DeepSeek V4.1 Flash 1017

DeepSeekKey deepseek-v4.1-flash-1017Also reported as deepseek/deepseek-v4.1-flash-1017, deepseek-v4.1-flash:1017, ali/deepseek-v4.1-flash-1017, deepseek-ai/deepseek-v4.1-flash-1017, DeepSeek-V4.1-Flash-1017, alicn/deepseek-v4.1-flash-1017, sk/deepseek-v4.1-flash-1017, group/deepseek-v4.1-flash-1017, modelscope/deepseek-ai/deepseek-v4.1-flash-1017, @cf/deepseek-ai/deepseek-v4.1-flash-1017, codearts/deepseek-v4.1-flash-1017, cline-pass/deepseek-v4.1-flash-1017, cline-2/deepseek/deepseek-v4.1-flash-1017, cline/cline-pass/deepseek-v4.1-flash-1017, dahono/deepseek-v4.1-flash-1017

Rank
#28
by active users
Active users
79
Up 76 from 3 active users in the previous 30 days. vs previous 30 days
Adoption
8.2%
of 967 accounts
Tokens
80.4B
cache included
Est. cost
$1.3K
at public list prices
First seen
Sep 24, 2026
in any submission

Oct 15 – Nov 13, 2026 (UTC)967 accounts100% of tokens from an identified modelData through Nov 13, 2026, 07:02 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

4 active users on Nov 13, 2026

Daily active users for DeepSeek V4.1 Flash 1017, Oct 15, 2026 to Nov 13, 2026. Peak 21. Use the left and right arrow keys to read each day.25130
Show daily values
Daily active users and tokens for DeepSeek V4.1 Flash 1017
Date (UTC)Active usersTokens
Oct 15, 202600
Oct 16, 202619.7M
Oct 17, 202600
Oct 18, 20265113.9M
Oct 19, 202614451.2M
Oct 20, 202612548.8M
Oct 21, 202614350.6M
Oct 22, 2026141B
Oct 23, 2026171.3B
Oct 24, 20261125.1B
Oct 25, 2026154.2B
Oct 26, 2026163.1B
Oct 27, 2026123B
Oct 28, 2026191.7B
Oct 29, 2026144.5B
Oct 30, 2026192.3B
Oct 31, 2026132.9B
Nov 1, 2026172B
Nov 2, 2026131.7B
Nov 3, 2026141.3B
Nov 4, 2026142.4B
Nov 5, 2026161.8B
Nov 6, 2026181.7B
Nov 7, 2026173B
Nov 8, 2026152.7B
Nov 9, 2026213.9B
Nov 10, 2026174.1B
Nov 11, 2026154B
Nov 12, 2026141.3B
Nov 13, 2026418.9M

Token mix

How the 80.4B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input5.5%
  • Output0.4%
  • Cache read94%
  • Cache write<0.1%
  • Reasoning<0.1%

Agents that carry DeepSeek V4.1 Flash 1017

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

  1. Pi35% of this model's tokens16active users
  2. OpenCode24% of this model's tokens16active users
  3. Oh My Pi16% of this model's tokens12active users
  4. Claude Code8.6% of this model's tokens9active users
  5. Hermes Agent4.7% of this model's tokens15active users
  6. Reasonix3.5% of this model's tokens2active users
  7. DeepSeek Harness2.8% of this model's tokens11active users
  8. 9Router1.4% of this model's tokens1active users
  9. Senpi (OmO Native)1.4% of this model's tokens4active users
  10. Codex CLI1.1% of this model's tokens4active users
  11. ZCode0.3% of this model's tokens4active users
  12. OpenClaw0.3% of this model's tokens2active users
  13. Amp<0.1% of this model's tokens1active users
  14. Gajae Code<0.1% of this model's tokens1active users
  15. Command Code<0.1% of this model's tokens1active users
  16. Goose<0.1% of this model's tokens1active users
  17. Cline<0.1% of this model's tokens1active users
  18. Cherry Studio<0.1% of this model's tokens3active users
  19. Grok Build<0.1% of this model's tokens1active users
  20. cc-mirror/curl<0.1% of this model's tokens1active users

Benchmarks

The best result for DeepSeek V4.1 Flash 1017 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
    159.4
    Rank #22 of 158 matched modelsNo conditions reportedModel released Oct 17, 2026Source: epoch.ai (opens in a new tab)
  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    47.7%
    Rank #9 of 21 matched modelsMaxModel released Oct 17, 2026Source: cursor.com (opens in a new tab)
    Show 3 more results with other run conditionsHide the other results
    • Listed as DeepSeek V4.1 Flash 1017 Medium
      46.3%
      MediumModel released Oct 17, 2026Source: cursor.com (opens in a new tab)
    • Listed as DeepSeek V4.1 Flash 1017 High
      45.6%
      HighModel released Oct 17, 2026Source: cursor.com (opens in a new tab)
    • Listed as DeepSeek V4.1 Flash 1017 Low
      44.9%
      LowModel released Oct 17, 2026Source: cursor.com (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    93.2%
    Rank #23 of 160 matched modelsMaxRun date Oct 19, 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
    71.2%
    Rank #30 of 90 matched modelsMaxRun date Oct 19, 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
    42.5%
    Rank #48 of 86 matched modelsMaxRun date Oct 19, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, DeepSWE, FrontierSWE, Agent Arena, WebDev Arena. 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. DeepSeek is the lab's own API and the reference price for the estimates below.

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
$0.01
Est. per 1M tokens
94% cache reads
At the community mix
$0.01
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.26
Per 1M tokens at list prices
No cache

Cache reads were 94% of DeepSeek V4.1 Flash 1017 tokens in the last 30 days and 96% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • DeepSeek list prices per 1M tokens: input $0.15, output $0.60, cache read $0.003.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 30 days.
  • The community mix is the tokens of every identified model in the last 30 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

  • DeepSeekReferencedeepseek-flash
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.003 cache read per 1M tokensCache write not listed1.05M tokens of context
  • OpenRouterdeepseek/deepseek-v4.1-flash-1017
    $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-1017
    $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
  • Fireworks AIaccounts/fireworks/routers/deepseek-flash-latest
    $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
Show 2 more providersShow fewer providers
  • Deep Infradeepseek-ai/DeepSeek-V4.1-Flash-1017
    $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-1017
    $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
1.05M tokens
Max output
393K tokens
Input
Text, Image
Output
Text
Knowledge cutoff
May 2025
Release date
Oct 17, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used DeepSeek V4.1 Flash 1017 most in this period, by tokens. Hidden accounts are never listed.

  1. 1Limber Cheng@limberc24.4Btokens$412est. cost7active days$412 est. cost · 7 active days
  2. 2Andrei Branga@andreibranga15.6Btokens$179est. cost22active days$179 est. cost · 22 active days
  3. 3Brad Lishman@bradlishman11.1Btokens$123est. cost13active days$123 est. cost · 13 active days
  4. 4Baptiste@BaptisteFaisy2.8Btokens<$1est. cost6active days<$1 est. cost · 6 active days
  5. 5Park Hee Chan@channprj2.7Btokens<$1est. cost3active days<$1 est. cost · 3 active days
  6. 6mandoworks@mandoworks2.7Btokens$31est. cost19active days$31 est. cost · 19 active days
  7. 7Nehr@AgileInnov8tor2.4Btokens$24est. cost14active days$24 est. cost · 14 active days
  8. 8曹亚文@bobcyw2.4Btokens$23est. cost3active days$23 est. cost · 3 active days
  9. 9Casper@Casper0152.2Btokens<$1est. cost9active days<$1 est. cost · 9 active days
  10. 10Sunghyun Cho@anaclumos1.8Btokens$14est. cost3active days$14 est. cost · 3 active days

More from DeepSeek

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

  1. DeepSeek V4.1 Flash24% adoption230active users
  2. DeepSeek V4.1 Flash Free16% adoption150active users
  3. DeepSeek Flash12% adoption120active users
  4. DeepSeek V4 Pro5.5% adoption53active users
  5. DeepSeek V4 Flash5.0% adoption48active users
  6. DeepSeek V4 Flash 07311.8% adoption17active 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.
  • 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