Back to Models Directory
OpenAIgpt-oss-20b

OpenAI: gpt-oss-20b API Pricing

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, opti...

Base Input Price$0.030/ 1M tokens
Base Output Price$0.13/ 1M tokens
Prompt Cache Read$0.030-0% discount
Batch API Rate-20%24h async offload

Inference Hosts & Aggregator Providers

Compare rates and latency across direct APIs, OpenRouter, and hyperscale cloud providers

Live verified rates
Provider NameInput / 1MOutput / 1MPrompt CachingAccess Endpoint
OpenAI Direct$0.030$0.13Not availableConnect
OpenRouter$0.030$0.13Not availableConnect