openai/gpt-oss-20b

Context

64K

Input

text

Output

text

Tool calling

Supported

About this model

GPT-OSS-20B is OpenAI's efficiency-optimized 20-billion-parameter transformer featuring architectural innovations from GPT-4. Designed for accessible deployment, it delivers 85% of GPT-OSS-120B's capability at 6× lower resource requirements. Includes sparse attention mechanisms, constitutional AI safeguards, and deterministic output options.

Compare Text Models

Input modalities

text

Accepted as model input

Providers

Available routing options for this model through OneInfer.

OpenAI

Available

Input tokens

$0.050 / 1M tokens

Output tokens

$0.200 / 1M tokens

Routing

OneInfer optimized

Thinking Machines

Available

Input tokens

$0.180 / 1M tokens

Output tokens

$0.450 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

Usage	Price
Input tokens	$0.050 / 1M tokens
Output tokens	$0.200 / 1M tokens

Performance

Published evaluation results associated with this model.

Reasoning & Knowledge

MMLU (5-shot)78.4

ARC-Challenge84.2

Big-Bench Hard75.1

GPQA42.6

Mathematical Proficiency

MATH (CoT)46.3

GSM8K88.7

Code Generation

HumanEval+72.5

Repobench-P64.8

Safety & Alignment

ToxiGen Bias Score91.8

Harmful Query Rejection95.3

API example

Refer Documentation

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $ONEINFER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-oss-20b",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'