Grok 4.5

xAIKey grok-4.5Also reported as xai/grok-4.5, gcli/grok-4.5, grok/grok-4.5, combo/grok-4.5, grok-oauth/grok-4.5, grok2api/grok-4.5, cursor/grok-4.5, x-ai/grok-4.5, opencode-go/grok-4.5, bohe/grok-4.5, pool/grok-4.5, shuo/grok-4.5, cliproxy internal/grok-4.5, cliproxy/grok-4.5, dignal/x-ai/grok-4.5

Rank
#114
by active users
Active users
9
Down 18 from 27 active users in the previous 30 days. vs previous 30 days
Adoption
0.9%
of 958 accounts
Tokens
1.1B
cache included
Est. cost
$491
at public list prices
First seen
Jun 11, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)958 accounts100% of tokens from an identified modelData through Nov 12, 2026, 00:47 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 12, 2026

Daily active users for Grok 4.5, Oct 14, 2026 to Nov 12, 2026. Peak 4. Use the left and right arrow keys to read each day.420
Show daily values
Daily active users and tokens for Grok 4.5
Date (UTC)Active usersTokens
Oct 14, 2026451.1M
Oct 15, 2026223.3M
Oct 16, 20263163.9M
Oct 17, 2026314.8M
Oct 18, 202637.3M
Oct 19, 2026115.6M
Oct 20, 202616M
Oct 21, 202600
Oct 22, 2026158.3M
Oct 23, 2026117.4M
Oct 24, 202619.2M
Oct 25, 2026216.4M
Oct 26, 2026339.1M
Oct 27, 2026110.5M
Oct 28, 202623.7M
Oct 29, 20261726K
Oct 30, 202629.4M
Oct 31, 2026145.4M
Nov 1, 2026134.5M
Nov 2, 2026210.2M
Nov 3, 202618.5M
Nov 4, 202616.8M
Nov 5, 202615.6M
Nov 6, 2026214M
Nov 7, 20262241.6M
Nov 8, 20263245.1M
Nov 9, 2026112.2M
Nov 10, 202618.9M
Nov 11, 202613.6M
Nov 12, 202600

Token mix

How the 1.1B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input15%
  • Output0.4%
  • Cache read85%
  • Cache write0%
  • Reasoning0.1%

Agents that carry Grok 4.5

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

  1. Grok Build53% of this model's tokens6active users
  2. OpenClaw27% of this model's tokens1active users
  3. Oh My Pi18% of this model's tokens1active users
  4. OpenCode0.8% of this model's tokens1active users
  5. Pi0.8% of this model's tokens1active users

Benchmarks

The best result for Grok 4.5 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
    154.1
    Rank #43 of 160 matched modelsNo conditions reportedModel released Jul 8, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.0Agentic coding · Terminal-Bench
    12.4%
    Rank #22 of 23 matched modelsHigh · Grok BuildPublished Aug 27, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Grok Build carried 53% of Grok 4.5 tokens in the last 30 days (6 active users).

  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    53.8%
    Rank #18 of 26 matched modelsHigh · mini-swe-agentModel released Jul 8, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,553
    Rank #38 of 110 matched modelsNo conditions reportedPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    93.4%
    Rank #16 of 151 matched modelsHighRun date Jul 8, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 96.4%, and Epoch AI estimates the reachable maximum at 97%. Differences between top models are small.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    57.2%
    Rank #44 of 86 matched modelsHighRun date Jul 9, 2026Source: epoch.ai (opens in a new tab)

    Near its ceiling: the top score is 93.7%, and Epoch AI estimates the reachable maximum at 95%. Differences between top models are small.

  • SimpleQA VerifiedKnowledge · Epoch AI
    48.3%
    Rank #31 of 80 matched modelsHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, CursorBench, 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 Oct 21, 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
$0.58
Est. per 1M tokens
85% cache reads
At the community mix
$0.38
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$3
Per 1M tokens at list prices
No cache

Cache reads were 85% of Grok 4.5 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 $0.30.
  • 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-4.5
    $2 input per 1M tokens$6 output per 1M tokens$0.30 cache read per 1M tokensCache write not listed500K tokens of context
  • OpenRouterx-ai/grok-4.5
    $2 input per 1M tokens$6 output per 1M tokens$0.30 cache read per 1M tokensCache write not listed500K tokens of context
  • Vercel AI Gatewayspacexai/grok-4.5
    $2 input per 1M tokens$6 output per 1M tokens$0.30 cache read per 1M tokensCache write not listed500K tokens of context

Specs

From models.dev (MIT), retrieved Oct 21, 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
— not listed
Release date
Jul 8, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used Grok 4.5 most in this period, by tokens. Hidden accounts are never listed.

  1. 1Mark Ferraz@mferraznw510.4Mtokens$82est. cost9active days$82 est. cost · 9 active days
  2. 2Zhen Huang@ZhenHuangLab295.2Mtokens$290est. cost21active days$290 est. cost · 21 active days
  3. 3Linh Doan@linhdmn193.1Mtokens$86est. cost4active days$86 est. cost · 4 active days
  4. 4Muhammad Yusuf@iamyuu73.9Mtokens$31est. cost8active days$31 est. cost · 8 active days
  5. 5Sean Swanson@seanGSISG8.5Mtokens—est. cost2active daysno price · 2 active days
  6. 6黄凌苍@lingcang7281.1Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  7. 7Soju06@Soju061.1Mtokens<$1est. cost1active days<$1 est. cost · 1 active days
  8. 8Tito@mynameistito50.3Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
  9. 9darkest_alex@aldegad3.7Ktokens<$1est. cost1active days<$1 est. cost · 1 active days

More from xAI

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

  1. Grok 4.714% adoption131active users
  2. Grok 4.64.3% adoption41active users
  3. Grok Bot Default3.1% adoption30active users
  4. Grok 4.7 Build Fast2.6% adoption25active users
  5. Grok Bot Automation2.1% adoption20active users
  6. Grok 4.7 High Fast1.9% adoption18active 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 Oct 21, 2026 · Data through Oct 15, 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 4.0 official leaderboard rows (results only, no task content).Terms not stated · Retrieved Oct 21, 2026 · Data through Oct 6, 2026Terminal-Bench 4.0 leaderboard, tbench.ai. Every score links back to the leaderboard.
  • models.devSpecs and list prices per provider.MIT · Retrieved Oct 21, 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