gpt-oss-20b

OpenAI · openai/gpt-oss-20b

← Back to leaderboard

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...

gpt-oss-20b ranks #61 of 348 models in the default AI Benchmark Hub order (quality first, then cost). At $0.08 blended per million tokens, it is cheaper than 94% of models with published API pricing. Its 131,072-token context window is 2.0× smaller than the catalog median (262,144 tokens).

open weightstexttext->text

Context

Max context: 131072
Max output: 117964

Pricing

Input / 1M: 0.03
Output / 1M: 0.13
Blend / 1M: 0.08

Quality

Quality index:

Provider

Provider: OpenAI
Moderated: no

Monthly cost at this blended rate

Estimated API spend if every token is billed at $0.08per million (the blend of this model's input and output prices). Real bills depend on the input/output mix.

Tokens / monthEst. cost (USD)
1,000,000$0.08
10,000,000$0.80
100,000,000$8.00

Related models

Same lab, similar price, or similar quality — useful next comparisons.

More from OpenAI

Closest API price