GPT OSS 20B
GPT OSS 20B is OpenAI's smaller open-weight model with roughly 21 billion total parameters and 3.6 billion active per token, designed for low-latency, agentic, and on-device workloads.
ReasoningTool Use
index.ts
import { streamText } from 'ai'
const result = streamText({ model: 'openai/gpt-oss-20b', prompt: 'Why is the sky blue?'})Providers
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
| Provider |
|---|
 Amazon Bedrock | 128K | 0.3s | 325tps | $0.07/M | $0.30/M | — | — | 08/05/2025 | ||||
 Fireworks | 128K | 1.0s | 50tps | $0.07/M | $0.30/M | Read:$0.04/M Write:— | — | — | +1 | 08/05/2025 | ||
 Groq | 131K | 0.6s | 915tps | $0.07/M | $0.30/M | Read:$0.04/M Write:— | — | — | +1 | 08/05/2025 | ||
 DeepInfra | 131K | 0.6s | 157tps | $0.03/M | $0.14/M | — | — | 08/05/2025 | ||||
 Together AI | 131K | 0.3s | 102tps | $0.05/M | $0.20/M | — | — | 08/05/2025 | ||||
 Novita AI | 131K | 0.6s | 126tps | $0.04/M | $0.15/M | — | — | 08/05/2025 | ||||
 Parasail | 131K | $0.04/M | $0.20/M | — | — | 08/05/2025 |