/ Models

Language models

OpenAI: gpt-oss-20b

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

Maker
Openai
Context window
131K
Max output
131K
Input / 1M
$0.03
Output / 1M
$0.13
1M in + 1M out
$0.16

Everything else

Max output131K
Input / 1M$0.03
Output / 1M$0.13
Cache read / 1M$0.03
Cache write / 1M
1M in + 1M out$0.16
Takestext
Returnstext
Toolsyes
Reasoningalways on · high, medium, low
Open weightsyes
Released2025-08-05
Knowledge cutoff2024-06-30
Retires
Catalog idopenai/gpt-oss-20b

Using it

In 00, this model is picked per agent — and per tier, so the model that answers your customers need not be the one that writes your code. Get 00.

← all models