UTC

GPT OSS 120B

OpenAI · open weights · served by 107 providers · tool calling, reasoning

openai/gpt-oss-120b

Weights
Open
Released
2025-08-05
Knowledge cutoff
2024-06
Context window
131K
Deprecation dates

When each platform deprecates GPT OSS 120B, as LiteLLM records it. Plan the move before the date: after it, the platform may stop serving the model or stop updating it.

  • Azure AI Foundrydeprecates 2027-09-15azure_ai/gpt-oss-120bsuccessor: azure_ai/gpt-6.1-terra
  • Fireworks AIdeprecated 2026-11-07fireworks_ai/accounts/fireworks/models/gpt-oss-120b
Every upcoming deprecation →
Hugging Face repository

openai/gpt-oss-120b at commit b5c939de8f, last changed 2025-08-26

Licence
apache-2.0
Access
Open download
Library
transformers
Formats
.bin .safetensors
  • 1 weight file uses a pickle-based format, which can run code when loaded. Load the safetensors files instead.
  • No model signature file is published with the weights.

What the Hub's scanners report

23 weight files, 23 with a scan result. No scanner reports an issue with them.

The model at this commit, its 23 weight files with their SHA-256.

Facts from the Hugging Face Hub and its file scanners (Protect AI, Cisco, Hugging Face picklescan, VirusTotal, JFrog), as of 2026-11-18. ShieldMap does not copy model cards.

Who serves it
  • Abacusopenai/gpt-oss-120b
  • ai&openai/gpt-oss-120b
  • AI/ML APIopenai/gpt-oss-120b
  • AI Power Gridgpt-oss-120b
  • AKI.IOgpt-oss-120b
  • Amazon Bedrockopenai.gpt-oss-120b
  • Amazon Bedrockopenai.gpt-oss-120b-1:0
  • Amazon Bedrockus-gov.openai.gpt-oss-120b-1:0
  • Basetenopenai/gpt-oss-120b
  • Cerebrasgpt-oss-120b
  • Clarifaiopenai/chat-completion/models/gpt-oss-120b-high-throughput
  • CloudFerro Sherlockopenai/gpt-oss-120b
  • Cloudflare Workers AI@cf/openai/gpt-oss-120b
  • Cortecsgpt-oss-120b
  • Crusoeopenai/gpt-oss-120b
  • Databricksdatabricks-gpt-oss-120b
  • Deep Infraopenai/gpt-oss-120b
  • DigitalOceanopenai-gpt-oss-120b
  • DInferencegpt-oss-120b
  • Eden AIarkanecloud/openai/gpt-oss-120b
  • Eden AIcerebras/gpt-oss-120b
  • Eden AIcloudflare/@cf/openai/gpt-oss-120b
  • Eden AIdatabricks/databricks-gpt-oss-120b
  • Eden AIdatabricks/databricks-gpt-oss-120b@eu
83 more providers

Eden AI (deepinfra/openai/gpt-oss-120b), Eden AI (flexai/gpt-oss-120b), Eden AI (greenpt/gpt-oss-120b), Eden AI (groq/openai/gpt-oss-120b), Eden AI (ionos/openai/gpt-oss-120b), Eden AI (nebius/openai/gpt-oss-120b), Eden AI (ovhcloud/gpt-oss-120b), Eden AI (scaleway/gpt-oss-120b), Eden AI (together_ai/openai/gpt-oss-120b), Eden AI (tsystems/gpt-oss-120b), evroc (openai/gpt-oss-120b), FastRouter (openai/gpt-oss-120b), FrogBot (gpt-oss-120b), Vertex (openai/gpt-oss-120b-maas), GraphN (gpt-oss-120b), GreenPT (gpt-oss-120b), GreenPT (green-r), GreenPT (green-r-raw), Groq (openai/gpt-oss-120b), Helicone (gpt-oss-120b), Hugging Face (openai/gpt-oss-120b), Charm Hyper (gpt-oss-120b), Impossibl (cerebras/gpt-oss-120b), Impossibl (fireworks/gpt-oss-120b), Impossibl (groq/gpt-oss-120b), Inference Cooperative (tinfoil/gpt-oss-120b), Inference APIs (openai/gpt-oss-120b), IO.NET (openai/gpt-oss-120b), Keln (openai/gpt-oss-120b), Kenari (gpt-oss-120b), Kilo Gateway (openai/gpt-oss-120b), Klavo AI (openai/gpt-oss-120b), DevPass (LLM Gateway) (gpt-oss-120b), LLM Gateway (azure/gpt-oss-120b), LLM Gateway (cerebras/gpt-oss-120b), LLM Gateway (flexai/gpt-oss-120b), LLM Gateway (groq/gpt-oss-120b), LLM Gateway (scx-ai/gpt-oss-120b), LLM Gateway (together-ai/gpt-oss-120b), LowRouter (auto/openai/gpt-oss-120b), Merge Gateway (openai/gpt-oss-120b), Moneo (gpt-oss-120b), NanoGPT (TEE/gpt-oss-120b), NanoGPT (openai/gpt-oss-120b), Nebius Token Factory (openai/gpt-oss-120b), Neon (gpt-oss-120b), Novita AI (openai/gpt-oss-120b), OCI Generative AI (openai.gpt-oss-120b), Ollama Cloud (gpt-oss:120b), OpenReason (openai/gpt-oss-120b), OpenRouter (openai/gpt-oss-120b), Opper (gpt-oss-120b), OrcaRouter (openai/gpt-oss-120b), OVHcloud AI Endpoints (gpt-oss-120b), Pendra (gpt-oss:120b), Phala (openai/gpt-oss-120b), Phase Router (gpt-oss-120b), Poe (cerebras/gpt-oss-120b-cs), Powerspring (gpt-oss-120b), Prime Inference (openai/gpt-oss-120b), Privatemode AI (gpt-oss-120b), QVAC (gpt-oss-120b), Regolo AI (gpt-oss-120b), Runcrate (openai/gpt-oss-120b), SambaNova (gpt-oss-120b), Scaleway (gpt-oss-120b), SCX.ai (gpt-oss-120b), SiliconFlow (openai/gpt-oss-120b), SOKKAN Router (openai/gpt-oss-120b), STACKIT (openai/gpt-oss-120b), stepping stone AG (openai/gpt-oss-120b), submodel (openai/gpt-oss-120b), Synthetic (hf:openai/gpt-oss-120b), Thinking Machines (openai/gpt-oss-120b), Thinking Machines (openai/gpt-oss-120b:peft:131072), Tinfoil (gpt-oss-120b), Together AI (openai/gpt-oss-120b), TrustedTokens (openai/gpt-oss-120b), Venice AI (openai-gpt-oss-120b), Vercel AI Gateway (openai/gpt-oss-120b), CoreWeave (openai/gpt-oss-120b), watsonx.ai (openai/gpt-oss-120b), ZeroGPU (gpt-oss-120b)

Running it yourself

Open weights are loaded and served by code that has its own advisories. These inference servers and model loaders are on ShieldMap; load weights only from the publisher's own repository, and prefer safetensors over formats that can run code.

How supply-chain attacks on models work →

Sources: models.dev (MIT) and the LiteLLM model catalogue (MIT). Deprecation dates are as each platform published them and as LiteLLM records them; check the platform before you rely on one. Data as of 2026-11-22.