Free to start

DeepSeek: DeepSeek V4.1 Flash 1017

Try DeepSeek V4.1 Flash 1017 on us. Starter credit covers your first requests, then one key reaches all 16 provider routes with automatic failover.

`deepseek/deepseek-v4.1-flash-1017`

open weights US providers EU-focused DeepSeek

All models

Publisher	DeepSeekdeepseek
AI IQ	IQ 128 #19 on AI IQ
Context	1,048,576 tokens
Providers	TinfoilTrusted Confidential ZDR Nebius Token Factory ZDR Wafer ZDR Baseten ZDR Sail Research ZDR Featherless AI ZDR Novita AI Makora Morph Pearl Research Labs Engy Cloudflare Workers AI Arcee AI Lyceum Boundless DeepInfra
Credits routes	16 provider routes
Modes	chat open weights US providers EU-focused
Billing	Credits

Current route evidence

Live leaderboard

$0.03165/1MLowest Credits input price

$0.1266/1MLowest Credits output price

714 msFastest measured p50 TTFT via deepinfra

not enough dataHighest measured throughput

Recent provider-route uptime spans 100.00% across 16 routes and 16 providers. Price comes from the current Credits catalog. Speed and uptime come from routed probes rather than vendor claims.

All route prices All providers Performance details

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
Engyengy	$0.03165/1M	$0.01/1M	$0.1266/1M	Unknown	no verified privacy claim Retention details Engy's October 21 policy distinguishes its no-content-logging gateway from independent GPU workers. End-to-end ZDR requires provider.zdr=true or a verified account/key setting; TrustedRouter has not verified that setting for this route. Requests without it may reach independently operated workers. Integrity audits may retain output token IDs on qwen3.6-35b-a3b for 30 days. These routes are not strict ZDR, confidential inference or verified E2EE. Provider policy source	Operator country: Not verified Location details Headquarters / registered office: Not verified. Inference: Inference countries undisclosed; no verified country-specific residency commitment. Qwen3.8-27B and GLM 5.3 Flash are listed as Engy-operated ZDR models, but the reviewed catalog, docs and privacy policy do not disclose their GPU countries or a complete failover-location set. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-26. API documentation Privacy and processing path Full location evidence	TTFT: 1.18 s Speed: insufficient data Last sample: 2026-10-30T21:18:37.000Z
Pearl Research Labspearl	$0.05275/1M	$0.01/1M	$0.3165/1M	Unknown	no verified privacy claim Retention details Pearl Research states that it retains operational metadata for security and does not train on customer data. No public contractual zero-data-retention terms are linked, so TrustedRouter classifies these routes as Standard and excludes them from ZDR, confidential-compute, and E2EE routing. Provider policy source	Operator country: IL Location details Headquarters / registered office: Tel Aviv-Yafo, Israel. Company location source (reviewed 2026-09-27). Inference: Multi-region provider: US Central, Taiwan and Australia declared; model-specific inference location and exhaustive failover scope unconfirmed. Pearl supplied these serving regions in its marketplace application. This is provider-wide information, not a confirmed per-model or exhaustive failover list. GLM 5.3 Flash and DeepSeek V4.1 Flash do not declare regions in the reviewed native catalog. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-26. Native model catalog (authentication required) Privacy policy (not a GPU-location declaration) Full location evidence	TTFT: 1.55 s Speed: insufficient data Last sample: 2026-10-31T09:01:16.000Z
Sail Researchsail-research	$0.09495/1M	$0.01/1M	$0.3165/1M	FP8 + FP4 experts (reference weights) Provider declaration, reviewed 2026-10-28. Per-request precision is not verified. Sail explicitly lists the reference 1017 checkpoint; its reviewed config combines FP8 weights and FP4 experts. Sail does not pin a serving revision in its public catalog. The checkpoint source is evidence of the declared reference format, not proof that a request ran those exact bytes. KV cache: unspecified. Sail exact-model reference-checkpoint declaration Reviewed reference weight configuration	ZDR Retention details Sail's public DPA and security documentation provide default ZDR for inference: Sail and its subprocessors process prompts and outputs ephemerally in memory, without persistent storage or training absent written consent. Files API uploads and stateful Sailboxes are excluded. This is policy-backed ZDR, not verified confidential compute or E2EE. Provider policy source	Operator country: Not verified Location details Headquarters / registered office: Not verified. Inference: Global, dynamically placed; TrustedRouter does not enforce Sail's US-only option. Sail documents multi-region processing by default, including outside the United States. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Data processing and residency Provider US-only option Full location evidence	TTFT: 1.29 s Speed: insufficient data Last sample: 2026-10-31T01:29:01.000Z
Waferwafer	$0.15825/1M	$0.01/1M	$0.633/1M	Unknown	ZDR Retention details Wafer's authenticated model catalog reports that this exact route supports request-scoped ZDR via Wafer-ZDR: required. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: 1.85 s Speed: insufficient data Last sample: 2026-10-31T10:06:40.000Z
DeepInfradeepinfra	$0.211/1M	$0.01/1M	$0.633/1M	FP8 (provider-declared) Provider declaration, reviewed 2026-10-28. Per-request precision is not verified. The provider's page labels this exact route FP8. It does not publish an immutable serving-weight revision or a complete mixed-precision breakdown; this is not a claim that every tensor is FP8. KV cache: unspecified. Provider's exact-model precision declaration	no verified privacy claim Retention details Tracked as no-store, not strict ZDR. DeepInfra documents memory-only handling and no training for ordinary inference, but reserves the right to log a small portion of requests for debugging or security. Google- and Anthropic-backed routes also inherit those vendors' terms. Provider policy source	Operator country: US Location details Headquarters / registered office: Palo Alto, California, United States. Company location source (reviewed 2026-09-27). Inference: US infrastructure plus announced Canadian capacity; model-specific residency unconfirmed. DeepInfra describes US infrastructure and announced its first international data center in Toronto on July 8, 2026. This is a provider footprint, not an exhaustive or model-specific placement list. DeepSeek V4.1 Flash placement has not been confirmed; do not declare this route US-only. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-27. DeepInfra infrastructure statement DeepInfra Toronto announcement Full location evidence	TTFT: 0.71 s Speed: insufficient data Last sample: 2026-10-31T10:00:10.659Z
Morphmorph	$0.1266/1M	$0.01/1M	$0.844/1M	Unknown	privacy unknown Retention details Morph's public paid tier documents up to 30 days of content retention. Zero retention is reserved for enterprise contracts. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: 4.03 s Speed: insufficient data Last sample: 2026-10-31T08:38:05.000Z
Featherless AIfeatherless	$0.237375/1M	Not published	$0.9495/1M	FP8 (provider-declared) Provider declaration, reviewed 2026-10-28. Per-request precision is not verified. The provider's page labels this exact route FP8. It does not publish an immutable serving-weight revision or a complete mixed-precision breakdown; this is not a claim that every tensor is FP8. KV cache: unspecified. Provider's exact-model precision declaration	ZDR Retention details Featherless's published privacy policy states that prompts and completions are neither collected nor stored. Account, payment and usage metadata, including token counts and sampler settings, may be retained. This is policy-backed ZDR, not verified confidential compute or E2EE. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: insufficient data Speed: insufficient data
Boundlessboundless	$0.2532/1M	$0.01/1M	$1.0128/1M	Unknown	privacy unknown Retention details Boundless's October 27 terms prohibit persistent input/output storage after real-time processing, while retaining content-free request records for up to 90 days. The terms still disclaim third-party infrastructure practices; an equivalent downstream retention commitment is not verified. Routes remain outside strict ZDR, confidential compute and E2EE. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: US, UK and/or EU infrastructure, provider-declared; no per-request residency commitment. October 27 terms, section 3.3, describe provider-wide infrastructure in the US, UK and/or EU; not an exact-model placement receipt. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Infrastructure and data terms Full location evidence	TTFT: insufficient data Speed: insufficient data
Makoramakora	$0.15825/1M	$0.01/1M	$1.266/1M	Unknown	privacy unknown Retention details Makora's Developer Pro and pay-as-you-go tiers advertise ZDR, but permit encrypted on-host SSD caches with no fixed deletion deadline and retention of flagged content for safety investigations. Starter and Developer tiers retain content for 30 days. No training on any tier. These routes remain excluded from strict ZDR. Provider policy source	Operator country: US Location details Headquarters / registered office: Not verified. Inference: United States primary processing, provider-declared; international processing is permitted and exact-model residency is unverified. Privacy policy section 7 lists AWS and TensorWave inference compute in the US; section 10 also permits international processing. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Inference subprocessors and processing region Full location evidence	TTFT: 0.86 s Speed: insufficient data Last sample: 2026-10-31T07:42:45.000Z
Arcee AIarcee	$0.3165/1M	$0.01/1M	$1.266/1M	Unknown	privacy unknown Retention details Arcee's July 24 privacy policy permits collection of inputs and outputs to provide and improve its services. No route-specific ZDR exception is verified for TrustedRouter's account. These routes remain Standard, not confidential compute or E2EE. Provider policy source	Operator country: Not verified Location details Headquarters / 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. Full location evidence	TTFT: 2.52 s Speed: insufficient data Last sample: 2026-10-31T10:34:45.000Z
Basetenbaseten	$0.3165/1M	$0.01/1M	$1.266/1M	Unknown	ZDR Retention details Baseten states that it does not store synchronous Model API inputs or outputs by default. TrustedRouter uses the synchronous Model API path; Baseten documents separate temporary input storage for async inference. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: insufficient data Speed: insufficient data
Cloudflare Workers AIcloudflare-workers-ai	$0.3165/1M	$0.01/1M	$1.266/1M	Unknown	privacy unknown Retention details Workers AI documents no input/output retention after ordinary stateless inference and no model training. Stateful features, customer-enabled logging/caching, and safety, security or legal exceptions may retain content. No exception-free commitment is verified for this account; these routes remain outside strict ZDR. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: insufficient data Speed: insufficient data
Nebius Token Factorynebius	$0.3165/1M	Not published	$1.266/1M	Unknown	ZDR Retention details Marked ZDR via TrustedRouter's arrangement — Nebius RETAINS inputs/outputs by default (for speculative decoding); zero retention is an opt-in control, which the deployed Nebius account has enabled. Nebius does not train on customer data. Provider policy source	Operator country: NL Location details Headquarters / registered office: Amsterdam, Netherlands. Company location source (reviewed 2026-10-28). Inference: Global, dynamically placed public inference; no fixed-country commitment. Token Factory public endpoints are Global; Finland storage of retained content does not identify the inference location. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. Processing and dedicated endpoint residency Full location evidence	TTFT: 1.01 s Speed: insufficient data Last sample: 2026-10-31T06:32:39.000Z
Novita AInovita	$0.3165/1M	$0.01/1M	$1.266/1M	FP8 (provider-declared) Provider declaration, reviewed 2026-10-28. Per-request precision is not verified. The provider's page labels this exact route FP8. It does not publish an immutable serving-weight revision or a complete mixed-precision breakdown; this is not a claim that every tensor is FP8. KV cache: unspecified. Provider's exact-model precision declaration	privacy unknown Retention details No provider-ZDR claim is tracked here. Novita's privacy policy says personal information is not used for model training; customer-content processing is governed by customer agreements. Provider policy source	Operator country: US Location details Headquarters / registered office: San Francisco, California, United States. Company location source (reviewed 2026-09-27). Inference: Shared inference API; processing countries unconfirmed, no fixed-region commitment. No exhaustive inference-country list verified for the shared model API. Novita publishes worldwide GPU rental regions, but that separate product does not establish shared serverless model placement. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-10-28. GPU rental regions (different product) Native model catalog Full location evidence	TTFT: insufficient data Speed: insufficient data
Lyceumlyceum	$0.5275/1M	$0.131875/1M	$1.5825/1M	Unknown	privacy unknown Retention details Lyceum's terms state that inference inputs and outputs are used only to generate results, are not stored beyond technical necessity, and are not used for training or analysis. No account-specific ZDR or verified confidential-compute guarantee is tracked; these routes remain Standard. German company jurisdiction is not a guarantee that every model executes in the EU. Provider policy source	Operator country: DE Location details Headquarters / registered office: Berlin, Germany; Zurich, Switzerland (registered offices). Company location source (reviewed 2026-10-28). Inference: Inference location not verified; no country-specific residency commitment. Lyceum documents model-specific serving locations; its German headquarters is not a fleet-wide EU residency guarantee. Region pinning through TR: Not supported by the current TrustedRouter integration. Reviewed 2026-09-30. Model-specific hosting and pricing Full location evidence	TTFT: 1.20 s Speed: insufficient data Last sample: 2026-10-31T05:19:02.000Z
Tinfoiltinfoil	$0.68575/1M	$0.13715/1M	$1.52975/1M	FP8 + FP4 experts Published serving configuration, reviewed 2026-10-28. Per-request precision is not verified. The published configuration pins the 1017 checkpoint and fp8_ds_mla KV cache. The checkpoint uses FP8 block weights with FP4 experts, not uniform FP8. Source review is not proof of a particular request's deployed image or weight revision. KV cache: fp8_ds_mla. Published serving configuration Pinned weight configuration	Confidential ZDR Retention details Tracked as a confidential inference provider with attested provider compute and no prompt/output logging claims. Provider policy source	Operator country: US Location details Headquarters / 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. Full location evidence	TTFT: 1.27 s Speed: insufficient data Last sample: 2026-10-31T08:49:43.000Z

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

Compare DeepSeek: DeepSeek V4.1 Flash 1017

All comparisons

DeepSeek: DeepSeek V4.1 Flash 1017 vs Z.ai: GLM 5.349 combined provider routes
DeepSeek: DeepSeek V4.1 Flash 1017 vs Z.ai: GLM 5.248 combined provider routes
DeepSeek: DeepSeek V4.1 Flash 1017 vs Z.ai: GLM 5.3 Flash48 combined provider routes
DeepSeek: DeepSeek V4.1 Flash 1017 vs MoonshotAI: Kimi K344 combined provider routes
DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4.1 Flash 101742 combined provider routes
DeepSeek: DeepSeek V4.1 Flash 1017 vs OpenAI: gpt-oss-120b40 combined provider routes

Questions

What model ID should I use for DeepSeek: DeepSeek V4.1 Flash 1017?

Use deepseek/deepseek-v4.1-flash-1017 as the model field with the TrustedRouter OpenAI-compatible API. Credits routing and provider fallback happen behind that model ID.

Which providers serve DeepSeek: DeepSeek V4.1 Flash 1017?

TrustedRouter currently lists Tinfoil, Nebius Token Factory, Wafer, Baseten, Sail Research, Featherless AI, Novita AI, Makora, Morph, Pearl Research Labs, Engy, Cloudflare Workers AI, Arcee AI, Lyceum, Boundless, and DeepInfra for DeepSeek: DeepSeek V4.1 Flash 1017. Provider availability and routing eligibility can change as catalog and health data update.

How much does DeepSeek: DeepSeek V4.1 Flash 1017 cost through TrustedRouter?

The current lowest Credits input price is $0.03165/1M and the lowest Credits output price is $0.1266/1M. Prices are per one million tokens and come from the current route catalog.

How do I require zero data retention for DeepSeek: DeepSeek V4.1 Flash 1017?

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.