DeepSeek V4.1 Flash Uncensored
Try DeepSeek V4.1 Flash Uncensored on us. Starter credit covers your first requests, then one key reaches this route and every other model in the catalog.
dealignai/deepseek-v4.1-flash-1017-uncensored
| Publisher | dealignai |
|---|---|
| AI IQ | No AI IQ profile matched yet. |
| Context | 1,048,576 tokens |
| Providers | |
| Credits routes | 1 provider route |
| Modes | chat |
| Billing | Credits |
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.
Current route evidence
Live leaderboardRecent provider-route uptime spans 96.39% 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 |
|---|---|---|---|---|---|---|---|
| Maplemaple | $0.68575/1M | $0.13715/1M | $1.52975/1M |
FP8 + FP4 expertsPublished serving configuration, reviewed 2026-10-29. Per-request precision is not verified. The reviewed dedicated worker pins the uncensored checkpoint and fp8_ds_mla KV cache. Its weight configuration declares FP8 block weights with FP4 experts, not uniform FP8. This source metadata is not a per-request precision receipt and does not apply to Maple's stock DeepSeek route. KV cache: fp8_ds_mla. |
Confidential
ZDR
Retention detailsThe 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. |
Operator country: Not verified
Location detailsHeadquarters / registered office: Not verified. Inference: Inference location not verified; no country-specific residency commitment. No inference-location declaration has been verified for this provider. Region pinning through TR: No verified provider-specific location pin documented here. |
TTFT: 1.54 s
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/dealignai/deepseek-v4.1-flash-1017-uncensored/endpoints
Compare DeepSeek V4.1 Flash Uncensored
All comparisons- DeepSeek V4.1 Flash Uncensored vs Qwen: Qwen3.8 27B23 combined provider routes
Questions
What model ID should I use for DeepSeek V4.1 Flash Uncensored?
Use dealignai/deepseek-v4.1-flash-1017-uncensored as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.
Which providers serve DeepSeek V4.1 Flash Uncensored?
TrustedRouter currently lists Maple for DeepSeek V4.1 Flash Uncensored. Provider availability and routing eligibility can change as catalog and health data update.
How much does DeepSeek V4.1 Flash Uncensored cost through TrustedRouter?
The current lowest Credits input price is $0.68575/1M and the lowest Credits output price is $1.52975/1M. Prices are per one million tokens and come from the current route catalog.
How do I require zero data retention for DeepSeek V4.1 Flash Uncensored?
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.