GPT OSS 20B · deepinfra

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 lower-latency inference. The model is trained in OpenAI’s Harmony response format and supports reasoning level configuration, fine-tuning, and agentic capabilities including function calling, tool use, and structured outputs.

Base modelAll models on this baseAll models of the providerto the provider

Read also: gpt-oss API pricing: gpt-oss-120b and gpt-oss-20b at every provider

All OpenAI models at every provider

Input, $/1M $0.03

Output, $/1M $0.14

Context 131 072

Max output 16 384

Accepts text

Last checked 04.11.2026 12:00:14 UTC

Source —