Modeldex
Drag to turnCard front showing

OpenAITextPromo

gpt-oss-120b

Language model from OpenAI, 117B parameters.

openai/gpt-oss-120b
Type
Text
Quality
57 · Top 43% on the Epoch Capabilities Index
Parameters
117B (116,829,156,672)
Downloads
3.2M in the last 30 days
Likes
5.4K
Access to weights
Open download
On Hugging Face since
Aug 4, 2025
Takes in
Text
Puts out
Text
Access
Open weights
License
Apache 2.0
Rarity
Promo
Set number
623/1044
Open on Hugging FaceQuality 57Where to run it 73Race it 1090 tok/sMeet its creatureBattle Qwen3.5-0.8B

License read from the model’s Hugging Face card. Stats from OpenAI’s official Hugging Face account, refreshed daily.

How good is it?

Public leaderboard scores for gpt-oss-120b, refreshed daily from Epoch AI and LMArena.

Top 43% of the 277 models on the Epoch Capabilities Index: #120.

Quality is the share of a leaderboard’s models this one beats, from 0 to 100. Chat models are rated on Epoch AI’s Capabilities Index when it lists them, otherwise on LMArena; image and video models on LMArena’s image and video arenas.

Leaderboards

Benchmarks Epoch AI runs

Scores from Epoch AI and LMArena, licensed CC BY 4.0. Boards list models under their own names, so a close match is shown with the name it was scored under. Credits

Where to run it

63 providers sell gpt-oss-120b through an API, and 10 Hugging Face hosts serve it. Prices are per million tokens, cheapest first.

API providers

ProviderInputOutputContext
KenariFreegpt-oss-120bFreeFree131K
PendraFreegpt-oss:120bFreeFree131K
QVACFreegpt-oss-120bFreeFree131K
SyntheticCheapest paidhf:openai/gpt-oss-120b$0.10$0.10131K
DevPass (LLM Gateway)gpt-oss-120b$0.032$0.14131K
LLM Gatewayrunware/gpt-oss-120b$0.032$0.14131K
Kilo Gatewayopenai/gpt-oss-120b$0.03$0.15131K
NanoGPTopenai/gpt-oss-120b$0.03$0.15128K
Heliconegpt-oss-120b$0.04$0.16131K
CoreWeaveopenai/gpt-oss-120b$0.03$0.17131K
Show 53 more providers
ProviderInputOutputContext
OrcaRouteropenai/gpt-oss-120b$0.03$0.17131K
Deep Infraopenai/gpt-oss-120b$0.037$0.17131K
Eden AIdeepinfra/openai/gpt-oss-120b$0.037$0.17131K
Crusoeopenai/gpt-oss-120b$0.05$0.20131K
Merge Gatewayopenai/gpt-oss-120b$0.05$0.25128K
Novita AIopenai/gpt-oss-120b$0.05$0.25131K
DInferencegpt-oss-120b$0.068$0.27131K
Databricksdatabricks-gpt-oss-120b$0.072$0.28131K
Vertexopenai/gpt-oss-120b-maas$0.09$0.36131K
IO.NETopenai/gpt-oss-120b$0.04$0.40131K
OpenReasonopenai/gpt-oss-120b$0.11$0.42131K
Abacusopenai/gpt-oss-120b$0.08$0.44128K
Cortecsgpt-oss-120b$0.089$0.45131K
SiliconFlowopenai/gpt-oss-120b$0.05$0.45131K
OVHcloud AI Endpointsgpt-oss-120b$0.09$0.47131K
Basetenopenai/gpt-oss-120b$0.10$0.50128K
submodelopenai/gpt-oss-120b$0.10$0.50131K
Vercel AI Gatewayopenai/gpt-oss-120b$0.10$0.50131K
AKI.IOgpt-oss-120b$0.15$0.55128K
SCX.aigpt-oss-120b$0.17$0.55131K
SambaNovagpt-oss-120b$0.22$0.59131K
ai&openai/gpt-oss-120b$0.15$0.60131K
Amazon Bedrockopenai.gpt-oss-120b$0.15$0.60131K
FastRouteropenai/gpt-oss-120b$0.15$0.60131K
Fireworks AIaccounts/fireworks/models/gpt-oss-120b$0.15$0.60131K
FrogBotgpt-oss-120b$0.15$0.60131K
Groqopenai/gpt-oss-120b$0.15$0.60131K
Impossiblgroq/gpt-oss-120b$0.15$0.60131K
Nebius Token Factoryopenai/gpt-oss-120b$0.15$0.60131K
Neongpt-oss-120b$0.15$0.60131K
OCI Generative AIopenai.gpt-oss-120b$0.15$0.60128K
Ollama Cloudgpt-oss:120b$0.15$0.60131K
OpenRouteropenai/gpt-oss-120b$0.15$0.60131K
Pioneeropenai/gpt-oss-120b$0.15$0.60131K
Scalewaygpt-oss-120b$0.15$0.60128K
Tempr Gatewaygroq/openai/gpt-oss-120b$0.15$0.60131K
Tinfoilgpt-oss-120b$0.15$0.60131K
Together AIopenai/gpt-oss-120b$0.15$0.60131K
watsonx.aiopenai/gpt-oss-120b$0.16$0.64131K
LowRouterauto/openai/gpt-oss-120b$0.17$0.68131K
Charm Hypergpt-oss-120b$0.18$0.68131K
Cerebrasgpt-oss-120b$0.35$0.75131K
Cloudflare Workers AI@cf/openai/gpt-oss-120b$0.35$0.75128K
Prime Inferenceopenai/gpt-oss-120b$0.35$0.75131K
Privatemode AIgpt-oss-120b$0.23$0.75128K
STACKITopenai/gpt-oss-120b$0.53$0.76131K
GreenPTgpt-oss-120b$0.23$0.80131K
evrocopenai/gpt-oss-120b$0.23$0.9266K
AI/ML APIopenai/gpt-oss-120b$0.48$1.31131K
CloudFerro Sherlockopenai/gpt-oss-120b$2.92$2.92131K
Regolo AIgpt-oss-120b$1.00$4.20128K
Oppergpt-oss-120b$1.16$4.88128K
Qiniugpt-oss-120b——128K

Hugging Face Inference Providers

HostInputOutputContextSpeedFirst token
DeepInfraTools$0.037$0.17131K44 tok/s2.6s
NscaleTools$0.10$0.40131K109 tok/s0.6s
OVHcloudTools$0.09$0.47131K18 tok/s0.4s
BasetenTools$0.10$0.50128K188 tok/s0.2s
FireworksTools$0.15$0.60131K172 tok/s0.5s
Together AITools$0.15$0.60131K105 tok/s0.4s
ScalewayTools$0.17$0.68—37 tok/s2.4s
GroqTools$0.15$0.75131K396 tok/s0.5s
CerebrasFastestTools$0.35$0.75131K1090 tok/s0.2s
Featherless—————

From models.dev and Hugging Face, checked daily. Resellers’ listings can lag behind their price pages, so confirm with the provider before you commit.

More from OpenAI

OpenAI

GPT-6.1 Sol

CTX1.05M
99Quality
Reasoning · Vision · Tools
TextImagePDFInput$2/M
TextOutput$10/M

Near-Astra performance for complex coding, computer use, and professional work at a lower cost.

PaidProprietary1026/1044
OpenAI

GPT-6 Sol

CTX1.05M
97Quality
Reasoning · Vision · Tools
TextImagePDFInput$2/M
TextOutput$10/M

OpenAI model for complex coding and agentic workflows

PaidProprietary1021/1044
OpenAI

GPT-6 Luna

CTX1.05M
91Quality
Reasoning · Vision · Tools
TextImagePDFInput$0.10/M
TextOutput$0.50/M

OpenAI's most efficient model for focused, high-volume tasks

PaidProprietary1020/1044
OpenAI

GPT-6 Astra

CTX1.05M
100Quality
Reasoning · Vision · Tools
TextImagePDFInput$10/M
TextOutput$50/M

GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation.

PaidProprietary996/1044
OpenAI

GPT-5.6 Terra

CTX1.05M
96Quality
Reasoning · Vision · Tools
TextImagePDFInput$2/M
TextOutput$12/M

Balanced GPT-5.6 model for capable, cost-efficient everyday work

PaidProprietary947/1044
OpenAI

GPT-5.6 Sol

CTX1.05M
96Quality
Reasoning · Vision · Tools
TextImagePDFInput$4/M
TextOutput$20/M

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

PaidProprietary946/1044
OpenAI

GPT-5.6 Luna

CTX1.05M
91Quality
Reasoning · Vision · Tools
TextImagePDFInput$0.20/M
TextOutput$1.20/M

Cost-efficient GPT-5.6 model for fast, high-volume workloads

PaidProprietary945/1044
OpenAI

GPT-5.6

CTX1.05M
Reasoning · Vision · Tools
TextImagePDFInput$4/M
TextOutput$20/M

Frontier GPT-5.6 model for complex professional work, coding, and agentic workflows

PaidProprietary944/1044
Deck0/4
  1. Empty slot
  2. Empty slot
  3. Empty slot
  4. Empty slot