GPT-5.4 Mini

OpenAIKey gpt-5.4-miniAlso reported as cx/gpt-5.4-mini, codex/gpt-5.4-mini, openai/gpt-5.4-mini, combo/quick/gpt-5.4-mini, router_client:unknown/gpt-5.4-mini, gh/gpt-5.4-mini, router_client:codex/gpt-5.4-mini, vibeproxy/gpt-5.4-mini, openai%20codex%20(chatgpt%20plus%2fpro)/gpt-5.4-mini, cliproxy/gpt-5.4-mini

No usage of GPT-5.4 Mini in the last 7 days. Showing all time instead.

Rank
#14
by active users
Active users
1,039
All time
Adoption
42%
of 2,457 accounts
Tokens
200.3B
cache included
Est. cost
$232.9K
at public list prices
First seen
Jan 24, 2026
in any submission

Oct 10, 2024 – Nov 12, 2026 (UTC)2,457 accounts100% of tokens from an identified modelData through Nov 12, 2026, 07:57 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 GPT-5.4 Mini, Oct 10, 2024 to Nov 12, 2026. Peak 141. Use the left and right arrow keys to read each day.150750
Show daily values
Daily active users and tokens for GPT-5.4 Mini
Date (UTC)Active usersTokens
Oct 10, 202400
Oct 11, 202400
Oct 12, 202400
Oct 13, 202400
Oct 14, 202400
Oct 15, 202400
Oct 16, 202400
Oct 17, 202400
Oct 18, 202400
Oct 19, 202400
Oct 20, 202400
Oct 21, 202400
Oct 22, 202400
Oct 23, 202400
Oct 24, 202400
Oct 25, 202400
Oct 26, 202400
Oct 27, 202400
Oct 28, 202400
Oct 29, 202400
Oct 30, 202400
Oct 31, 202400
Nov 1, 202400
Nov 2, 202400
Nov 3, 202400
Nov 4, 202400
Nov 5, 202400
Nov 6, 202400
Nov 7, 202400
Nov 8, 202400
Nov 9, 202400
Nov 10, 202400
Nov 11, 202400
Nov 12, 202400
Nov 13, 202400
Nov 14, 202400
Nov 15, 202400
Nov 16, 202400
Nov 17, 202400
Nov 18, 202400
Nov 19, 202400
Nov 20, 202400
Nov 21, 202400
Nov 22, 202400
Nov 23, 202400
Nov 24, 202400
Nov 25, 202400
Nov 26, 202400
Nov 27, 202400
Nov 28, 202400
Nov 29, 202400
Nov 30, 202400
Dec 1, 202400
Dec 2, 202400
Dec 3, 202400
Dec 4, 202400
Dec 5, 202400
Dec 6, 202400
Dec 7, 202400
Dec 8, 202400
Dec 9, 202400
Dec 10, 202400
Dec 11, 202400
Dec 12, 202400
Dec 13, 202400
Dec 14, 202400
Dec 15, 202400
Dec 16, 202400
Dec 17, 202400
Dec 18, 202400
Dec 19, 202400
Dec 20, 202400
Dec 21, 202400
Dec 22, 202400
Dec 23, 202400
Dec 24, 202400
Dec 25, 202400
Dec 26, 202400
Dec 27, 202400
Dec 28, 202400
Dec 29, 202400
Dec 30, 202400
Dec 31, 202400
Jan 1, 202500
Jan 2, 202500
Jan 3, 202500
Jan 4, 202500
Jan 5, 202500
Jan 6, 202500
Jan 7, 202500
Jan 8, 202500
Jan 9, 202500
Jan 10, 202500
Jan 11, 202500
Jan 12, 202500
Jan 13, 202500
Jan 14, 202500
Jan 15, 202500
Jan 16, 202500
Jan 17, 202500
Jan 18, 202500
Jan 19, 202500
Jan 20, 202500
Jan 21, 202500
Jan 22, 202500
Jan 23, 202500
Jan 24, 202500
Jan 25, 202500
Jan 26, 202500
Jan 27, 202500
Jan 28, 202500
Jan 29, 202500
Jan 30, 202500
Jan 31, 202500
Feb 1, 202500
Feb 2, 202500
Feb 3, 202500
Feb 4, 202500
Feb 5, 202500
Feb 6, 202500
Feb 7, 202500
Feb 8, 202500
Feb 9, 202500
Feb 10, 202500
Feb 11, 202500
Feb 12, 202500
Feb 13, 202500
Feb 14, 202500
Feb 15, 202500
Feb 16, 202500
Feb 17, 202500
Feb 18, 202500
Feb 19, 202500
Feb 20, 202500
Feb 21, 202500
Feb 22, 202500
Feb 23, 202500
Feb 24, 202500
Feb 25, 202500
Feb 26, 202500
Feb 27, 202500
Feb 28, 202500
Mar 1, 202500
Mar 2, 202500
Mar 3, 202500
Mar 4, 202500
Mar 5, 202500
Mar 6, 202500
Mar 7, 202500
Mar 8, 202500
Mar 9, 202500
Mar 10, 202500
Mar 11, 202500
Mar 12, 202500
Mar 13, 202500
Mar 14, 202500
Mar 15, 202500
Mar 16, 202500
Mar 17, 202500
Mar 18, 202500
Mar 19, 202500
Mar 20, 202500
Mar 21, 202500
Mar 22, 202500
Mar 23, 202500
Mar 24, 202500
Mar 25, 202500
Mar 26, 202500
Mar 27, 202500
Mar 28, 202500
Mar 29, 202500
Mar 30, 202500
Mar 31, 202500
Apr 1, 202500
Apr 2, 202500
Apr 3, 202500
Apr 4, 202500
Apr 5, 202500
Apr 6, 202500
Apr 7, 202500
Apr 8, 202500
Apr 9, 202500
Apr 10, 202500
Apr 11, 202500
Apr 12, 202500
Apr 13, 202500
Apr 14, 202500
Apr 15, 202500
Apr 16, 202500
Apr 17, 202500
Apr 18, 202500
Apr 19, 202500
Apr 20, 202500
Apr 21, 202500
Apr 22, 202500
Apr 23, 202500
Apr 24, 202500
Apr 25, 202500
Apr 26, 202500
Apr 27, 202500
Apr 28, 202500
Apr 29, 202500
Apr 30, 202500
May 1, 202500
May 2, 202500
May 3, 202500
May 4, 202500
May 5, 202500
May 6, 202500
May 7, 202500
May 8, 202500
May 9, 202500
May 10, 202500
May 11, 202500
May 12, 202500
May 13, 202500
May 14, 202500
May 15, 202500
May 16, 202500
May 17, 202500
May 18, 202500
May 19, 202500
May 20, 202500
May 21, 202500
May 22, 202500
May 23, 202500
May 24, 202500
May 25, 202500
May 26, 202500
May 27, 202500
May 28, 202500
May 29, 202500
May 30, 202500
May 31, 202500
Jun 1, 202500
Jun 2, 202500
Jun 3, 202500
Jun 4, 202500
Jun 5, 202500
Jun 6, 202500
Jun 7, 202500
Jun 8, 202500
Jun 9, 202500
Jun 10, 202500
Jun 11, 202500
Jun 12, 202500
Jun 13, 202500
Jun 14, 202500
Jun 15, 202500
Jun 16, 202500
Jun 17, 202500
Jun 18, 202500
Jun 19, 202500
Jun 20, 202500
Jun 21, 202500
Jun 22, 202500
Jun 23, 202500
Jun 24, 202500
Jun 25, 202500
Jun 26, 202500
Jun 27, 202500
Jun 28, 202500
Jun 29, 202500
Jun 30, 202500
Jul 1, 202500
Jul 2, 202500
Jul 3, 202500
Jul 4, 202500
Jul 5, 202500
Jul 6, 202500
Jul 7, 202500
Jul 8, 202500
Jul 9, 202500
Jul 10, 202500
Jul 11, 202500
Jul 12, 202500
Jul 13, 202500
Jul 14, 202500
Jul 15, 202500
Jul 16, 202500
Jul 17, 202500
Jul 18, 202500
Jul 19, 202500
Jul 20, 202500
Jul 21, 202500
Jul 22, 202500
Jul 23, 202500
Jul 24, 202500
Jul 25, 202500
Jul 26, 202500
Jul 27, 202500
Jul 28, 202500
Jul 29, 202500
Jul 30, 202500
Jul 31, 202500
Aug 1, 202500
Aug 2, 202500
Aug 3, 202500
Aug 4, 202500
Aug 5, 202500
Aug 6, 202500
Aug 7, 202500
Aug 8, 202500
Aug 9, 202500
Aug 10, 202500
Aug 11, 202500
Aug 12, 202500
Aug 13, 202500
Aug 14, 202500
Aug 15, 202500
Aug 16, 202500
Aug 17, 202500
Aug 18, 202500
Aug 19, 202500
Aug 20, 202500
Aug 21, 202500
Aug 22, 202500
Aug 23, 202500
Aug 24, 202500
Aug 25, 202500
Aug 26, 202500
Aug 27, 202500
Aug 28, 202500
Aug 29, 202500
Aug 30, 202500
Aug 31, 202500
Sep 1, 202500
Sep 2, 202500
Sep 3, 202500
Sep 4, 202500
Sep 5, 202500
Sep 6, 202500
Sep 7, 202500
Sep 8, 202500
Sep 9, 202500
Sep 10, 202500
Sep 11, 202500
Sep 12, 202500
Sep 13, 202500
Sep 14, 202500
Sep 15, 202500
Sep 16, 202500
Sep 17, 202500
Sep 18, 202500
Sep 19, 202500
Sep 20, 202500
Sep 21, 202500
Sep 22, 202500
Sep 23, 202500
Sep 24, 202500
Sep 25, 202500
Sep 26, 202500
Sep 27, 202500
Sep 28, 202500
Sep 29, 202500
Sep 30, 202500
Oct 1, 202500
Oct 2, 202500
Oct 3, 202500
Oct 4, 202500
Oct 5, 202500
Oct 6, 202500
Oct 7, 202500
Oct 8, 202500
Oct 9, 202500
Oct 10, 202500
Oct 11, 202500
Oct 12, 202500
Oct 13, 202500
Oct 14, 202500
Oct 15, 202500
Oct 16, 202500
Oct 17, 202500
Oct 18, 202500
Oct 19, 202500
Oct 20, 202500
Oct 21, 202500
Oct 22, 202500
Oct 23, 202500
Oct 24, 202500
Oct 25, 202500
Oct 26, 202500
Oct 27, 202500
Oct 28, 202500
Oct 29, 202500
Oct 30, 202500
Oct 31, 202500
Nov 1, 202500
Nov 2, 202500
Nov 3, 202500
Nov 4, 202500
Nov 5, 202500
Nov 6, 202500
Nov 7, 202500
Nov 8, 202500
Nov 9, 202500
Nov 10, 202500
Nov 11, 202500
Nov 12, 202500
Nov 13, 202500
Nov 14, 202500
Nov 15, 202500
Nov 16, 202500
Nov 17, 202500
Nov 18, 202500
Nov 19, 202500
Nov 20, 202500
Nov 21, 202500
Nov 22, 202500
Nov 23, 202500
Nov 24, 202500
Nov 25, 202500
Nov 26, 202500
Nov 27, 202500
Nov 28, 202500
Nov 29, 202500
Nov 30, 202500
Dec 1, 202500
Dec 2, 202500
Dec 3, 202500
Dec 4, 202500
Dec 5, 202500
Dec 6, 202500
Dec 7, 202500
Dec 8, 202500
Dec 9, 202500
Dec 10, 202500
Dec 11, 202500
Dec 12, 202500
Dec 13, 202500
Dec 14, 202500
Dec 15, 202500
Dec 16, 202500
Dec 17, 202500
Dec 18, 202500
Dec 19, 202500
Dec 20, 202500
Dec 21, 202500
Dec 22, 202500
Dec 23, 202500
Dec 24, 202500
Dec 25, 202500
Dec 26, 202500
Dec 27, 202500
Dec 28, 202500
Dec 29, 202500
Dec 30, 202500
Dec 31, 202500
Jan 1, 202600
Jan 2, 202600
Jan 3, 202600
Jan 4, 202600
Jan 5, 202600
Jan 6, 202600
Jan 7, 202600
Jan 8, 202600
Jan 9, 202600
Jan 10, 202600
Jan 11, 202600
Jan 12, 202600
Jan 13, 202600
Jan 14, 202600
Jan 15, 202600
Jan 16, 202600
Jan 17, 202600
Jan 18, 202600
Jan 19, 202600
Jan 20, 202600
Jan 21, 202600
Jan 22, 202600
Jan 23, 202600
Jan 24, 20261260K
Jan 25, 202613.2M
Jan 26, 202611.4M
Jan 27, 20261340K
Jan 28, 20261706K
Jan 29, 202611.8M
Jan 30, 20261750K
Jan 31, 202612.1M
Feb 1, 202611.2M
Feb 2, 202611.3M
Feb 3, 202611.4M
Feb 4, 202611.6M
Feb 5, 202611.1M
Feb 6, 202613.4M
Feb 7, 20261939K
Feb 8, 20262449K
Feb 9, 202612.1M
Feb 10, 202613.5M
Feb 11, 202612.5M
Feb 12, 202613.3M
Feb 13, 202611.9M
Feb 14, 20261905K
Feb 15, 202621.2M
Feb 16, 20261558K
Feb 17, 202611.1M
Feb 18, 202621.1M
Feb 19, 202622.8M
Feb 20, 202623.6M
Feb 21, 20261903K
Feb 22, 202623.7M
Feb 23, 20261685K
Feb 24, 20261854K
Feb 25, 202623.8M
Feb 26, 202621.5M
Feb 27, 20262859K
Feb 28, 202621.3M
Mar 1, 202621.2M
Mar 2, 202622.6M
Mar 3, 202611.1M
Mar 4, 202612.7M
Mar 5, 202613M
Mar 6, 202611.7M
Mar 7, 202600
Mar 8, 20261987K
Mar 9, 202600
Mar 10, 20261168K
Mar 11, 202611.2M
Mar 12, 202600
Mar 13, 20261274K
Mar 14, 20262642K
Mar 15, 202621.1M
Mar 16, 20261219K
Mar 17, 202615777M
Mar 18, 202650604.2M
Mar 19, 2026622.2B
Mar 20, 2026641.6B
Mar 21, 202651710.6M
Mar 22, 2026574.1B
Mar 23, 202664571.3M
Mar 24, 202667735M
Mar 25, 202682971.9M
Mar 26, 2026871B
Mar 27, 2026841.3B
Mar 28, 202671892.4M
Mar 29, 202668963.3M
Mar 30, 20261091.3B
Mar 31, 20261141.8B
Apr 1, 2026991.4B
Apr 2, 20261091.9B
Apr 3, 20261151.3B
Apr 4, 2026761.2B
Apr 5, 202677969.9M
Apr 6, 20261042B
Apr 7, 20261071.9B
Apr 8, 20261264.2B
Apr 9, 20261344.1B
Apr 10, 20261275.6B
Apr 11, 2026932.1B
Apr 12, 2026931.9B
Apr 13, 20261321.9B
Apr 14, 20261392.4B
Apr 15, 20261312.2B
Apr 16, 20261322.6B
Apr 17, 20261063.4B
Apr 18, 2026811B
Apr 19, 2026941.2B
Apr 20, 20261282.5B
Apr 21, 20261261.7B
Apr 22, 20261202.5B
Apr 23, 20261412.1B
Apr 24, 20261071.4B
Apr 25, 202672629.7M
Apr 26, 202668468.7M
Apr 27, 202689925.1M
Apr 28, 202680845.3M
Apr 29, 2026991.3B
Apr 30, 202692855.3M
May 1, 202672992.1M
May 2, 202654472.3M
May 3, 2026611.1B
May 4, 2026691.4B
May 5, 202665512.4M
May 6, 2026811.1B
May 7, 2026671.4B
May 8, 2026741.1B
May 9, 2026491.4B
May 10, 2026601.1B
May 11, 2026721.1B
May 12, 2026711.2B
May 13, 2026801.2B
May 14, 202665751M
May 15, 2026661.3B
May 16, 2026541.5B
May 17, 2026571.8B
May 18, 2026732.4B
May 19, 2026701.7B
May 20, 2026781B
May 21, 2026762.7B
May 22, 202670882.8M
May 23, 202648979.4M
May 24, 202661934.4M
May 25, 202662830.7M
May 26, 202681917.5M
May 27, 2026722.5B
May 28, 202666937.7M
May 29, 2026621.2B
May 30, 2026421.3B
May 31, 202668657.2M
Jun 1, 20261011.8B
Jun 2, 20261191.4B
Jun 3, 2026963.9B
Jun 4, 20261031.9B
Jun 5, 2026101910.8M
Jun 6, 202667639.4M
Jun 7, 2026691.5B
Jun 8, 2026891.6B
Jun 9, 2026102887.9M
Jun 10, 202684811.3M
Jun 11, 2026971B
Jun 12, 20261002.2B
Jun 13, 2026743.2B
Jun 14, 2026712.1B
Jun 15, 2026893.1B
Jun 16, 202684809.6M
Jun 17, 202694755.9M
Jun 18, 20261081.4B
Jun 19, 2026801.2B
Jun 20, 2026811.4B
Jun 21, 2026731.5B
Jun 22, 2026962.5B
Jun 23, 20261133.2B
Jun 24, 2026991.8B
Jun 25, 2026941B
Jun 26, 2026100804.2M
Jun 27, 202670548.8M
Jun 28, 202660667M
Jun 29, 202695764.9M
Jun 30, 2026992.4B
Jul 1, 2026942.6B
Jul 2, 20261052.6B
Jul 3, 202692943.7M
Jul 4, 2026731.5B
Jul 5, 2026671.5B
Jul 6, 202693562.2M
Jul 7, 20261011.2B
Jul 8, 2026981B
Jul 9, 202694769.1M
Jul 10, 202689885.3M
Jul 11, 202655650M
Jul 12, 202642741.2M
Jul 13, 202663525.6M
Jul 14, 202656303.6M
Jul 15, 202642218.1M
Jul 16, 202645224.6M
Jul 17, 202640479.5M
Jul 18, 2026351.9B
Jul 19, 2026381.3B
Jul 20, 202640310.7M
Jul 21, 202648319.5M
Jul 22, 202657460.1M
Jul 23, 202650404.3M
Jul 24, 202642317.9M
Jul 25, 202624186M
Jul 26, 202625205M
Jul 27, 202644520.7M
Jul 28, 202642531.3M
Jul 29, 202644867.2M
Jul 30, 202639711.5M
Jul 31, 202641502.2M
Aug 1, 202628130.7M
Aug 2, 202630348.5M
Aug 3, 202637422M
Aug 4, 202634333.3M
Aug 5, 202628343M
Aug 6, 202633609.4M
Aug 7, 202622179.5M
Aug 8, 202620242.9M
Aug 9, 202624261.7M
Aug 10, 202638388.5M
Aug 11, 202641452.8M
Aug 12, 202635459M
Aug 13, 202634318.4M
Aug 14, 202625358M
Aug 15, 202620201.8M
Aug 16, 202617180.6M
Aug 17, 202617152.3M
Aug 18, 202621120.3M
Aug 19, 202616131.6M
Aug 20, 202623134.6M
Aug 21, 202621372.2M
Aug 22, 202620374.9M
Aug 23, 202613336.1M
Aug 24, 202621259.9M
Aug 25, 202621565.6M
Aug 26, 202620336.5M
Aug 27, 202621209.3M
Aug 28, 202623274.8M
Aug 29, 202620136.7M
Aug 30, 202616360.8M
Aug 31, 202622310.1M
Sep 1, 202624286.9M
Sep 2, 202622349.9M
Sep 3, 202618176.4M
Sep 4, 202621274.9M
Sep 5, 202618147.2M
Sep 6, 20261994.7M
Sep 7, 202623214.3M
Sep 8, 202617253M
Sep 9, 2026314.8M
Sep 10, 202600
Sep 11, 2026146
Sep 12, 202600
Sep 13, 202600
Sep 14, 202600
Sep 15, 202600
Sep 16, 2026110.2K
Sep 17, 202600
Sep 18, 202600
Sep 19, 20261800K
Sep 20, 2026121
Sep 21, 202600
Sep 22, 202600
Sep 23, 202600
Sep 24, 202600
Sep 25, 2026123
Sep 26, 202600
Sep 27, 202600
Sep 28, 20261572K
Sep 29, 2026146.9K
Sep 30, 202600
Oct 1, 202600
Oct 2, 202600
Oct 3, 202618.3K
Oct 4, 202600
Oct 5, 202600
Oct 6, 202600
Oct 7, 2026169.8K
Oct 8, 202614.3K
Oct 9, 20261192K
Oct 10, 202600
Oct 11, 202600
Oct 12, 202600
Oct 13, 202600
Oct 14, 202600
Oct 15, 202600
Oct 16, 202600
Oct 17, 202600
Oct 18, 202600
Oct 19, 202600
Oct 20, 202600
Oct 21, 202600
Oct 22, 202600
Oct 23, 202600
Oct 24, 202600
Oct 25, 202600
Oct 26, 2026116.3K
Oct 27, 202600
Oct 28, 202600
Oct 29, 202600
Oct 30, 202600
Oct 31, 202600
Nov 1, 202600
Nov 2, 202600
Nov 3, 202600
Nov 4, 202600
Nov 5, 202600
Nov 6, 202600
Nov 7, 202600
Nov 8, 202600
Nov 9, 202600
Nov 10, 202600
Nov 11, 202600
Nov 12, 202600

Token mix

How the 200.3B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input14%
  • Output1.3%
  • Cache read83%
  • Cache write<0.1%
  • Reasoning1.0%

Agents that carry GPT-5.4 Mini

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

  1. Codex CLI74% of this model's tokens862active users
  2. OpenCode18% of this model's tokens286active users
  3. OpenClaw2.7% of this model's tokens23active users
  4. Hermes Agent1.8% of this model's tokens77active users
  5. Pi1.7% of this model's tokens70active users
  6. Claude Code0.6% of this model's tokens17active users
  7. Oh My Pi0.3% of this model's tokens21active users
  8. Senpi (OmO Native)0.2% of this model's tokens17active users
  9. Aside0.2% of this model's tokens19active users
  10. Copilot<0.1% of this model's tokens22active users
  11. Gajae Code<0.1% of this model's tokens10active users
  12. Cline<0.1% of this model's tokens3active users
  13. Synthetic<0.1% of this model's tokens1active users
  14. Prime Agent<0.1% of this model's tokens2active users
  15. Cursor<0.1% of this model's tokens2active users
  16. Grok Build<0.1% of this model's tokens2active users
  17. Junie<0.1% of this model's tokens1active users
  18. Jcode<0.1% of this model's tokens1active users
  19. Kilo<0.1% of this model's tokens1active users
  20. Kimi<0.1% of this model's tokens2active users
  21. Goose<0.1% of this model's tokens1active users

Benchmarks

The best result for GPT-5.4 Mini 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
    149.3
    Rank #70 of 158 matched modelsNo conditions reportedModel released Mar 17, 2026Source: epoch.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,397
    Rank #80 of 110 matched modelsHighPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    86.9%
    Rank #66 of 160 matched modelsXHighRun date Aug 7, 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 2 more results with other run conditionsHide the other results
    • Listed as gpt-5.4-mini-2026-03-17_high
      83.6%
      HighRun date Apr 15, 2026Source: epoch.ai (opens in a new tab)
    • Listed as gpt-5.4-mini-2026-03-17_none
      64.1%
      No reasoningRun date Aug 7, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    51.2%
    Rank #55 of 90 matched modelsXHighRun date Jun 12, 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.

    Show 2 more results with other run conditionsHide the other results
    • Listed as gpt-5.4-mini-2026-03-17_low
      24.6%
      LowRun date Aug 28, 2026Source: epoch.ai (opens in a new tab)
    • Listed as gpt-5.4-mini-2026-03-17_none
      17.2%
      No reasoningRun date Aug 28, 2026Source: epoch.ai (opens in a new tab)
  • SimpleQA VerifiedKnowledge · Epoch AI
    29.4%
    Rank #69 of 86 matched modelsHighRun 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. 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. OpenAI 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
$0.28
Est. per 1M tokens
83% cache reads
At the community mix
$0.14
Est. per 1M tokens
93% cache reads
3:1 input/output blend
$1.69
Per 1M tokens at list prices
No cache

Cache reads were 83% of GPT-5.4 Mini tokens across all time and 93% of all tokens. The 3:1 blend, (3 × input + output) ÷ 4, is the usual comparison and ignores cache.

Assumptions

  • OpenAI list prices per 1M tokens: input $0.75, output $4.50, cache read $0.07.
  • This model's mix is its own input, output, cache and reasoning tokens across all time.
  • The community mix is the tokens of every identified model across all time.
  • 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

  • OpenAIReferencegpt-5.4-mini
    $0.75 input per 1M tokens$4.50 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed400K tokens of context
  • Azuregpt-5.4-mini
    $0.75 input per 1M tokens$4.50 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed400K tokens of context
  • OpenRouteropenai/gpt-5.4-mini
    $0.75 input per 1M tokens$4.50 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed400K tokens of context
  • Vercel AI Gatewayopenai/gpt-5.4-mini
    $0.75 input per 1M tokens$4.50 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed400K 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
400K tokens
Max output
128K tokens
Input
Text, Image
Output
Text
Knowledge cutoff
Aug 31, 2025
Release date
Mar 17, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GPT-5.4 Mini most in this period, by tokens. Hidden accounts are never listed.

  1. 1Lai Quang Huy@1qh16.2Btokens$15.1Kest. cost94active days$15.1K est. cost · 94 active days
  2. 2Code_G@codeg-dev6.7Btokens$2.2Kest. cost120active days$2.2K est. cost · 120 active days
  3. 3Wooseok Sung@MercuriusDream6Btokens$1.1Kest. cost14active days$1.1K est. cost · 14 active days
  4. 4Sirawit Bongsuwan@srwbsw4.8Btokens$739est. cost71active days$739 est. cost · 71 active days
  5. 5Daniil Sedov@Gusarich4.7Btokens$856est. cost5active days$856 est. cost · 5 active days
  6. 6iborrowcheckbtw@xsyetopz4.7Btokens$648est. cost33active days$648 est. cost · 33 active days
  7. 7Yoonjae@AngryJay914.4Btokens$368est. cost9active days$368 est. cost · 9 active days
  8. 8starcasso@Betalgeuse3.8Btokens$647est. cost54active days$647 est. cost · 54 active days
  9. 9hayden@haydenkwak3.7Btokens$718est. cost33active days$718 est. cost · 33 active days
  10. 10YeonGyu-Kim@code-yeongyu3.5Btokens$833est. cost82active days$833 est. cost · 82 active days

More from OpenAI

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

  1. GPT-5.565% adoption1,585active users
  2. GPT-5.462% adoption1,528active users
  3. GPT-5.3 Codex54% adoption1,334active users
  4. GPT-5.6 Sol51% adoption1,260active users
  5. GPT-5.6 Terra45% adoption1,105active users
  6. GPT-5.6 Luna44% adoption1,078active 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