openai / text-generation Open weights Also via API updated 1 year ago

gpt-oss-20b

Name: gpt-oss-20b
Price: 0.03 USD
Author: openai

Welcome to the gpt-oss series, OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

Params

21.5 B

Context

131,072

Downloads 30d

5.8 M

Likes

5,292

Commercial use: allowed apache-2.0 Not gated SAFETENSORS View on Hugging Face ↗

Download history

daily snapshots · 106 days

▲ 121 K in the last 30 days (2.0%)

8.6 M5.7 M

Jul 28Sep 1Oct 6Nov 10

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
model.safetensors	u8	27.5 GB	34.0 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	27.5 GB	82.4 GB	❌ Won’t fit

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Run it

copy-paste, exact tags checked against the Hub

~ · curl · api/v1

$ curl -s https://aimodelscomparison.com/api/v1/models/gpt-oss-20b
{
  "hf_id": "openai/gpt-oss-20b",
  "params_b": 21.51,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 5830063,
  "vram_estimates": [
    { "quant": "u8", "gb": 34.0 }
  ],
  "updated_at": "2026-07-28T17:06:36Z"
}

est. VRAM —on RTX 4090 · 24 GBJSON API →

Use via API

via OpenRouter · USD per 1M tokens · synced 2026-11-10

$0.03

input / 1M

$0.13

output / 1M

$0.03

cached input / 1M

$0.16

1M in + 1M out

:batch variant $0.024 in · $0.11 out

Context window: 131,072 tokens
Max output: 117,964 tokens
Providers: 10
Cheapest provider: PrimeIntellect · $0.02 / $0.03
Best throughput: —
AA Intelligence / Coding / Agentic: — / 20.7 / 1.2

✓ Tool calling ✓ Reasoning ✓ Structured outputs ✗ Image input ✗ File input ✗ Audio input ✓ Prompt caching

Specifications

Architecture: GptOssForCausalLM
Parameters: 21.5 B
Tensor type: U8
Context length: 131,072
Vocabulary: 201,088
Layers / heads: 24 / 64
Licence: apache-2.0
First seen on the Hub: 2025-08-04
Training datasets: undisclosed
Added to our catalog: 2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.

Derivative gpt-oss-20b-GGUF unsloth 624 K Derivative gpt-oss-20b-GGUF ggml-org 356 K Derivative gpt-oss-20b-MXFP4-Q8 mlx-community 171 K Derivative GPT-OSS-20B-NPU2 FastFlowLM 140 K Derivative gpt-oss-safeguard-20b openai 22 K

Compare with any text-generation model

Popular comparisons

Qwen3-14B 12.9 M Qwen3-8B 6.8 M Qwen2.5-7B-Instruct 6.0 M dolphin-2.9.1-yi-1.5-34b 4.8 M Qwen3.6-35B-A3B-NVFP4 4.0 M OTel-2.0-Decision-26B-A4B-4bit 3.2 M

Appears in

Commercial-use text models