OpenAI

OpenAI GPT OSS 20B

openai
Chat

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.

Modalities

In / out price

$0.03 / $0.14

per 1M

Context

131K

Max output

131K

Released

Updated

Sep 19, 2026

Providers

1 route

The same model can have different pricing and privacy guarantees depending on who serves it. Only routes currently callable through AnonRouter are shown.

ProviderPrivacyInput / 1MOutput / 1MCache read / 1MContextMax outputUptimeLatencyThroughput
DeepInfraDeepInfra
Private$0.03$0.14131K131K

Privacy

2 / 4

Private routing

Private tier

  1. Anonymous
  2. Private
  3. TEE
  4. E2EE

Prompt and response content is not retained after the request. Request content is visible to the inference runtime while it is being processed. Learn more

Features

3
Streaming
Tool calling
Reasoning

Uptime

OpenAI GPT OSS 20B — AnonRouter Models