gpt-oss-20b

openai/gpt-oss-20b

Open GPT reasoning model for self-hosted agents and controllable deployments

Compare

Context window: 131K
Input: Text
Output: Text
Released: 2025-08-05

Max output: 131K
Knowledge cutoff: 2024-06-30
Model parameters: 22B
Active parameters: 3.6B
Weights: Open
License: apache-2.0
Capabilities: Open weight, Reasoning, Structured, Temperature, Tool call

Pricing

No official pricing available.

Estimate usage cost

Compare verified public prices for this exact model and region. Enter uncached input and cache usage separately. Estimates exclude unspecified fees, credits and currency conversion. Set requests to zero to estimate token charges only.

Input tokens

Output tokens

Cache read tokens

Cache write tokens

Requests

Context tokens (optional)

Currency

Batch processing

Performance

Overall capability

40.4/100

Coding: 38.4
Reasoning: 39.4
Professional work: 30.1
Knowledge & language: 32.5


Terminal-Bench 4.0 (AA rerun)gpt-oss-20b (High)	Coding	Artificial Analysis	2026-11-05
AutomationBench-AAgpt-oss-20b (High)	Professional work	Artificial Analysis	2026-11-05
GDPval-AA	Professional work	Artificial Analysis	2026-11-05
Humanity’s Last Examgpt-oss-20b (High)	Reasoning	Artificial Analysis	2026-11-05
AA-Briefcase	Professional work	Artificial Analysis	2026-11-05
AA-LCRgpt-oss-20b (High)	Knowledge & language	Artificial Analysis	2026-11-05
SciCodegpt-oss-20b (High)	Coding	Artificial Analysis	2026-11-05
IFBench（Artificial Analysis）gpt-oss-20b (High)	Knowledge & language	Artificial Analysis	2026-11-05

Providers

No providers found

ModelRegistry · Catalog updated 2026-11-05