gpt-oss-20b

by openai

OpenAI’s 21B-parameter open-weight Mixture-of-Experts (MoE) model, released under the Apache 2.0 license. Features 3.6B active parameters per forward pass, optimized for low-latency inference and deployability on consumer or single-GPU hardware. Trained in OpenAI’s Harmony response format, it supports reasoning level configuration, fine-tuning, and agentic capabilities such as function calling and structured outputs.

Pricing

Pay-as-you-go rates for this model. More details can be found here.

Input Tokens (1M)

$0.02

Output Tokens (1M)

$0.10

Capabilities

Input Modalities

Text
File

Output Modalities

Text

Rate Limits

Requests per minute (RPM) and per day (RPD) by tier. More about tiers here

TierRPMRPD
Free
Tier 110
Tier 215
Tier 325
Tier 450

Usage Analytics

Token usage across the last 30 active days

gpt-oss-20b — Model | NagaAI