GPT OSS 20B

OpenAIKey gpt-oss-20bAlso reported as openai/gpt-oss-20b, gpt-oss:20b, @cf/openai/gpt-oss-20b, ollama/gpt-oss:20b, workers-ai/@cf/openai/gpt-oss-20b

Rank: #351; by active users
Active users: 2; No change from 2 active users in the previous 30 days. vs previous 30 days
Adoption: 0.2%; of 960 accounts
Tokens: 1.1M; cache included
Est. cost: —; at public list prices
First seen: Aug 19, 2025; in any submission

Oct 14 – Nov 12, 2026 (UTC)960 accounts100% of tokens from an identified modelData through Nov 12, 2026, 04:57 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 OSS 20B, 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 OSS 20B
Date (UTC)	Active users	Tokens
Oct 14, 2026	1	1.1M
Oct 15, 2026	0	0
Oct 16, 2026	0	0
Oct 17, 2026	0	0
Oct 18, 2026	0	0
Oct 19, 2026	0	0
Oct 20, 2026	0	0
Oct 21, 2026	0	0
Oct 22, 2026	0	0
Oct 23, 2026	0	0
Oct 24, 2026	0	0
Oct 25, 2026	0	0
Oct 26, 2026	0	0
Oct 27, 2026	0	0
Oct 28, 2026	0	0
Oct 29, 2026	0	0
Oct 30, 2026	1	25.8K
Oct 31, 2026	0	0
Nov 1, 2026	0	0
Nov 2, 2026	0	0
Nov 3, 2026	0	0
Nov 4, 2026	0	0
Nov 5, 2026	0	0
Nov 6, 2026	0	0
Nov 7, 2026	0	0
Nov 8, 2026	0	0
Nov 9, 2026	0	0
Nov 10, 2026	0	0
Nov 11, 2026	0	0
Nov 12, 2026	0	0

Token mix

How the 1.1M tokens split. Cache reads are usually most of an agent's tokens and are priced far below input.

Input99%
Output0.5%
Cache read0%
Cache write0%
Reasoning<0.1%

Agents that carry GPT OSS 20B

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

LM Studio98% of this model's tokens1active users
OpenCode2.3% of this model's tokens1active users

Benchmarks

The best result for GPT OSS 20B 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
135.0
Epoch Capabilities Index: 135.0
Model
GPT OSS 20B
Listed as
gpt-oss-20b
Conditions
Not reported
Interval
132.3–137.5
Unit
ECI
Model released
Aug 5, 2025
Retrieved
Nov 12, 2026
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
Rank #131 of 158 matched modelsNo conditions reportedModel released Aug 5, 2025Source: epoch.ai (opens in a new tab)
GPQA DiamondReasoning · Epoch AI
60.8%
GPQA Diamond: 60.8%
Model
GPT OSS 20B
Listed as
gpt-oss-20b_medium
Conditions
Medium
Unit
% correct
Run date
Aug 27, 2026
Retrieved
Nov 12, 2026
Best of 3 reported results for this model.
Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
Rank #122 of 160 matched modelsMediumRun date Aug 27, 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.
Show 2 more results with other run conditionsHide the other results
- Listed as gpt-oss-20b_low
  53.2%
  GPQA Diamond: 53.2%
  Model
  GPT OSS 20B
  Listed as
  gpt-oss-20b_low
  Conditions
  Low
  Unit
  % correct
  Run date
  Aug 27, 2026
  Retrieved
  Nov 12, 2026
  Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
  LowRun date Aug 27, 2026Source: epoch.ai (opens in a new tab)
- Listed as gpt-oss-20b_high
  46.0%
  GPQA Diamond: 46.0%
  Model
  GPT OSS 20B
  Listed as
  gpt-oss-20b_high
  Conditions
  High
  Unit
  % correct
  Run date
  Aug 6, 2026
  Retrieved
  Nov 12, 2026
  Source · Epoch AI, ‘Capabilities & benchmarking’, epoch.ai/benchmarks (CC BY 4.0)
  HighRun date Aug 6, 2026Source: epoch.ai (opens in a new tab)

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: $0.07; Est. per 1M tokens
0% cache reads
At the community mix: $0.07; Est. per 1M tokens
96% cache reads
3:1 input/output blend: $0.13; Per 1M tokens at list prices
No cache

Cache reads were 0% of GPT OSS 20B 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 $0.07, output $0.30.
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-20b
$0.07 input per 1M tokens$0.30 output per 1M tokensCache read not listedCache write not listed131K tokens of context
OpenRouteropenai/gpt-oss-20b
$0.03 input per 1M tokens$0.13 output per 1M tokens$0.03 cache read per 1M tokensCache write not listed131K tokens of context
Vercel AI Gatewayopenai/gpt-oss-20b
$0.03 input per 1M tokens$0.14 output per 1M tokensCache read not listedCache write not listed131K tokens of context
Deep Infraopenai/gpt-oss-20b
$0.03 input per 1M tokens$0.14 output per 1M tokensCache read not listedCache write not listed131K tokens of context
Groqopenai/gpt-oss-20b
$0.07 input per 1M tokens$0.30 output per 1M tokens$0.04 cache read per 1M tokensCache write not listed131K 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: 118K 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 20B most in this period, by tokens. Hidden accounts are never listed.

1seoyoung@b1ueseoyoung1.1Mtokens—est. cost1active daysno price · 1 active days
2Mark Tielemans@MarkTielemans25.8Ktokens—est. cost1active daysno price · 1 active days

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

GPT-6.1 Sol69% adoption663active users
GPT-6 Astra59% adoption564active users
GPT-6 Luna45% adoption434active users
Codex Auto Review30% adoption289active users
GPT-6.1 Terra28% adoption271active users
GPT-6 Sol26% adoption247active 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