OpenAI

gpt-oss-20b

Released 2025-08-05 · Knowledge up to 2024-06-30

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...

You send / 1M

$0.018

tokens in

It replies / 1M

$0.090

tokens out

Memory

131K

tokens it can read at once

Typical request

$0.0001

1,000 words in, 400 out

Data privacy

No training or retention: Yes. At least one provider serves it with zero data retention.

ProviderYou send / 1MIt replies / 1MUptimePrivacy policy
AkashML · fp4$0.020$0.100100%Read
CoreWeave · fp4$0.030$0.130100%Read
DekaLLM · bf16$0.029$0.14098%Read
DeepInfra · bf16$0.030$0.14099%Read
Amazon Bedrock$0.070$0.150100%Read
Amazon Bedrock$0.070$0.150100%Read
Parasail · fp4$0.030$0.15084%Read
SiliconFlow · fp8$0.040$0.18078%Read
Google$0.070$0.2500%Read
Groq$0.075$0.300100%Read

Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.

What it can do

  • Reads: text
  • Writes: text
  • Reasoning: Yes
  • Tool calling: Yes
  • Longest reply: 33K tokens
  • Repeated text is billed at $0.0090 per 1M (prompt caching)
  • Intelligence score: 10 / 100 (Artificial Analysis)

Similar models

Appears in

Estimate your monthly cost with gpt-oss-20b →