GPT-5.5

OpenAIKey gpt-5.5Also reported as router_client:codex/gpt-5.5, cx/gpt-5.5, router_client:unknown/gpt-5.5, openai/gpt-5.5, azure/gpt-5.5, hapuppy/gpt-5.5, kuro/gpt-5.5, codex/gpt-5.5, vibeproxy/gpt-5.5, zhen/gpt-5.5, combo/deep/gpt-5.5, cliproxy/gpt-5.5, csgpu/csu/pro/gpt-5.5, combo/ultrabrain/gpt-5.5, openai codex/gpt-5.5, combo/ruthless-reviewer/gpt-5.5, combo/architecture-consultant/gpt-5.5, openai-codex/gpt-5.5, shopai/gpt-5.5, eco/gpt-5.5

Rank
#51
by active users
Active users
30
Down 161 from 191 active users in the previous 30 days. vs previous 30 days
Adoption
3.1%
of 958 accounts
Tokens
624.2M
cache included
Est. cost
$756
at public list prices
First seen
Dec 31, 2025
in any submission

Oct 14 – Nov 12, 2026 (UTC)958 accounts100% of tokens from an identified modelData through Nov 12, 2026, 01:09 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-5.5, Oct 14, 2026 to Nov 12, 2026. Peak 26. Use the left and right arrow keys to read each day.30150
Show daily values
Daily active users and tokens for GPT-5.5
Date (UTC)Active usersTokens
Oct 14, 202626488.2M
Oct 15, 20262483K
Oct 16, 202600
Oct 17, 202600
Oct 18, 202600
Oct 19, 202623.9M
Oct 20, 202612.3M
Oct 21, 202600
Oct 22, 202600
Oct 23, 202611.5M
Oct 24, 202611.7M
Oct 25, 202600
Oct 26, 202600
Oct 27, 202614.9M
Oct 28, 2026110.9M
Oct 29, 202619.6M
Oct 30, 202611.5M
Oct 31, 202615.3M
Nov 1, 202612.8M
Nov 2, 20261703K
Nov 3, 2026190.4M
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 624.2M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input9.1%
  • Output0.3%
  • Cache read90%
  • Cache write0%
  • Reasoning0.1%

Agents that carry GPT-5.5

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

  1. Codex CLI89% of this model's tokens20active users
  2. OpenCode7.1% of this model's tokens1active users
  3. OpenClaw2.1% of this model's tokens3active users
  4. Synthetic1.8% of this model's tokens1active users
  5. Junie0.3% of this model's tokens1active users
  6. Hermes Agent0.1% of this model's tokens3active users
  7. Aside<0.1% of this model's tokens1active users

Benchmarks

The best result for GPT-5.5 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
    159.7
    Rank #14 of 160 matched modelsNo conditions reportedModel released Apr 23, 2026Source: epoch.ai (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    67.0%
    Rank #11 of 26 matched modelsXHigh · mini-swe-agentModel released Apr 23, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    Show 3 more results with other run conditionsHide the other results
    • Listed as gpt-5-5 (high)
      64.4%
      High · mini-swe-agentModel released Apr 23, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as gpt-5-5 (medium)
      54.0%
      Medium · mini-swe-agentModel released Apr 23, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as gpt-5-5 (low)
      27.0%
      Low · mini-swe-agentModel released Apr 23, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,513
    Rank #50 of 110 matched modelsXHigh · CodexPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)

    Tokscale usage: Codex CLI carried 89% of GPT-5.5 tokens in the last 30 days (20 active users).

    Show 2 more results with other run conditionsHide the other results
    • Listed as GPT-5.5 (High, Codex Harness)
      1,487
      High · CodexPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
    • Listed as GPT-5.5 (Codex Harness)
      1,456
      CodexPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • Agent ArenaAgents · LMArena
    +0.03
    Rank #17 of 48 matched modelsXHigh · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
    Show 1 more result with other run conditionsHide the other results
    • Listed as GPT-5.5
      −0.00
      Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    94.0%
    Rank #12 of 151 matched modelsXHighRun date Apr 24, 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-5.5_low
      90.7%
      LowRun date May 5, 2026Source: epoch.ai (opens in a new tab)
    • Listed as gpt-5.5_none
      77.3%
      No reasoningRun date Aug 7, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    85.3%
    Rank #13 of 86 matched modelsXHighRun date Jun 11, 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
    63.0%
    Rank #14 of 80 matched modelsXHighRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
  • SWE-bench VerifiedHistory · Epoch AI
    80.6%
    Rank #2 of 32 matched modelsXHighRun date Apr 24, 2026Source: epoch.ai (opens in a new tab)

    History only. Newer agentic coding benchmarks are on the main board.

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.0, CursorBench, FrontierSWE. 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
$1.04
Est. per 1M tokens
90% cache reads
At the community mix
$0.76
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$11.25
Per 1M tokens at list prices
No cache

Cache reads were 90% of GPT-5.5 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

  • OpenAI list prices per 1M tokens: input $5, output $30, 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

  • OpenAIReferencegpt-5.5
    $5 input per 1M tokens$30 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Amazon Bedrockopenai.gpt-5.5
    $5.50 input per 1M tokens$33 output per 1M tokens$0.55 cache read per 1M tokensCache write not listed1M tokens of context
  • Azuregpt-5.5
    $5 input per 1M tokens$30 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed1.05M tokens of context
  • OpenRouteropenai/gpt-5.5
    $5 input per 1M tokens$30 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed1.05M tokens of context
  • Vercel AI Gatewayopenai/gpt-5.5
    $5 input per 1M tokens$30 output per 1M tokens$0.50 cache read per 1M tokensCache write not listed1M 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
1.05M tokens
Max output
128K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Dec 1, 2025
Release date
Apr 23, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GPT-5.5 most in this period, by tokens. Hidden accounts are never listed.

  1. 1HERO@baizhiyuan152.2Mtokens$131est. cost1active days$131 est. cost · 1 active days
  2. 2kr-yeon@kr-yeon129.9Mtokens$246est. cost1active days$246 est. cost · 1 active days
  3. 3Gian Crescini Santillan@lightshire108.3Mtokens$117est. cost1active days$117 est. cost · 1 active days
  4. 4wongup721-cmyk@wongup721-cmyk90.4Mtokens$89est. cost1active days$89 est. cost · 1 active days
  5. 5Joscha Götzer@JosXa44.1Mtokens$55est. cost12active days$55 est. cost · 12 active days
  6. 6Soju06@Soju0634.1Mtokens$29est. cost1active days$29 est. cost · 1 active days
  7. 7cxvh@cxvh13.8Mtokens$13est. cost1active days$13 est. cost · 1 active days
  8. 8Bulo@BuloZB12Mtokens$31est. cost1active days$31 est. cost · 1 active days
  9. 9Youngmin Joo@ymjoo1211.1Mtokens—est. cost1active daysno price · 1 active days
  10. 10Muxy1108@Muxy11087.6Mtokens$7est. cost1active days$7 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