GPT OSS 20B

by OpenAI

Open source GPT 20B via AWS Bedrock (EU region)

Context window
128K
Max output
8K
Input price
$0.07 /1M
Output price
$0.30 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#198 of 505 LLMs
TierEfficient
Output speed282 tok/s
First token0.36s
Intelligence Index24.5
Coding Index18.5
Math Index89.3
MMLU-Pro
75%
GPQA Diamond
69%
Humanity's Last Exam
10%
LiveCodeBench
78%
SciCode
34%
AIME 2025
89%
IFBench
65%
Long-context reasoning
31%
Terminal-Bench Hard
11%
τ²-Bench Telecom
60%

Available routes

The same GPT OSS 20B runs on 3 different routes through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
AWS BedrockEUDefaultNo
None
PAYG$0.07$0.30
FireworksUSDefaultNo
None for open models by default — does not log or store prompt or generation data without explicit opt-in.
PAYG$0.07$0.30
GroqUSOpt-inNo
None for inference by default. Up to 30 days for abuse-monitoring / system-reliability when triggered.
PAYG$0.07$0.30

Human review: No human review

Other models from OpenAI

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
GPT OSS 20B by OpenAI — pricing, benchmarks, hosting routes | Opper AI