token.app › OpenAI › gpt-oss-20b (free)

gpt-oss-20b (free) pricing & benchmarks

gpt-oss-20b (free) is available from OpenAI at Free per million input tokens and Free per million output tokens (Free blended at 3:1). It accepts up to 131,072 tokens of context. 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...

Pricing

Per million tokens · OpenRouter

InputFree

OutputFree

Blended (3:1)Free

Specification

openai/gpt-oss-20b:free

Context window131K

Max output33K

ReleasedAug 2025

LicenceOpen weights

Modalitiesin:text, out:text

No independently-run benchmark scores are published for gpt-oss-20b (free) yet. We show nothing rather than reprinting an unverified figure.

Compare gpt-oss-20b (free)

gpt-oss-20b (free) vs Qwen3.8 Max gpt-oss-20b (free) vs DeepSeek V4 Flash 0731 gpt-oss-20b (free) vs Claude Opus 5 gpt-oss-20b (free) vs Gemini 3.6 Flash gpt-oss-20b (free) vs Kimi K3 gpt-oss-20b (free) vs Grok 4.5 gpt-oss-20b (free) vs Claude Sonnet 5 gpt-oss-20b (free) vs GLM 5.2

FAQ

How much does gpt-oss-20b (free) cost?

gpt-oss-20b (free) costs Free per million input tokens and Free per million output tokens on OpenRouter. At a 3:1 input:output mix that blends to Free per million tokens.

What is gpt-oss-20b (free)'s context window?

gpt-oss-20b (free) accepts up to 131,072 tokens of context, and can generate up to 32,768 output tokens.