Back to Models

gpt-oss-20B (high)

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI
24/ 57

Intelligence Score

Intelligence

24

#106 of 212 (top 50%)

Speed

296 tok/s

#6 of 141

Price

$0.09

per M tokens

#11 cheapest of 142

Context Window

131K

tokens

Latency: 1ms (#12)

Score Breakdown

Quality Score40%
Speed Score38%
Cost Score99%

Similar Models

gpt-oss-120B (low)

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

24intelligence

GPT-5.4 nano

![OpenAI](https://artificialanalysis.ai/img/logos/openai_small.svg)OpenAI

24intelligence

NVIDIA Nemotron 3 Nano

![NVIDIA](https://artificialanalysis.ai/img/logos/nvidia_small.svg)NVIDIA

24intelligence

LongCat Flash Lite

![LongCat](https://artificialanalysis.ai/img/logos/longcat_small.svg)LongCat

24intelligence

Grok 4.1 Fast

![xAI](https://artificialanalysis.ai/img/logos/xai.svg)xAI

24intelligence

Use This Model

Claude Code

claude --model gpt-oss-20b

API (cURL)

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

Vercel AI SDK

import { generateText } from "ai";
import { openrouter } from "@openrouter/ai-sdk-provider";

const { text } = await generateText({
  model: openrouter("gpt-oss-20b"),
  prompt: "Hello",
});
Back to Models