DeepSeek V4.1 Flash

DeepSeekKey deepseek-v4.1-flashAlso reported as deepseek/deepseek-v4.1-flash, cb/deepseek-v4.1-flash, group/deepseek-v4.1-flash, combo/deepseek-v4.1-flash, inferhub/deepseek-v4.1-flash, ses-lite/deepseek-v4.1-flash, ih/deepseek-v4.1-flash, deepseek-ai/deepseek-v4.1-flash, bai/deepseek-v4.1-flash, opencode-go/deepseek-v4.1-flash, ollama-cloud/deepseek-v4.1-flash, opencode/deepseek-v4.1-flash, auto/deepseek-v4.1-flash, commandcode/deepseek/deepseek-v4.1-flash, cmc/deepseek/deepseek-v4.1-flash, workbuddy/deepseek-v4.1-flash, puri/deepseek-v4.1-flash, command-code/deepseek/deepseek-v4.1-flash, workbuddy-ai/deepseek-v4.1-flash, commandcode/deepseek-v4.1-flash

Rank
#11
by active users
Active users
91
Down 34 from 125 active users in the previous 7 days. vs previous 7 days
Adoption
15%
of 610 accounts
Tokens
125.9B
cache included
Est. cost
$1.8K
at public list prices
First seen
May 23, 2026
in any submission

Nov 6–12, 2026 (UTC)610 accounts100% of tokens from an identified modelData through Nov 12, 2026, 07:55 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

25 active users on Nov 12, 2026

Daily active users for DeepSeek V4.1 Flash, Nov 6, 2026 to Nov 12, 2026. Peak 61. Use the left and right arrow keys to read each day.80400
Show daily values
Daily active users and tokens for DeepSeek V4.1 Flash
Date (UTC)Active usersTokens
Nov 6, 20265718.3B
Nov 7, 20264821.2B
Nov 8, 20265422.5B
Nov 9, 20266122.4B
Nov 10, 20265119.9B
Nov 11, 20265014.1B
Nov 12, 2026257.5B

Token mix

How the 125.9B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input5.9%
  • Output0.4%
  • Cache read94%
  • Cache write0%
  • Reasoning<0.1%

Agents that carry DeepSeek V4.1 Flash

Each agent's share of this model's tokens, and how many accounts used the model through it.

  1. OpenCode33% of this model's tokens28active users
  2. Oh My Pi25% of this model's tokens17active users
  3. Claude Code21% of this model's tokens10active users
  4. Senpi (OmO Native)9.6% of this model's tokens6active users
  5. Codex CLI3.2% of this model's tokens9active users
  6. Pi3.1% of this model's tokens16active users
  7. WorkBuddy1.8% of this model's tokens11active users
  8. DeepSeek Harness1.3% of this model's tokens5active users
  9. ZCode1.2% of this model's tokens1active users
  10. Hermes Agent0.6% of this model's tokens12active users
  11. Aside0.2% of this model's tokens2active users
  12. Command Code0.2% of this model's tokens3active users
  13. CodeBuddy0.2% of this model's tokens3active users
  14. Hindsight0.1% of this model's tokens2active users
  15. Kimi<0.1% of this model's tokens1active users
  16. cc-mirror/curl<0.1% of this model's tokens1active users
  17. cc-mirror/python-urllib<0.1% of this model's tokens1active users

Benchmarks

The best result for DeepSeek V4.1 Flash in each benchmark Tokscale tracks. Each benchmark has its own unit, run conditions and source, so compare a score only with other models on the same benchmark. Rank is among the models Tokscale matched in that benchmark.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    156.7
    Rank #34 of 158 matched modelsNo conditions reportedModel released Sep 9, 2026Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,664
    Rank #12 of 110 matched modelsMaxPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as DeepSeek-V4.1-Flash-20260910 (Max)
      1,618
      MaxPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    +0.03
    Rank #19 of 48 matched modelsMax · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    89.8%
    Rank #49 of 160 matched modelsMaxRun date Oct 9, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.5%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    67.4%
    Rank #36 of 90 matched modelsMaxRun date Oct 8, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 95.1%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    42.9%
    Rank #47 of 86 matched modelsMaxRun date Oct 13, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE. A missing result is not a score of zero.

Pricing

List prices from models.dev in US dollars per 1M tokens, retrieved Nov 12, 2026. Azure is the reference price for the estimates below. It is the first provider listed; models.dev lists no price from the lab's own API.

Price at real agent usageEstimate at list prices

What 1M tokens cost at the reference list price when they split into input, output and cache the way Tokscale users' agents used them. It is not what anyone paid.

At this model's mix
$0.03
Est. per 1M tokens
94% cache reads
At the community mix
$0.02
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.52
Per 1M tokens at list prices
No cache

Cache reads were 94% of DeepSeek V4.1 Flash tokens in the last 7 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • Azure list prices per 1M tokens: input $0.30, output $1.20, cache read $0.006.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
  • The community mix is the tokens of every identified model in the last 7 days.
  • This is an estimate at list prices, not what anyone paid.
  • Reasoning tokens are priced as output.
  • Long-context tiers, batch pricing and discounts are not applied.
  • Token mixes come from public Tokscale submissions. Hidden accounts are excluded.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • AzureReferencedeepseek-v4.1-flash
    $0.30 input per 1M tokens$1.20 output per 1M tokens$0.006 cache read per 1M tokensCache write not listed1M tokens of context
  • OpenRouterdeepseek/deepseek-v4.1-flash
    $0.006 input per 1M tokens$0.50 output per 1M tokens$0.005 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewaydeepseek/deepseek-v4.1-flash
    $0.30 input per 1M tokens$1.20 output per 1M tokens$0.007 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Together AIdeepseek-ai/DeepSeek-V4.1-Flash
    $0.30 input per 1M tokens$1.20 output per 1M tokens$0.006 cache read per 1M tokensCache write not listed1.05M tokens of context
Show 3 more providersShow fewer providers
  • Fireworks AIaccounts/fireworks/models/deepseek-v4p1-flash
    $0.30 input per 1M tokens$1.20 output per 1M tokens$0.006 cache read per 1M tokensCache write not listed1M tokens of context
  • Deep Infradeepseek-ai/DeepSeek-V4.1-Flash
    $0.20 input per 1M tokens$0.60 output per 1M tokens$0.006 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Basetendeepseek-ai/DeepSeek-V4.1-Flash
    $0.30 input per 1M tokens$1.20 output per 1M tokens$0.007 cache read per 1M tokensCache write not listed1.05M tokens of context

Specs

From models.dev (MIT), retrieved Nov 12, 2026, as the lab or the first listed provider reports them. A dash means models.dev does not list the value.

Context window
1M tokens
Max output
128K tokens
Input
Text, Image
Output
Text
Knowledge cutoff
May 2025
Release date
Sep 10, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used DeepSeek V4.1 Flash most in this period, by tokens. Hidden accounts are never listed.

  1. 1MinYoul Yang@alpoxdev20.2Btokens$539est. cost7active days$539 est. cost · 7 active days
  2. 2registered2nd@registered2nd18.6Btokens$189est. cost5active days$189 est. cost · 5 active days
  3. 3Shun Kakinoki@shunkakinoki15.2Btokens$13est. cost7active days$13 est. cost · 7 active days
  4. 4DevNewbie1826@DevNewbie18268.8Btokens$259est. cost7active days$259 est. cost · 7 active days
  5. 5Darren@buddman12088.4Btokens<$1est. cost7active days<$1 est. cost · 7 active days
  6. 6Carlos Florêncio@carlosflorencio6.7Btokens$64est. cost6active days$64 est. cost · 6 active days
  7. 7Lee Wai Chong@leewaichong3.9Btokens$41est. cost6active days$41 est. cost · 6 active days
  8. 812zrr23@12zrr233.6Btokens$22est. cost7active days$22 est. cost · 7 active days
  9. 9Ray Tian@xtianxx3.6Btokens$60est. cost7active days$60 est. cost · 7 active days
  10. 10LynnGuo666@LynnGuo6662.9Btokens$61est. cost4active days$61 est. cost · 4 active days

More from DeepSeek

Other DeepSeek models in the same period, by active users.

  1. DeepSeek Flash6.2% adoption38active users
  2. DeepSeek V4.1 Flash 10175.6% adoption34active users
  3. DeepSeek V4.1 Flash Free5.1% adoption31active users
  4. DeepSeek V4 Flash1.6% adoption10active users
  5. DeepSeek V4 Pro1.5% adoption9active users
  6. DeepSeek V4.1 Flash Ultrafast0.8% adoption5active users
All models

Sources and attribution

Each score keeps its own source, unit and run conditions. Tokscale does not combine benchmarks into one score, and a missing score means the model was not evaluated, not that it scored zero.

  • Epoch AIEpoch Capabilities Index, Epoch's own runs and the external results it collects.CC BY 4.0 · Retrieved Nov 12, 2026 · Data through Nov 9, 2026Epoch AI, ‘Capabilities & benchmarking’. Published online at epoch.ai. Retrieved from https://epoch.ai/benchmarks.
  • LMArenaWebDev Arena and Agent Arena leaderboards.CC BY 4.0 · Retrieved Oct 21, 2026 · Data through Oct 19, 2026LMArena leaderboard dataset (lmarena-ai/leaderboard-dataset), Hugging Face.
  • models.devSpecs and list prices per provider.MIT · Retrieved Nov 12, 2026models.dev, an open catalog of AI models (github.com/anomalyco/models.dev).
  • TokscaleActive users, tokens and token mix from public Tokscale submissions. Hidden accounts are excluded.How we count