← all models

gpt-oss-20b

openai

openrouter ollama cloud batch pricing
Parameters 20B openrouter api · from the model id
Context 128K 131072 tokens
Input $0.02 OpenRouter · cheapest output
Output $0.09 OpenRouter · cheapest output
Cache read $0.0090 OpenRouter · cheapest output

Providers

Provider In $/M Out $/M Cache $/M
Ollama cloud ollama pricing page $0.07 $0.30 $0.04
OpenRouter openrouter api $0.02 $0.09 $0.0090

Accepts

text

Capabilities

frequency_penalty include_reasoning logit_bias logprobs max_tokens min_p presence_penalty reasoning reasoning_effort repetition_penalty response_format seed stop structured_outputs temperature tool_choice tools top_k top_logprobs top_p

Description

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...

The OpenRouter API truncates descriptions — read the full text at the source

Also known as

Every id and name this model has been seen under — for matching it against another catalogue.

openrouter openai/gpt-oss-20b ollama gpt-oss:20b name OpenAI: gpt-oss-20b display name gpt-oss-20b

Identifiers

Vendor
openai
OpenRouter
openai/gpt-oss-20b
Ollama
gpt-oss:20b
Hugging Face
openai/gpt-oss-20b
Released
2025-08-05T17:17:09.000Z
First seen
59 d ago
Last crawled
16 min ago