DeepSeek · Model identity
DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
1pricing route
What published route metadata supports
CachingHugging FaceReasoningStructured outputTool useVision
Input modalities
ImageText
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Only source-backed fields are filled
Release dateNot independently verified
Knowledge cutoffNot independently verified
Open weightsNot independently verified
OpenRouter catalog date2026-09-10
LLMPrice does not infer a release date, knowledge cutoff, or open-weight status from a model name, Hugging Face link, or pricing route.
Could this workload cost less?Compare DeepSeek V4.1 Flash with cheaper models using the same workload.
Find cheaper alternatives →| Endpoint / route | Model ID | Input | Cached | Output | Context | Source |
|---|---|---|---|---|---|---|
| OpenRouterStandard | deepseek/deepseek-v4.1-flash | $0.3 | $0.006 | $1.2 | 1.05M | OpenRouter API ↗ |
Hugging Face references
Presence of a Hugging Face ID is not treated as proof that model weights are open.
1 verified price change since Aug 26, 2026
1 route availability change recorded. No earlier prices are inferred.
Input / 1M$0.3Sep 11, 2026 → Sep 14, 2026
Output / 1M$1.2Sep 11, 2026 → Sep 14, 2026
- Sep 14, 2026OpenRouter · Standard
Input $0.15 → $0.3 · Cached input $0.003 → $0.006 · Output $0.6 → $1.2
- Sep 11, 2026OpenRouter · Standard
New pricing route added