GPT-6.1 Terra

OpenAIKey gpt-6.1-terraAlso reported as owo/gpt-6.1-terra, codex/gpt-6.1-terra, auto/gpt-6.1-terra, p2bc7fb/gpt-6.1-terra, main/gpt-6.1-terra, openai/gpt-6.1-terra, p2d5835/gpt-6.1-terra, nexavlinks/gpt-6.1-terra, s2a-codex/gpt-6.1-terra

Rank
#9
by active users
Active users
136
Down 66 from 202 active users in the previous 7 days. vs previous 7 days
Adoption
22%
of 610 accounts
Tokens
94.1B
cache included
Est. cost
$6.3K
at public list prices
First seen
Aug 21, 2026
in any submission

Nov 6–12, 2026 (UTC)610 accounts100% of tokens from an identified modelData through Nov 12, 2026, 07:55 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

17 active users on Nov 12, 2026

Daily active users for GPT-6.1 Terra, Nov 6, 2026 to Nov 12, 2026. Peak 81. Use the left and right arrow keys to read each day.100500
Show daily values
Daily active users and tokens for GPT-6.1 Terra
Date (UTC)Active usersTokens
Nov 6, 20268129.2B
Nov 7, 20266415.1B
Nov 8, 20265622B
Nov 9, 20267112.2B
Nov 10, 2026547.2B
Nov 11, 2026378B
Nov 12, 202617373M

Token mix

How the 94.1B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input1.2%
  • Output0.1%
  • Cache read99%
  • Cache write<0.1%
  • Reasoning<0.1%

Agents that carry GPT-6.1 Terra

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

  1. Codex CLI82% of this model's tokens110active users
  2. Claude Code8.8% of this model's tokens3active users
  3. Oh My Pi3.5% of this model's tokens6active users
  4. OpenCode3.5% of this model's tokens8active users
  5. Pi1.3% of this model's tokens5active users
  6. Senpi (OmO Native)0.8% of this model's tokens4active users
  7. Hermes Agent0.3% of this model's tokens10active users
  8. DeepSeek Harness<0.1% of this model's tokens1active users
  9. Aside<0.1% of this model's tokens5active users
  10. Junie<0.1% of this model's tokens1active users

Benchmarks

The best result for GPT-6.1 Terra 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
    167.7
    Rank #6 of 158 matched modelsNo conditions reportedModel released Oct 26, 2026Source: epoch.ai (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    94.3%
    Rank #10 of 160 matched modelsMaxRun date Oct 26, 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.

  • FrontierMath Tiers 1–3 (v2)Reasoning · Epoch AI
    90.9%
    Rank #5 of 90 matched modelsMaxRun date Oct 26, 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.

  • SimpleQA VerifiedKnowledge · Epoch AI
    57.3%
    Rank #22 of 86 matched modelsMaxRun date Oct 26, 2026Source: epoch.ai (opens in a new tab)

Not evaluated: Humanity's Last Exam, Terminal-Bench 4.1, CursorBench, DeepSWE, FrontierSWE, Agent Arena, WebDev 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
$0.07
Est. per 1M tokens
99% cache reads
At the community mix
$0.10
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$2
Per 1M tokens at list prices
No cache

Cache reads were 99% of GPT-6.1 Terra tokens in the last 7 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 $1, output $5, cache read $0.05, cache write $1.25.
  • This model's mix is its own input, output, cache and reasoning tokens in the last 7 days.
  • The community mix is the tokens of every identified model in the last 7 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-6.1-terra
    $1 input per 1M tokens$5 output per 1M tokens$0.05 cache read per 1M tokens$1.25 cache write per 1M tokens1.05M tokens of context
  • Amazon Bedrockopenai.gpt-6.1-terra
    $1.10 input per 1M tokens$5.50 output per 1M tokens$0.06 cache read per 1M tokens$1.38 cache write per 1M tokens1.05M tokens of context
  • Azuregpt-6.1-terra
    $1 input per 1M tokens$5 output per 1M tokens$0.05 cache read per 1M tokens$1.25 cache write per 1M tokens1.05M tokens of context
  • OpenRouteropenai/gpt-6.1-terra
    $1 input per 1M tokens$5 output per 1M tokens$0.05 cache read per 1M tokens$1.25 cache write per 1M tokens1.05M tokens of context
  • Vercel AI Gatewayopenai/gpt-6.1-terra
    $1 input per 1M tokens$5 output per 1M tokens$0.05 cache read per 1M tokens$1.25 cache write per 1M tokens1.05M 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
1.05M tokens
Max output
128K tokens
Input
Text, Image, PDF
Output
Text
Knowledge cutoff
Jun 1, 2026
Release date
Oct 26, 2026
Open weights
No
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GPT-6.1 Terra most in this period, by tokens. Hidden accounts are never listed.

  1. 1Yoginth@bigint21Btokens$1.2Kest. cost3active days$1.2K est. cost · 3 active days
  2. 2Chubby Person@BenLampson9Btokens$561est. cost4active days$561 est. cost · 4 active days
  3. 3super244@super2448.8Btokens$489est. cost2active days$489 est. cost · 2 active days
  4. 4Christopher Butler@techsaint8.3Btokens$584est. cost6active days$584 est. cost · 6 active days
  5. 5joonyeonglim@joonyeonglim5.8Btokens$365est. cost7active days$365 est. cost · 7 active days
  6. 6AnganSamadder@AnganSamadder4.4Btokens$262est. cost6active days$262 est. cost · 6 active days
  7. 7Raxxoor@dhaern3Btokens$242est. cost6active days$242 est. cost · 6 active days
  8. 8Sunghyun Kim@hellosunghyun2.7Btokens$158est. cost5active days$158 est. cost · 5 active days
  9. 9ben@0thernet2.2Btokens$69est. cost5active days$69 est. cost · 5 active days
  10. 10준권 @elppaaa2.2Btokens$166est. cost5active days$166 est. cost · 5 active days

More from OpenAI

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

  1. GPT-6.1 Sol57% adoption350active users
  2. GPT-6 Astra44% adoption267active users
  3. GPT-6 Luna25% adoption154active users
  4. Codex Auto Review18% adoption112active users
  5. GPT-5.6 Sol10% adoption61active users
  6. GPT-6 Sol8.7% adoption53active 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.
  • 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