GPT-5.6 Sol

OpenAIKey gpt-5.6-solAlso reported as router_client:codex/gpt-5.6-sol, codex/gpt-5.6-sol, cx/gpt-5.6-sol, openai/gpt-5.6-sol, chatgpt-web/gpt-5.6-sol, kiro/gpt-5.6-sol, openai codex/gpt-5.6-sol, azure-openai/gpt-5.6-sol, main/gpt-5.6-sol, cursor/gpt-5.6-sol, anthropic/codex/gpt-5.6-sol, eai/gpt/gpt-5.6-sol, azure-foundry/gpt-5.6-sol, gpt-5.6 sol, a6/gpt-5.6-sol, auto/gpt-5.6-sol, combo/gpt-5.6-sol, gpt/gpt-5.6-sol, router_client:unknown/gpt-5.6-sol, cbai/gpt-5.6-sol

Rank
#13
by active users
Active users
217
Down 497 from 714 active users in the previous 30 days. vs previous 30 days
Adoption
23%
of 958 accounts
Tokens
207B
cache included
Est. cost
$158.3K
at public list prices
First seen
Apr 14, 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.

7 active users on Nov 12, 2026

Daily active users for GPT-5.6 Sol, Oct 14, 2026 to Nov 12, 2026. Peak 73. Use the left and right arrow keys to read each day.80400
Show daily values
Daily active users and tokens for GPT-5.6 Sol
Date (UTC)Active usersTokens
Oct 14, 20266711.3B
Oct 15, 20267320.4B
Oct 16, 20265910.4B
Oct 17, 2026495.8B
Oct 18, 2026444.5B
Oct 19, 2026635.2B
Oct 20, 20265412B
Oct 21, 20265514B
Oct 22, 2026642.6B
Oct 23, 2026567.1B
Oct 24, 20265312.2B
Oct 25, 20265213.9B
Oct 26, 2026598.7B
Oct 27, 20265126.1B
Oct 28, 20264812.6B
Oct 29, 2026483.5B
Oct 30, 2026432.7B
Oct 31, 2026384.5B
Nov 1, 2026332.1B
Nov 2, 2026365.4B
Nov 3, 2026377B
Nov 4, 2026342.4B
Nov 5, 2026313B
Nov 6, 2026332.2B
Nov 7, 2026253B
Nov 8, 2026261.4B
Nov 9, 202625703.4M
Nov 10, 2026191.1B
Nov 11, 2026191.6B
Nov 12, 2026745.2M

Token mix

How the 207B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input3.3%
  • Output0.2%
  • Cache read96%
  • Cache write<0.1%
  • Reasoning<0.1%

Agents that carry GPT-5.6 Sol

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

  1. Codex CLI63% of this model's tokens171active users
  2. Oh My Pi27% of this model's tokens21active users
  3. Prime Agent4.9% of this model's tokens1active users
  4. Senpi (OmO Native)2.2% of this model's tokens16active users
  5. Hermes Agent2.1% of this model's tokens17active users
  6. Gajae Code0.3% of this model's tokens1active users
  7. OpenCode0.2% of this model's tokens6active users
  8. Aside<0.1% of this model's tokens8active users
  9. Pi<0.1% of this model's tokens8active users
  10. ZCode<0.1% of this model's tokens3active users
  11. Copilot<0.1% of this model's tokens1active users
  12. OpenClaw<0.1% of this model's tokens2active users
  13. Synthetic<0.1% of this model's tokens1active users
  14. DeepSeek Harness<0.1% of this model's tokens3active users
  15. Claude Code<0.1% of this model's tokens3active users
  16. cc-mirror/mozilla<0.1% of this model's tokens1active users
  17. cc-mirror/curl<0.1% of this model's tokens1active users
  18. 9Router<0.1% of this model's tokens1active users

Benchmarks

The best result for GPT-5.6 Sol 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
    162.8
    Rank #11 of 160 matched modelsNo conditions reportedModel released Jul 9, 2026Source: epoch.ai (opens in a new tab)
  • Terminal-Bench 4.0Agentic coding · Terminal-Bench
    37.3%
    Rank #11 of 23 matched modelsMax · CodexPublished Aug 27, 2026Source: tbench.ai (opens in a new tab)

    Tokscale usage: Codex CLI carried 63% of GPT-5.6 Sol tokens in the last 30 days (171 active users).

  • CursorBenchAgentic coding · Cursor, collected by Epoch AI
    41.7%
    Rank #10 of 18 matched modelsMaxModel released Jul 9, 2026Source: cursor.com (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as GPT-5.6 Sol Extra High
      37.7%
      XHighModel released Jul 9, 2026Source: cursor.com (opens in a new tab)
    • Listed as GPT-5.6 Sol High
      35.7%
      HighModel released Jul 9, 2026Source: cursor.com (opens in a new tab)
    • Listed as GPT-5.6 Sol Medium
      31.1%
      MediumModel released Jul 9, 2026Source: cursor.com (opens in a new tab)
    • Listed as GPT-5.6 Sol Low
      24.6%
      LowModel released Jul 9, 2026Source: cursor.com (opens in a new tab)
  • DeepSWEAgentic coding · Datacurve, collected by Epoch AI
    72.7%
    Rank #4 of 26 matched modelsMax · mini-swe-agentModel released Jul 9, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    Show 4 more results with other run conditionsHide the other results
    • Listed as gpt-5-6-sol (xhigh)
      70.7%
      XHigh · mini-swe-agentModel released Jul 9, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as gpt-5-6-sol (high)
      69.4%
      High · mini-swe-agentModel released Jul 9, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as gpt-5-6-sol (medium)
      61.1%
      Medium · mini-swe-agentModel released Jul 9, 2026Source: deepswe.datacurve.ai (opens in a new tab)
    • Listed as gpt-5-6-sol (low)
      45.4%
      Low · mini-swe-agentModel released Jul 9, 2026Source: deepswe.datacurve.ai (opens in a new tab)
  • FrontierSWEAgentic coding · FrontierSWE, collected by Epoch AI
    32.2%
    Rank #9 of 21 matched modelsMax · proximusModel released Jul 9, 2026Source: frontierswe.com (opens in a new tab)
  • WebDev ArenaWeb development · LMArena
    1,616
    Rank #24 of 110 matched modelsXHigh · CodexPublished Oct 19, 2026Source: huggingface.co (opens in a new tab)

    Tokscale usage: Codex CLI carried 63% of GPT-5.6 Sol tokens in the last 30 days (171 active users).

  • Agent ArenaAgents · LMArena
    +0.07
    Rank #10 of 48 matched modelsXHigh · Arena Agent ModePublished Oct 19, 2026Source: huggingface.co (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    93.5%
    Rank #15 of 151 matched modelsMaxRun date Jul 9, 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-5.6-sol_low
      89.9%
      LowRun date Aug 7, 2026Source: epoch.ai (opens in a new tab)
    • Listed as gpt-5.6-sol_none
      82.8%
      No reasoningRun date Aug 7, 2026Source: epoch.ai (opens in a new tab)
  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    89.1%
    Rank #6 of 86 matched modelsMaxRun 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
    69.7%
    Rank #9 of 80 matched modelsMaxRun date Aug 10, 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 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
$0.58
Est. per 1M tokens
96% cache reads
At the community mix
$0.61
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$8
Per 1M tokens at list prices
No cache

Cache reads were 96% of GPT-5.6 Sol 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 $4, output $20, cache read $0.40, cache write $5.
  • 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.

List prices by provider

  • OpenAIReferencegpt-5.6-sol
    $4 input per 1M tokens$20 output per 1M tokens$0.40 cache read per 1M tokens$5 cache write per 1M tokens1.05M tokens of context
  • Amazon Bedrockopenai.gpt-5.6-sol
    $4.40 input per 1M tokens$22 output per 1M tokens$0.44 cache read per 1M tokens$5.50 cache write per 1M tokens1.05M tokens of context
  • Azuregpt-5.6-sol
    $4 input per 1M tokens$20 output per 1M tokens$0.40 cache read per 1M tokens$5 cache write per 1M tokens1.05M tokens of context
  • OpenRouteropenai/gpt-5.6-sol
    $4 input per 1M tokens$20 output per 1M tokens$0.40 cache read per 1M tokens$5 cache write per 1M tokens1.05M tokens of context
  • Vercel AI Gatewayopenai/gpt-5.6-sol
    $4 input per 1M tokens$20 output per 1M tokens$0.40 cache read per 1M tokens$5 cache write per 1M tokens1.05M 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
Feb 16, 2026
Release date
Jul 9, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GPT-5.6 Sol most in this period, by tokens. Hidden accounts are never listed.

  1. 1szymonsec@szymonsec64.2Btokens$55.8Kest. cost16active days$55.8K est. cost · 16 active days
  2. 2Kabir Acharya@KabirAcharya37.5Btokens$19.9Kest. cost20active days$19.9K est. cost · 20 active days
  3. 3Junho Yeo@junhoyeo10.1Btokens$13.2Kest. cost15active days$13.2K est. cost · 15 active days
  4. 4Waivey Kim@waiveyk7.8Btokens$4.2Kest. cost10active days$4.2K est. cost · 10 active days
  5. 5Guanzheng Wei@GuanZhengPM7.6Btokens$8.8Kest. cost29active days$8.8K est. cost · 29 active days
  6. 6Khaliq@khaliqgant6.2Btokens$3.1Kest. cost25active days$3.1K est. cost · 25 active days
  7. 7joonyeonglim@joonyeonglim5.4Btokens$3.2Kest. cost15active days$3.2K est. cost · 15 active days
  8. 8Kim Jin-Yeong@jinzer05.4Btokens$4.1Kest. cost24active days$4.1K est. cost · 24 active days
  9. 9Wooseok Sung@MercuriusDream4.9Btokens$2.7Kest. cost6active days$2.7K est. cost · 6 active days
  10. 10harris.dev@harrisrobin4.7Btokens$2.7Kest. cost14active days$2.7K est. cost · 14 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.
  • 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