DeepSeek: DeepSeek V4.1 Flash
Try DeepSeek V4.1 Flash on us. Starter credit covers your first requests, then one key reaches all 24 provider routes with automatic failover.
deepseek/deepseek-v4.1-flash
| Publisher | DeepSeekdeepseek |
|---|---|
| AI IQ | IQ 126 #22 on AI IQ |
| Context | 1,048,576 tokens |
| Providers |
TinfoilConfidential
ZDR
Nebius Token Factory
ZDR
Together
ZDR
Wafer
ZDR
Baseten
ZDR
Telnyx
ZDR
Engy
ZDR
Zro (MoonMath)
ZDR
CoralBricks
ZDR
Novita AI
SiliconFlow
Crusoe
Makora
Pearl Research Labs
Sail Research
Arcee AI
IO Intelligence
Lyceum
Boundless
Tencent Cloud TokenHub
Weights & Biases
Featherless AI
DeepInfra
Atlas Cloud
|
| Credits routes | 24 provider routes |
| Modes | chat decide open weights US providers EU-focused |
| Billing | Credits |
Current route evidence
Live leaderboardRecent provider-route uptime spans not enough data across 24 routes and 24 providers. 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.
| Provider | Input | Cached input | Output | Weight format | TR router attested | Provider policy |
|---|---|---|---|---|---|---|
| Engyengy | $0.0422/1M | $0.01/1M | $0.0844/1M | Unknown | yes | ZDR provider E2EE not verified |
| Pearl Research Labspearl | $0.05275/1M | $0.01/1M | $0.3165/1M | Unknown | yes | no verified privacy claim |
| Sail Researchsail-research | $0.09495/1M | $0.01/1M | $0.3165/1M | Unknown | yes | privacy unknown |
| SiliconFlowsiliconflow | $0.15825/1M | $0.01/1M | $0.633/1M | Unknown | yes | privacy unknown |
| Tencent Cloud TokenHubtencent | $0.15825/1M | $0.01/1M | $0.633/1M | Unknown | yes | privacy unknown |
| DeepInfradeepinfra | $0.211/1M | $0.01/1M | $0.633/1M | Unknown | yes | no verified privacy claim |
| Weights & Biaseswandb | $0.211/1M | $0.03165/1M | $0.68575/1M | Unknown | yes | no verified privacy claim |
| Arcee AIarcee | $0.2321/1M | $0.01/1M | $0.6963/1M | Unknown | yes | privacy unknown |
| Boundlessboundless | $0.211/1M | $0.01055/1M | $1.055/1M | Unknown | yes | privacy unknown |
| CoralBrickscoralbricks | $0.01055/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR provider E2EE not verified |
| Makoramakora | $0.2743/1M | $0.01/1M | $1.23435/1M | Unknown | yes | privacy unknown |
| Crusoecrusoe | $0.30595/1M | $0.01/1M | $1.266/1M | Unknown | yes | privacy unknown |
| Atlas Cloudatlas-cloud | $0.3165/1M | $0.03165/1M | $1.266/1M | Unknown | yes | privacy unknown |
| Basetenbaseten | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR |
| Featherless AIfeatherless | $0.3165/1M | Not published | $1.266/1M | Unknown | yes | privacy unknown |
| Nebius Token Factorynebius | $0.3165/1M | Not published | $1.266/1M | Unknown | yes | ZDR |
| Novita AInovita | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | privacy unknown |
| Telnyxtelnyx | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR |
| Togethertogether | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR |
| Waferwafer | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR |
| Zro (MoonMath)zro | $0.3165/1M | $0.01/1M | $1.266/1M | Unknown | yes | ZDR |
| IO Intelligenceio-net | $0.3798/1M | $0.1899/1M | $1.5192/1M | Unknown | yes | privacy unknown |
| Lyceumlyceum | $0.5275/1M | $0.13715/1M | $1.5825/1M | Unknown | yes | privacy unknown |
| Tinfoiltinfoil | $0.68575/1M | $0.13715/1M | $1.52975/1M |
FP8 + FP4 expertsPublished serving configuration, reviewed 2026-09-27. Per-request precision is not verified. Pinned quantization config declares FP8 with FP4 expert weights. BF16 default dtype does not describe the quantized weights. KV cache: unspecified. |
yes | Confidential ZDR |
Endpoint JSON: https://api-azure.trustedrouter.com/v1/models/deepseek/deepseek-v4.1-flash/endpoints
Compare DeepSeek: DeepSeek V4.1 Flash
All comparisons- DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5.357 combined provider routes
- DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5.256 combined provider routes
- DeepSeek: DeepSeek V4.1 Flash vs Z.ai: GLM 5.3 Flash56 combined provider routes
- DeepSeek: DeepSeek V4.1 Flash vs MoonshotAI: Kimi K352 combined provider routes
- DeepSeek: DeepSeek V4 Flash 0731 vs DeepSeek: DeepSeek V4.1 Flash50 combined provider routes
- DeepSeek: DeepSeek V4.1 Flash vs OpenAI: gpt-oss-120b47 combined provider routes
Questions
What model ID should I use for DeepSeek: DeepSeek V4.1 Flash?
Use deepseek/deepseek-v4.1-flash 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?
TrustedRouter currently lists Tinfoil, Nebius Token Factory, Together, Wafer, Baseten, Telnyx, Engy, Zro (MoonMath), CoralBricks, Novita AI, SiliconFlow, Crusoe, Makora, Pearl Research Labs, Sail Research, Arcee AI, IO Intelligence, Lyceum, Boundless, Tencent Cloud TokenHub, Weights & Biases, Featherless AI, DeepInfra, and Atlas Cloud for DeepSeek: DeepSeek V4.1 Flash. Provider availability and routing eligibility can change as catalog and health data update.
How much does DeepSeek: DeepSeek V4.1 Flash cost through TrustedRouter?
The current lowest Credits input price is $0.01055/1M and the lowest Credits output price is $0.0844/1M. 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?
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.