GPT OSS 20B

Overview

The gpt-oss-20b model (technically 20.9B parameters) achieves near-parity with OpenAI o4-mini on core reasoning benchmarks, while running efficiently on a single 80 GB GPU. The gpt-oss-20b model delivers similar results to OpenAI o3‑mini on common benchmarks and can run on edge devices with just 16 GB of memory, making it ideal for on-device use cases, local inference, or rapid iteration without costly infrastructure. Both models also perform strongly on tool use, few-shot function calling, CoT reasoning (as seen in results on the Tau-Bench agentic evaluation suite) and HealthBench (even outperforming proprietary models like OpenAI o1 and GPT‑4o). Note: While referred to as '20b' for simplicity, it technically has 20.9B parameters.

GPT OSS 20B was released on August 5, 2025. API access is available through 4 providers, including Novita, Fireworks and others.

Benchmarks

GPT OSS 20B Performance Across Datasets

Scores sourced from the model's scorecard, paper, or official blog posts

llm-stats.com - Fri Dec 26 2025

Pricing

Pricing, performance, and capabilities for GPT OSS 20B across different providers:

Provider	Input ($/M)	Output ($/M)	Max Input	Max Output	Latency (s)	Throughput	Quantization	Input	Output
Novitabf16	$0.05	$0.20	131.1K	32.8K	—	—	bf16	Text Image Audio Video	Text Image Audio Video
Fireworks	$0.10	$0.50	131.0K	30.0K	—	—	—	Text Image Audio Video	Text Image Audio Video
Groq	$0.10	$0.50	131.0K	30.0K	0.38	1000 tok/s	—	Text Image Audio Video	Text Image Audio Video
OpenAI	$0.10	$0.50	131.1K	131.1K	5.2	115.0 tok/s	—	Text Image Audio Video	Text Image Audio Video

Price Comparison for GPT OSS 20B

Price per 1M input tokens (USD), lower is better

llm-stats.com - Fri Dec 26 2025

Throughput Comparison for GPT OSS 20B

Tokens per second, higher is better

llm-stats.com - Fri Dec 26 2025

Latency Comparison for GPT OSS 20B

Time to first token (s), lower is better

llm-stats.com - Fri Dec 26 2025

API Access