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

gpt-oss-120b

Name: gpt-oss-120b
Price: 0.15 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

120.4 B

Context

131,072

Downloads 30d

2.4 M

Likes

5,501

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

Download history

daily snapshots · 106 days

▲ 1.4 M in the last 30 days (37.1%)

5.5 M2.4 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	130.5 GB	162.1 GB	❌ Won’t fit
model.safetensors (bf16, full)	bf16 + 128K ctx	130.5 GB	433.0 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-120b
{
  "hf_id": "openai/gpt-oss-120b",
  "params_b": 120.41,
  "context_length": 131072,
  "license": { "id": "apache-2.0", "commercial": "yes" },
  "downloads_30d": 2417644,
  "vram_estimates": [
    { "quant": "u8", "gb": 162.1 }
  ],
  "updated_at": "2026-07-28T17:06:58Z"
}

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

Use via API

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

$0.15

input / 1M

$0.60

output / 1M

$0.075

cached input / 1M

$0.75

1M in + 1M out

:batch variant $0.03 in · $0.14 out

Context window: 131,072 tokens
Max output: 65,536 tokens
Providers: 22
Cheapest provider: PrimeIntellect · $0.04 / $0.085
Best throughput: —
AA Intelligence / Coding / Agentic: 3.8 / 30.4 / 3.7

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

Specifications

Architecture: GptOssForCausalLM
Parameters: 120.4 B
Tensor type: U8
Context length: 131,072
Vocabulary: 201,088
Layers / heads: 36 / 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-120b-GGUF ggml-org 306 K Derivative gpt-oss-120b-Eagle3-short-context nvidia 195 K

Compare with any text-generation model

Popular comparisons

dolphin-2.9.1-yi-1.5-34b 4.8 M DeepSeek-V4-Flash-0731 2.7 M GLM-4.5-Air 1.3 M DeepSeek-V4-Flash 1.2 M NVIDIA-Nemotron-3-Super-120B-A12B-BF16 1.0 M Ornith-1.5-122B-GGUF 871 K