tokenstat
tokenstat
DeepSeek

DeepSeek: V4.1 Flash

deepseek/deepseek-v4.1-flash · rates as of · Benchmarks · AI plans · Calculator

DeepSeek V4.1 Flash model for reasoning and agentic coding

Cheapest input
$0.04
$/MTok · models.dev
Cheapest output
$0.08
$/MTok
Context
1.1M
tokens
Sources
4
76 listings

Price changes

Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.

Input $/MTok over sampled dates
Output $/MTok
  • ↓ lowerOutput $2.40 → $0.08
  • ↑ higherInput $0.003 → $0.04
  • ↑ higherOutput $0.09 → $2.40
  • ↑ higherInput $0.0015 → $0.003
  • ↓ lowerOutput $2.40 → $0.09
  • ↓ lowerInput $0.003 → $0.0015
  • ↑ higherOutput $0.08 → $2.40
  • ↓ lowerInput $0.04 → $0.003

Sources

Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number. Free/$0 listings are hidden by default (6 omitted). Show free/$0 listings.

SourceProviderInputOutputCache readContext
tokenstatdeepseek/deepseek-v4.1-flashDeepSeek$0.3$1.20$0.0061M
models.devcheapestdeepseek-v4.1-flashEngy$0.04$0.08$0.008328K
LiteLLMopenrouter/deepseek/deepseek-v4.1-flashN/A$0.044$0.3$0.015N/A
OpenRouterdeepseek/deepseek-v4.1-flash:batchOpenRouter$0.112$0.336$0.00341.0M
LiteLLMdeepseek/deepseek-v4.1-flash:batchN/A$0.112$0.336$0.0034N/A
models.devdeepseek/deepseek-v4.1-flashNanoGPT$0.13$0.52$0.0061M
models.devdeepseek/deepseek-v4.1-flash:thinkingNanoGPT$0.13$0.52$0.0061M
models.devdeepseek-v4.1-flashDevPass (LLM Gateway)$0.135$0.54$0.00271.1M
models.devluminal/deepseek-v4.1-flashLLM Gateway$0.135$0.54$0.00271M
models.devDeepSeek-V4.1-FlashAMD$0.14$0.28$0.00281.0M
models.devflexai/DeepSeek-V4.1-FlashEden AI$0.14$0.42$0.0211.0M
models.devconsensusprotocol/deepseek-v4.1-flashLLM Gateway$0.15$0.55$0.0051.0M
models.devqwen/deepseek-v4.1-flashEden AI$0.15$0.6$0.0151M
models.devdeepseek-flash302.AI$0.15$0.6$0.0031M
models.devdeepseek-flashDeepSeek$0.15$0.6$0.0031M
models.devdeepseek/deepseek-flashTempr Gateway$0.15$0.6$0.0031M
models.devdeepseek-v4.1-flashNeuralwatt$0.15$0.6$0.0151.0M
models.devdeepseek-v4.1-flashOllama Cloud$0.15$0.6$0.0031.0M
models.devdeepseek-v4.1-flashOpenCode Go$0.15$0.6$0.0031M
models.devdeepseek-v4.1-flashVultr$0.15$0.6$01.0M
models.devcline-pass/deepseek-v4.1-flashClinePass$0.15$0.6$0.0031M
models.devscx-ai-gp/deepseek-v4.1-flashLLM Gateway$0.15$0.6$0.011M
models.devdeepseek/deepseek-v4.1-flashMerge Gateway$0.15$0.6$0.0031M
models.devdeepseek/deepseek-v4.1-flashZenMux$0.15$0.6$0.0031M
models.devumans-deepseek-v4.1-flashUmans AI$0.15$0.6$0.0281.0M
LiteLLMdeepseek-ai/DeepSeek-V4.1-FlashN/A$0.15$0.6$0.006N/A
LiteLLMDeepSeek-V4.1-FlashN/A$0.15$0.6$0.006N/A
LiteLLMsail/deepseek-ai/DeepSeek-V4.1-FlashN/A$0.15$0.6$0.006N/A
models.devdeepseek-v4.1-flashAIHubMix$0.155$0.62$0.00311M
models.devdeepseek-v4.1-flashAbove.Dev$0.165$0.66$0.00331M
LiteLLMprism/deepseek-v4.1-flashN/A$0.17$0.63$0.07N/A
models.devdeepseek-ai/DeepSeek-V4.1-FlashDeepInfra$0.2$0.6$0.0061.0M
models.devdeepinfra/deepseek-ai/DeepSeek-V4.1-FlashEden AI$0.2$0.6$0.0061.0M
models.devdeepinfra/deepseek-v4.1-flashLLM Gateway$0.2$0.6$0.0061.0M
models.devdeepseek-ai/DeepSeek-V4.1-FlashCoreWeave$0.2$0.65$0.031.0M
models.devdeepseek-v4.1-flashCortecs$0.201$0.6$0.0041.0M
models.devdeepseek/deepseek-v4.1-flashOfox$0.21$0.84$0.00421M
models.devfireworks/deepseek-v4.1-flashLLM Gateway$0.22$0.66$0.0071.0M
models.devgreenference/deepseek-v4.1-flashEden AI$0.22$0.88$0.0071.0M
models.devdeepseek-v4.1-flashMelious$0.2318$1.16$0.01161M
models.devdeepseek-v4.1-flashVancine$0.24$0.96$0.00481M
models.devsciforium/deepseek-v4.1-flashLLM Gateway$0.246$0.944$0.0121.0M
models.devdeepseek-v4.1-flashGreenPT$0.2556$1.28$0.01281M
models.devdeepseek-v4.1-flashAlibaba / Qwen$0.2975$1.19$0.01491M
models.devdeepseek-ai/deepseek-v4.1-flashAi&$0.3$0.6$0.021.0M
models.devdeepseek-ai/DeepSeek-V4.1-FlashBaseten$0.3$1.20$0.031.0M
models.devtogether_ai/deepseek-ai/DeepSeek-V4.1-FlashEden AI$0.3$1.20$0.0061.0M
models.devdeepseek-ai/DeepSeek-V4.1-FlashHugging Face$0.3$1.20$01.0M
models.devdeepseek-ai/DeepSeek-V4.1-FlashNebius$0.3$1.20$0.31.0M
models.devdeepseek-ai/DeepSeek-V4.1-FlashTogether AI$0.3$1.20$0.0061.0M
models.devdeepseek-v4.1-flashDigitalOcean$0.3$1.20$0.0061.0M
models.devdeepseek-v4-1-flashEmpirioLabs AI$0.3$1.20$0.31M
models.devdeepseek-v4.1-flashOpenCode Zen$0.3$1.20$0.0061M
models.devdeepseek-v4-1-flashVenice AI$0.3$1.20$0.00751M
models.devdeepseek/deepseek-v4.1-flashCrossModel$0.3$1.20$0.0061M
models.devdeepseek/deepseek-v4.1-flashKilo Gateway$0.3$1.20$0.0061.0M
OpenRouterdeepseek/deepseek-v4.1-flashOpenRouter$0.3$1.20$0.0061.0M
models.devdeepseek/deepseek-v4.1-flashVercel AI Gateway$0.3$1.20$0.0071.0M
models.devaccounts/fireworks/models/deepseek-v4p1-flashFireworks AI$0.3$1.20$0.0061M
models.devtogether-ai/deepseek-v4.1-flashLLM Gateway$0.3$1.20$0.0061.0M
LiteLLMdeepseek-ai/deepseek-v4.1-flashN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek-flashN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek/deepseek-flashN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek-v4.1-flashN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek/deepseek-v4.1-flashN/A$0.3$1.20$0.006N/A
LiteLLMaccounts/fireworks/models/deepseek-v4p1-flashN/A$0.3$1.20$0.006N/A
LiteLLMazure_ai/deepseek-v4.1-flashN/A$0.3$1.20$0.006N/A
LiteLLMdeepseek-v4p1-flashN/A$0.3$1.20$0.006N/A
models.devdeepseek-v4.1-flashVivgrid$0.31$1.23$0.011M
models.devdeepseek-v4.1-flashCharm Hyper$0.33$1.31$0.031.0M
models.devtensorx/deepseek/deepseek-v4.1-flashEden AI$0.5$1.50$0.1251.0M
models.devdeepseek-v4.1-flashRequesty$0.5$1.50$0.051.0M
models.devdeepseek/deepseek-v4.1-flashTensorX$0.5$1.50$0.131.0M
models.devhf:deepseek-ai/DeepSeek-V4.1-FlashSynthetic$0.6$1.20$0.03524K
models.devdeepseek-v4-1-flashTinfoil$0.65$1.45$0.131.0M
models.devTEE/deepseek-v4.1-flashNanoGPT$0.65$1.45$0.131.0M

Capabilities

  • Reasoning
  • Tool calling
  • Structured output
  • Attachments
  • Open weights
  • In: text
  • In: image
  • In: pdf
  • Out: text
Knowledge cutoff: 2025-05Released: 2026-09-10SourceFamily: deepseek-flash

Scores

Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.

Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.

See what this model costs you

The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.

macOSDownloadWindowsPreviewCLImacOS · Linux · WindowsApp StoreDownloadGoogle PlayDownload