Grok 4.6

xAIKey grok-4.6Also reported as xai/grok-4.6, combo/grok-4.6, grok/grok-4.6, cursor/grok-4.6, x-ai/grok-4.6, grok-sub/grok-4.6, grok2api/grok-4.6, [次]grok-4.6, hr-gr/grok-4.6, grok-oauth/grok-4.6, shuo/grok-4.6, xai-oauth/grok-4.6, gcli/grok-4.6

Rank
#44
by active users
Active users
41
Down 114 from 155 active users in the previous 30 days. vs previous 30 days
Adoption
4.3%
of 956 accounts
Tokens
4B
cache included
Est. cost
$1.5K
at public list prices
First seen
May 21, 2026
in any submission

Oct 15 – Nov 13, 2026 (UTC)956 accounts100% of tokens from an identified modelData through Nov 13, 2026, 01:06 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 Grok 4.6, Oct 15, 2026 to Nov 13, 2026. Peak 14. Use the left and right arrow keys to read each day.1580
Show daily values
Daily active users and tokens for Grok 4.6
Date (UTC)Active usersTokens
Oct 15, 202612594.8M
Oct 16, 202610221.5M
Oct 17, 202610336.3M
Oct 18, 202614141.6M
Oct 19, 2026991.6M
Oct 20, 2026719.4M
Oct 21, 20268152M
Oct 22, 202610233.1M
Oct 23, 202612177.6M
Oct 24, 20269279.4M
Oct 25, 20268219.9M
Oct 26, 20269158.5M
Oct 27, 20261074.2M
Oct 28, 20267149.7M
Oct 29, 2026737.2M
Oct 30, 202610133.5M
Oct 31, 20266107.8M
Nov 1, 20265135.5M
Nov 2, 2026377.3M
Nov 3, 2026850.3M
Nov 4, 20264133.9M
Nov 5, 2026893.1M
Nov 6, 2026648.7M
Nov 7, 2026422.8M
Nov 8, 20266103.2M
Nov 9, 2026684.1M
Nov 10, 2026392.2M
Nov 11, 202615M
Nov 12, 202624.3M
Nov 13, 202600

Token mix

How the 4B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input10%
  • Output0.4%
  • Cache read89%
  • Cache write0%
  • Reasoning0.6%

Agents that carry Grok 4.6

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

  1. Grok Build51% of this model's tokens27active users
  2. Hermes Agent26% of this model's tokens5active users
  3. Aside12% of this model's tokens4active users
  4. Senpi (OmO Native)7.6% of this model's tokens4active users
  5. ZCode2.1% of this model's tokens1active users
  6. Pi0.6% of this model's tokens1active users
  7. OpenClaw0.3% of this model's tokens1active users
  8. OpenCode0.2% of this model's tokens2active users
  9. Claude Code0.1% of this model's tokens2active users
  10. Oh My Pi<0.1% of this model's tokens3active users

Benchmarks

The best result for Grok 4.6 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. Agent rows also show Tokscale usage through that agent, side by side with the score. Usage does not explain the score.

All benchmarks
  • Epoch Capabilities IndexOverall · Epoch AI
    157.8
    Rank #28 of 158 matched modelsNo conditions reportedModel released Aug 12, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.1Agentic coding · Terminal-Bench
    19.7%
    Rank #16 of 23 matched modelsHigh · Grok BuildPublished Nov 3, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Grok Build carried 51% of Grok 4.6 tokens in the last 30 days (27 active users).

  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    41.4%
    Rank #15 of 21 matched modelsXHighModel released Aug 12, 2026Source: cursor.com (opens in a new tab)
    Show 3 more results with other run conditionsHide the other results
    • Listed as Grok 4.6 High
      40.4%
      HighModel released Aug 12, 2026Source: cursor.com (opens in a new tab)
    • Listed as Grok 4.6 Medium
      36.1%
      MediumModel released Aug 12, 2026Source: cursor.com (opens in a new tab)
    • Listed as Grok 4.6 Low
      33.4%
      LowModel released Aug 12, 2026Source: cursor.com (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    67.5%
    Rank #9 of 26 matched modelsMedium · mini-swe-agentModel released Aug 12, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    Show 3 more results with other run conditionsHide the other results
    • Listed as grok-4-6 (xhigh)
      66.7%
      XHigh · mini-swe-agentModel released Aug 12, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as grok-4-6 (high)
      65.2%
      High · mini-swe-agentModel released Aug 12, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as grok-4-6 (low)
      41.6%
      Low · mini-swe-agentModel released Aug 12, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • FrontierSWEAgentic coding · FrontierSWE, collected by Epoch AI
    25.3%
    Rank #16 of 23 matched modelsXHigh · proximusModel released Aug 12, 2026Source: frontierswe.com (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,617
    Rank #23 of 110 matched modelsHighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    +0.01
    Rank #28 of 48 matched modelsXHigh · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    94.0%
    Rank #14 of 160 matched modelsHighRun date Aug 12, 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.

    Show 1 more result with other run conditionsHide the other results
    • Listed as grok-4.6_xhigh
      93.2%
      XHighRun date Aug 14, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    66.0%
    Rank #37 of 90 matched modelsXHighRun date Aug 14, 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
    49.3%
    Rank #33 of 86 matched modelsHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as grok-4.6_xhigh
      48.9%
      XHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam. 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. xAI 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
$0.71
Est. per 1M tokens
89% cache reads
At the community mix
$0.57
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$3
Per 1M tokens at list prices
No cache

Cache reads were 89% of Grok 4.6 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

  • xAI list prices per 1M tokens: input $2, output $6, cache read $0.50.
  • 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

  • xAIReferencegrok-4.6
    $2 input per 1M tokens$6 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed500K tokens of context
  • Amazon Bedrockxai.grok-4.6
    $2.20 input per 1M tokens$6.60 output per 1M tokens$0.55 cache read per 1M tokensCache write not listed500K tokens of context
  • Vertexxai/grok-4.6
    $2 input per 1M tokens$6 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed524K tokens of context
  • Azuregrok-4.6
    $2 input per 1M tokens$6 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed200K tokens of context
Show 2 more providersShow fewer providers
  • OpenRouterx-ai/grok-4.6
    $2 input per 1M tokens$6 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed500K tokens of context
  • Vercel AI Gatewayspacexai/grok-4.6
    $2 input per 1M tokens$6 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed500K 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
500K tokens
Max output
500K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Feb 1, 2026
Release date
Aug 12, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Grok 4.6 most in this period, by tokens. Hidden accounts are never listed.

  1. 1Mark Ferraz@mferraznw1.3Btokens$293est. cost18active days$293 est. cost · 18 active days
  2. 2Soju06@Soju06944.6Mtokens—est. cost27active daysno price · 27 active days
  3. 3Sangrak Choi@kargnas407Mtokens$295est. cost17active days$295 est. cost · 17 active days
  4. 4siddicky@siddicky347.7Mtokens$217est. cost13active days$217 est. cost · 13 active days
  5. 5Code_G@codeg-dev290.3Mtokens$96est. cost10active days$96 est. cost · 10 active days
  6. 6Sunghyun Cho@anaclumos178.4Mtokens$152est. cost4active days$152 est. cost · 4 active days
  7. 7WONJUN SEO@ownuun163Mtokens$135est. cost5active days$135 est. cost · 5 active days
  8. 8Zhen Huang@ZhenHuangLab138.7Mtokens$95est. cost28active days$95 est. cost · 28 active days
  9. 9Alireza Bashiri@al3rez105Mtokens$108est. cost6active days$108 est. cost · 6 active days
  10. 10Minseo Choi@trac3r0019.9Mtokens$14est. cost4active days$14 est. cost · 4 active days

More from xAI

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

  1. Grok 4.713% adoption128active users
  2. Grok Bot Default2.7% adoption26active users
  3. Grok 4.7 Build Fast2.6% adoption25active users
  4. Grok Bot Automation1.9% adoption18active users
  5. Grok 4.7 High Fast1.5% adoption14active users
  6. Grok 4.7 High1.5% adoption14active 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.
  • Terminal-BenchTerminal-Bench 4.1 official leaderboard rows (results only, no task content).Terms not stated · Retrieved Nov 12, 2026 · Data through Nov 11, 2026Terminal-Bench 4.1 leaderboard, tbench.ai. Every score links back to the leaderboard.
  • 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