Skip to content

gpt-oss-20b (batch)

ModelOpen sourceActive
by OpenAI · family “gpt-ossb-batch”

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... (description from the OpenRouter listing)

in: textout: textReasoningTool useStructured output
Epoch Capabilities Index
Not scored by Epoch AI
Listing ↗
Released
5 Aug 2025
Context window
131K tokens
Max output
118K tokens
Input $ / 1M tokens
$0.024
Output $ / 1M tokens
$0.11
Cached input $ / 1M
Unknown
Each benchmark shown separately with its own source

Benchmark results (0)

All benchmarks
No benchmark results recorded for this model.

Source: Epoch AI Benchmarking Hub (CC BY 4.0). “External” rows are leaderboard results Epoch collects from third parties. Best reported setting per benchmark is shown.

API list price over time

Price history

$ per 1M tokens

2 recorded prices on 2 Sep 2026 (OpenRouter listing + Internet Archive snapshots); re-read on every data refresh, most recently 7h ago. Steps show when the price changed.

Events

No events recorded yet.