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

Rank
#917
by active users
Active users
1
Down 5 from 6 active users in the previous 30 days. vs previous 30 days
Adoption
0.1%
of 958 accounts
Tokens
16.3K
cache included
Est. cost
<$1
at public list prices
First seen
Jan 24, 2026
in any submission

Oct 14 – Nov 12, 2026 (UTC)958 accounts100% of tokens from an identified modelData through Nov 12, 2026, 01:39 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 14, 2026 to Nov 12, 2026. Peak 1. Use the left and right arrow keys to read each day.110
Show daily values
Daily active users and tokens for GPT-5.4 Mini
Date (UTC)Active usersTokens
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 16.3K tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input70%
  • Output0.1%
  • Cache read30%
  • Cache write0%
  • Reasoning0%

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. Hermes Agent100% 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
    148.7
    Rank #66 of 160 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 #61 of 151 matched modelsXHighRun date Aug 7, 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.

    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 #51 of 86 matched modelsXHighRun date Jun 12, 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.

    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 #63 of 80 matched modelsHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.0, 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 Oct 21, 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
$0.55
Est. per 1M tokens
30% cache reads
At the community mix
$0.11
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$1.69
Per 1M tokens at list prices
No cache

Cache reads were 30% of GPT-5.4 Mini 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

  • 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 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

  • 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 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
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. 1PROTIK MONDAL@MNDL-2716.3Ktokens<$1est. cost1active days<$1 est. cost · 1 active days

More from OpenAI

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

  1. GPT-6.1 Sol69% adoption660active users
  2. GPT-6 Astra59% adoption563active users
  3. GPT-6 Luna45% adoption433active users
  4. Codex Auto Review30% adoption289active users
  5. GPT-6.1 Terra28% adoption271active users
  6. GPT-6 Sol26% adoption246active 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.
  • 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