DeepSeek V4 Flash

DeepSeekKey deepseek-v4-flashAlso reported as deepseek/deepseek-v4-flash, deepseek-ai/deepseek-v4-flash, opencode-go/deepseek-v4-flash, cline-pass/deepseek-v4-flash, cmc/deepseek/deepseek-v4-flash, cmd/deepseek/deepseek-v4-flash, ocg/deepseek-v4-flash, opengateway/deepseek/deepseek-v4-flash, ds/deepseek-v4-flash, fb/deepseek/deepseek-v4-flash, bai/deepseek-v4-flash, openrouter/deepseek/deepseek-v4-flash, hyper/deepseek-v4-flash, openrouter/deepseek-v4-flash, go/deepseek-v4-flash, command-code/deepseek/deepseek-v4-flash, tencentcloud-th/deepseek-v4-flash, bg/deepseek/deepseek-v4-flash, sub2api/deepseek-v4-flash, combo/deepseek-v4-flash

Rank
#46
by active users
Active users
9
Down 8 from 17 active users in the previous 7 days. vs previous 7 days
Adoption
1.5%
of 618 accounts
Tokens
333.5M
cache included
Est. cost
$15
at public list prices
First seen
Jan 2, 2026
in any submission

Nov 8–14, 2026 (UTC)618 accounts100% of tokens from an identified modelData through Nov 14, 2026, 01:58 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

1 active users on Nov 14, 2026

Daily active users for DeepSeek V4 Flash, Nov 8, 2026 to Nov 14, 2026. Peak 9. Use the left and right arrow keys to read each day.1050
Show daily values
Daily active users and tokens for DeepSeek V4 Flash
Date (UTC)Active usersTokens
Nov 8, 2026358.8M
Nov 9, 20269141.3M
Nov 10, 2026534.9M
Nov 11, 2026479M
Nov 12, 2026317.9M
Nov 13, 202621.6M
Nov 14, 2026121.7K

Token mix

How the 333.5M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input4.7%
  • Output0.8%
  • Cache read94%
  • Cache write0%
  • Reasoning0.2%

Agents that carry DeepSeek V4 Flash

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

  1. Pi82% of this model's tokens2active users
  2. Hermes Agent12% of this model's tokens3active users
  3. Claude Code5.0% of this model's tokens2active users
  4. DeepSeek Harness1.0% of this model's tokens1active users
  5. ZCode<0.1% of this model's tokens1active users
  6. Cherry Studio<0.1% of this model's tokens1active users

Benchmarks

The best result for DeepSeek V4 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
    146.8
    Rank #82 of 158 matched modelsNo conditions reportedModel released Apr 24, 2026Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,582
    Rank #33 of 110 matched modelsHighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)

Not evaluated: GPQA Diamond, Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), SimpleQA Verified, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE, Agent 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. 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
$0.19
Est. per 1M tokens
94% cache reads
At the community mix
$0.19
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.27
Per 1M tokens at list prices
No cache

Cache reads were 94% of DeepSeek V4 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 $0.19, output $0.51.
  • 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-read price is listed, so cache reads are priced as input.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • AzureReferencedeepseek-v4-flash
    $0.19 input per 1M tokens$0.51 output per 1M tokensCache read not listedCache write not listed1M tokens of context
  • OpenRouterdeepseek/deepseek-v4-flash
    $0.09 input per 1M tokens$0.18 output per 1M tokens$0.02 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewaydeepseek/deepseek-v4-flash
    $0.13 input per 1M tokens$0.26 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed1M tokens of context
  • Deep Infradeepseek-ai/DeepSeek-V4-Flash
    $0.09 input per 1M tokens$0.18 output per 1M tokens$0.02 cache read per 1M tokens$0.11 cache write per 1M tokens1.05M 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
384K tokens
Input
Text
Output
Text
Knowledge cutoff
May 2025
Release date
Apr 24, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

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

  1. 1Dorian@Denszh221.1Mtokens$10est. cost4active days$10 est. cost · 4 active days
  2. 2Hanlin Zhao@Starrylyn53.2Mtokens$1est. cost3active days$1 est. cost · 3 active days
  3. 3Arthur Brownlee IV@nulluserid24.3Mtokens$1est. cost6active days$1 est. cost · 6 active days
  4. 4Shun Kakinoki@shunkakinoki13.5Mtokens<$1est. cost7active days<$1 est. cost · 7 active days
  5. 5xingguangcuican@xingguangcuican666612.8Mtokens$1est. cost1active days$1 est. cost · 1 active days
  6. 6fanziyun@fanziyun4.1Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  7. 7AA0xBroleez@AA0xBroleez3.5Mtokens<$1est. cost3active days<$1 est. cost · 3 active days
  8. 8why@whyy95271.1Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  9. 9Anthony-Hoo@Anthony-Hoo285tokens<$1est. cost1active days<$1 est. cost · 1 active days

More from DeepSeek

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

  1. DeepSeek V4.1 Flash16% adoption96active users
  2. DeepSeek Flash6.0% adoption37active users
  3. DeepSeek V4.1 Flash Free6.0% adoption37active users
  4. DeepSeek V4.1 Flash 10175.2% adoption32active users
  5. DeepSeek V4 Pro1.6% adoption10active users
  6. DeepSeek V4.1 Flash 1M1.1% adoption7active 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