gpt-oss-20b

Overview

OpenAI's open-weight 21B Mixture-of-Experts model (3.6B active parameters), released under Apache 2.0. Built for low-latency, high-throughput inference, it runs comfortably on a single GPU and handles classification, extraction, routing and short-form summarization well above its size class. That combination has made it one of the most-used budget models on the platform. LLMRouteHub spreads traffic across 14 providers for the lowest live price and automatic failover, so it's a sensible default whenever you need 'good enough' quality at the lowest cost per token.

Benchmarks

Standardized scores (0–100), normalized across the catalog.

Providers

LLMRouteHub routes to the cheapest healthy provider by default. Showing the top 5 of 14 providers by routed volume.

Use this model

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