRouter-Metadata: enabled' \
  -d '{
    "model": "dealignai/deepseek-v4.1-flash-1017-uncensored",
    "messages": [{"role": "user", "content": "Explain a binary search in three sentences."}],
    "provider": {
      "only": ["maple"],
      "allow_fallbacks": false,
      "min_privacy": "confidential"
    },
    "max_tokens": 512,
    "stream": true,
    "stream_options": {"include_usage": true}
  }'

Supported on this route: text Chat Completions, streaming and non-streaming, and cached-input billing. Images, tools, structured-output schemas, and BYOK are not currently advertised as supported. For a JSON response, set stream to false and omit stream_options.

The streaming metadata event identifies the selected provider and gateway region; the usage events report token counts and cost. Non-streaming responses include usage.provider_usage. Gateway region is not the GPU location. Response metadata · Verify the TrustedRouter gateway

Confidential applies to this managed API route, not stock DeepSeek, Maple saved chats, or BYOK. Content zero retention does not remove account or billing records.

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

499 samples

Continuously sampled across Maple'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	1538 ms
Effective throughput	—
Uptime	96.39%

Model	p50 TTFT	Effective throughput	Uptime	Config excluded	Availability samples
dealignai/deepseek-v4.1-flash-1017-uncensored	1538 ms	—	96.39%	—	499

Maple performance history · Full provider & model leaderboard.

Provider models

Models served by Maple.

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

Model	AI IQ	Context	Input	Cached input	Output
`dealignai/deepseek-v4.1-flash-1017-uncensored` DeepSeek V4.1 Flash Uncensored	—	1,048,576	$0.68575/1M	$0.13715/1M	$1.52975/1M

Questions

Does Maple have zero data retention?

Reviewed managed Maple routes can qualify for zero data retention. Check the exact model's endpoint policy: safety-retention, durable-cache and unreviewed routes are excluded. BYOK does not inherit this classification. Use provider.min_privacy=zdr to enforce eligibility.

Is Maple end-to-end encrypted?

TrustedRouter records Maple as supporting provider-side confidential compute and end-to-end encrypted inference. The route-specific model page shows whether that protection applies to a particular endpoint.

Which Maple models are available through TrustedRouter?

This page currently lists 1 public Maple model, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.