GPT OSS 120B

OpenAIKey gpt-oss-120bAlso reported as openai/gpt-oss-120b, gpt-oss:120b, hyper/gpt-oss-120b, alcf-metis/gpt-oss-120b, alcf-minerva/gpt-oss-120b, ollama/gpt-oss:120b, openrouter/openai/gpt-oss-120b, mlx-community/gpt-oss-120b, @cf/openai/gpt-oss-120b, alcf-sophia/openai/gpt-oss-120b

Rank
#153
by active users
Active users
5
Down 2 from 7 active users in the previous 30 days. vs previous 30 days
Adoption
0.5%
of 967 accounts
Tokens
8.1B
cache included
Est. cost
$630
at public list prices
First seen
Aug 7, 2025
in any submission

Oct 15 – Nov 13, 2026 (UTC)967 accounts100% of tokens from an identified modelData through Nov 13, 2026, 07:02 UTCHow we count

Daily active users

Distinct accounts that used this model on each UTC day.

0 active users on Nov 13, 2026

Daily active users for GPT OSS 120B, Oct 15, 2026 to Nov 13, 2026. Peak 2. Use the left and right arrow keys to read each day.210
Show daily values
Daily active users and tokens for GPT OSS 120B
Date (UTC)Active usersTokens
Oct 15, 20261150K
Oct 16, 202600
Oct 17, 202600
Oct 18, 202600
Oct 19, 202600
Oct 20, 202600
Oct 21, 20261170K
Oct 22, 202600
Oct 23, 202600
Oct 24, 202600
Oct 25, 202600
Oct 26, 20261193.9M
Oct 27, 20261460.7M
Oct 28, 20262246.5M
Oct 29, 2026166.5M
Oct 30, 20261614.3M
Oct 31, 202611.5B
Nov 1, 20261894M
Nov 2, 20261364.5M
Nov 3, 20261488.9M
Nov 4, 20261643M
Nov 5, 202611.9B
Nov 6, 20261628.1M
Nov 7, 202618K
Nov 8, 2026117.2K
Nov 9, 2026148.5K
Nov 10, 202600
Nov 11, 202611.2M
Nov 12, 20261103.2M
Nov 13, 202600

Token mix

How the 8.1B tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

  • Input27%
  • Output3.3%
  • Cache read70%
  • Cache write0%
  • Reasoning<0.1%

Agents that carry GPT OSS 120B

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

  1. Pi40% of this model's tokens2active users
  2. Synthetic35% of this model's tokens1active users
  3. Oh My Pi25% of this model's tokens3active users
  4. OpenCode<0.1% of this model's tokens2active users

Benchmarks

The best result for GPT OSS 120B 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
    140.2
    Rank #117 of 158 matched modelsNo conditions reportedModel released Aug 5, 2025Source: epoch.ai (opens in a new tab)
  • GPQA DiamondReasoning · Epoch AI
    75.8%
    Rank #102 of 160 matched modelsHighRun date Dec 11, 2025Source: 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.

Not evaluated: Humanity's Last Exam, FrontierMath Tiers 1–3 (v2), SimpleQA Verified, 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. Amazon Bedrock is the reference price for the estimates below. It is the first provider listed; models.dev lists no price from the lab's own API.

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
$0.16
Est. per 1M tokens
70% cache reads
At the community mix
$0.15
Est. per 1M tokens
96% cache reads
3:1 input/output blend
$0.26
Per 1M tokens at list prices
No cache

Cache reads were 70% of GPT OSS 120B 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

  • Amazon Bedrock list prices per 1M tokens: input $0.15, output $0.60.
  • 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-read price is listed, so cache reads are priced as input.
  • No cache-write price is listed, so cache writes are priced as input.

List prices by provider

  • Amazon BedrockReferenceopenai.gpt-oss-120b
    $0.15 input per 1M tokens$0.60 output per 1M tokensCache read not listedCache write not listed131K tokens of context
  • Vertexopenai/gpt-oss-120b-maas
    $0.09 input per 1M tokens$0.36 output per 1M tokensCache read not listedCache write not listed131K tokens of context
  • OpenRouteropenai/gpt-oss-120b
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed131K tokens of context
  • Vercel AI Gatewayopenai/gpt-oss-120b
    $0.10 input per 1M tokens$0.50 output per 1M tokens$0.10 cache read per 1M tokensCache write not listed131K tokens of context
Show 5 more providersShow fewer providers
  • Together AIopenai/gpt-oss-120b
    $0.15 input per 1M tokens$0.60 output per 1M tokensCache read not listedCache write not listed131K tokens of context
  • Deep Infraopenai/gpt-oss-120b
    $0.04 input per 1M tokens$0.17 output per 1M tokensCache read not listedCache write not listed131K tokens of context
  • Groqopenai/gpt-oss-120b
    $0.15 input per 1M tokens$0.60 output per 1M tokens$0.07 cache read per 1M tokensCache write not listed131K tokens of context
  • Cerebrasgpt-oss-120b
    $0.35 input per 1M tokens$0.75 output per 1M tokens$0.35 cache read per 1M tokensCache write not listed131K tokens of context
  • Basetenopenai/gpt-oss-120b
    $0.10 input per 1M tokens$0.50 output per 1M tokens$0.10 cache read per 1M tokensCache write not listed128K 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
131K tokens
Max output
41K tokens
Input
Text
Output
Text
Knowledge cutoff
Jun 2024
Release date
Aug 5, 2025
Open weights
Yes
Reasoning
Yes
Tool calling
Yes

Top public profiles

Public profiles that used GPT OSS 120B most in this period, by tokens. Hidden accounts are never listed.

  1. 1SeaL773@SeaL7738.1Btokens$630est. cost14active days$630 est. cost · 14 active days
  2. 2Joosung Park@hyperlapse122218Ktokens<$1est. cost2active days<$1 est. cost · 2 active days
  3. 3Anand Kamble@anand-kamble150Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
  4. 4Emmanuel Olowe@isEmmanuelOlowe128Ktokens<$1est. cost1active days<$1 est. cost · 1 active days
  5. 5Zenco@notzenco25.2Ktokens—est. cost2active daysno price · 2 active days

More from OpenAI

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

  1. GPT-6.1 Sol70% adoption675active users
  2. GPT-6 Astra59% adoption575active users
  3. GPT-6 Luna45% adoption439active users
  4. Codex Auto Review30% adoption292active users
  5. GPT-6.1 Terra29% adoption285active users
  6. GPT-6 Sol25% adoption245active 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