DeepSeek V4 Pro 0813

DeepSeekKey deepseek-v4-pro-0813Also reported as deepseek/deepseek-v4-pro-0813, @cf/deepseek-ai/deepseek-v4-pro-0813, deepseek-ai/deepseek-v4-pro-0813, deepseek-v4-pro:0813, alibaba-token-plan-intl/deepseek-v4-pro-0813, free/deepseek-v4-pro-0813, router_client:unknown/deepseek-v4-pro:0813, aion/deepseek-v4-pro-0813

Rank
#150
by active users
Active users
6
Down 5 from 11 active users in the previous 30 days. vs previous 30 days
Adoption
0.6%
of 967 accounts
Tokens
53.2M
cache included
Est. cost
$5
at public list prices
First seen
Aug 11, 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.

0 active users on Nov 13, 2026

Daily active users for DeepSeek V4 Pro 0813, Oct 15, 2026 to Nov 13, 2026. Peak 2. Use the left and right arrow keys to read each day.210
Show daily values
Daily active users and tokens for DeepSeek V4 Pro 0813
Date (UTC)Active usersTokens
Oct 15, 202611.5M
Oct 16, 202600
Oct 17, 202612.4M
Oct 18, 202611.7M
Oct 19, 202600
Oct 20, 202622.9M
Oct 21, 202600
Oct 22, 202600
Oct 23, 202600
Oct 24, 202619.2M
Oct 25, 202600
Oct 26, 202600
Oct 27, 202600
Oct 28, 202600
Oct 29, 202600
Oct 30, 202600
Oct 31, 202600
Nov 1, 202600
Nov 2, 2026133.1M
Nov 3, 202600
Nov 4, 202600
Nov 5, 202600
Nov 6, 202600
Nov 7, 202600
Nov 8, 20261203
Nov 9, 202600
Nov 10, 202600
Nov 11, 202612.3M
Nov 12, 202600
Nov 13, 202600

Token mix

How the 53.2M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input9.3%
  • Output0.9%
  • Cache read90%
  • Cache write0%
  • Reasoning0.3%

Agents that carry DeepSeek V4 Pro 0813

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

  1. OpenCode75% of this model's tokens3active users
  2. Pi17% of this model's tokens1active users
  3. OpenClaw7.7% of this model's tokens1active users
  4. cc-mirror/curl<0.1% of this model's tokens1active users

Benchmarks

The best result for DeepSeek V4 Pro 0813 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
    155.9
    Rank #41 of 158 matched modelsNo conditions reportedModel released Aug 13, 2026Source: epoch.ai (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    91.7%
    Rank #31 of 160 matched modelsMaxRun date Aug 18, 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
    64.6%
    Rank #41 of 90 matched modelsMaxRun date Aug 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
    52.9%
    Rank #27 of 86 matched modelsMaxRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, CursorBench, 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
$0.10
Est. per 1M tokens
90% cache reads
At the community mix
$0.05
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.99
Per 1M tokens at list prices
No cache

Cache reads were 90% of DeepSeek V4 Pro 0813 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 $0.66, output $1.98, cache read $0.02.
  • 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-v4-pro
    $0.66 input per 1M tokens$1.98 output per 1M tokens$0.02 cache read per 1M tokensCache write not listed1.05M tokens of context
  • OpenRouterdeepseek/deepseek-v4-pro-0813
    $0.11 input per 1M tokens$4.44 output per 1M tokens$0.10 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewaydeepseek/deepseek-v4-pro-0813
    $0.66 input per 1M tokens$1.98 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed1M tokens of context
  • Together AIdeepseek-ai/DeepSeek-V4-Pro-0813
    $1.32 input per 1M tokens$3.96 output per 1M tokens$0.13 cache read per 1M tokensCache write not listed1.05M tokens of context
Show 2 more providersShow fewer providers
  • Deep Infradeepseek-ai/DeepSeek-V4-Pro-0813
    $1.30 input per 1M tokens$2.60 output per 1M tokens$0.10 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Basetendeepseek-ai/DeepSeek-V4-Pro-0813
    $1.32 input per 1M tokens$3.96 output per 1M tokens$0.13 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
Output
Text
Knowledge cutoff
— not listed
Release date
Aug 13, 2026
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used DeepSeek V4 Pro 0813 most in this period, by tokens. Hidden accounts are never listed.

  1. 1皓@hpware35.5Mtokens$4est. cost2active days$4 est. cost · 2 active days
  2. 2Limber Cheng@limberc9.2Mtokens—est. cost1active daysno price · 1 active days
  3. 3Brandon@cloud-aspect4.1Mtokens<$1est. cost3active days<$1 est. cost · 3 active days
  4. 4snuconnectome@snuconnectome2.8Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  5. 5zRuvix@zRuvix1.5Mtokens—est. cost1active daysno price · 1 active days
  6. 6如是@MiFaZhan203tokens<$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 Flash24% adoption230active users
  2. DeepSeek V4.1 Flash Free16% adoption150active users
  3. DeepSeek Flash12% adoption120active users
  4. DeepSeek V4.1 Flash 10178.2% adoption79active users
  5. DeepSeek V4 Pro5.5% adoption53active users
  6. DeepSeek V4 Flash5.0% adoption48active 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