OpenAI's First Open-Weight Release Since GPT-2

gpt-oss OpenAI-Class AI, Fully On-Prem

Deploy OpenAI's open-weight reasoning models on your own hardware. The quality and behavior your teams already know from the OpenAI API — now with complete data sovereignty, no per-token cost, and no data leaving your servers.

gpt_oss_reasoning.py
# Same familiar OpenAI-style calls,
# now served from your own cluster
response = client.chat.completions.create(
    model="gpt-oss-120b",
    messages=[{
        "role": "user",
        "content": "Plan a migration and call the tools"
    }],
    reasoning_effort="high",
    tools=agent_tools
)

✓ Served on-prem — 0 bytes left your network

→ reasoning_effort=high · tool calls resolved locally

21B / 117B

Two MoE Model Sizes

128K

Context Window

Low/Med/High

Configurable Reasoning Effort

Apache 2.0

Open-Weight License

OpenAI Quality, Zero Cloud Dependency

gpt-oss brings the model family teams already trust inside your own perimeter — no API keys leaving the building, no metered billing.

Complete Data Sovereignty

Weights run entirely within your environment. Prompts, documents, and outputs never leave your servers — deploy fully air-gapped if you need to.

Fixed Cost, No Usage Limits

Replace per-token cloud billing with fixed infrastructure cost. Run unlimited inference at a predictable rate — no rate limits, no surprise invoices.

Compliance-Ready by Design

Keep regulated data in-region and under your own controls. Ideal for finance, healthcare, government, and any workload with strict residency requirements.

Familiar to Teams Already Using OpenAI

gpt-oss is OpenAI's first open-weight release since GPT-2, licensed under Apache 2.0. Teams that already build on OpenAI's API get the behavior and prompting patterns they know — the difference is where it runs. Point your existing integrations at a deployment you own, and nothing changes for your developers except the base URL.

Two Sizes, Both Mixture-of-Experts

Pick the model that fits your hardware. Both are reasoning models with configurable reasoning effort and a 128K context window.

gpt-oss-20b

Edge / Workstation

The single-GPU model. Around 21B total parameters with only ~3.6B active per token, so it stays fast and light while keeping strong reasoning.

Total / Active Params

~21B / ~3.6B

Minimum VRAM

~16 GB

Context Window

128K

Architecture

MoE

  • Runs on a single consumer GPU or high-end workstation
  • Ideal for on-device, branch-office, and edge deployments
  • Configurable reasoning effort: low / medium / high
Recommended

gpt-oss-120b

Flagship

The flagship model that fits on a single 80GB GPU. Around 117B total parameters with only ~5.1B active per token — flagship reasoning without a multi-GPU rack.

Total / Active Params

~117B / ~5.1B

Fits On

1× 80GB GPU

Context Window

128K

Architecture

MoE

  • Runs on a single 80GB GPU, e.g. one H100
  • Best fit for agentic workflows, tool use, and deep reasoning
  • Configurable reasoning effort: low / medium / high

Built for Reasoning and Agentic Work

gpt-oss models are reasoning models — strong at agentic workflows, tool use, and chain-of-thought. Dial reasoning effort up or down to match the task.

Agentic Workflows

Run multi-step agents that plan, act, and self-correct — entirely inside your network, with no external API calls.

  • Internal automation agents
  • Multi-step task orchestration
  • Autonomous research assistants

Tool Use & Function Calling

Connect the model to your own systems and APIs. It reasons about which tools to call and chains them to complete real tasks.

  • Internal API integration
  • Database and system queries
  • Structured, actionable outputs

Configurable Reasoning

Set reasoning effort to low, medium, or high per request — trade latency for depth on hard problems, keep it lean for simple ones.

  • Complex problem solving
  • Chain-of-thought analysis
  • Tunable latency vs. depth

Deployed in 72 Hours

We install gpt-oss on your infrastructure with an OpenAI-compatible endpoint. Your existing integrations keep working — you just change the base URL.

Quick Start

# Pull the deployment image
docker pull llmdeploy/gpt-oss:120b

# Or use our Python SDK
pip install sovereign-ai

# Initialize and run
from sovereign_ai import GptOss

model = GptOss("120b")
response = model.generate(
    prompt="Draft a rollout plan for the audit",
    reasoning_effort="high",
    max_tokens=1000
)

Infrastructure Support

gpt-oss-20b

~16GB VRAM · single GPU / workstation

gpt-oss-120b

Single 80GB GPU (e.g. one H100)

Deployment

Kubernetes, Docker, Bare Metal, Air-Gapped

Monitoring

Prometheus, Grafana, OpenTelemetry

OpenAI-Compatible API

Drop-in replacement for existing OpenAI integrations — familiar to any team already on the OpenAI API

# Simply change your base URL
client = OpenAI(
    base_url="https://your-deployment.com/v1",
    api_key="your-sovereign-ai-key"
)

72 hours

From kickoff to a running on-prem endpoint

Break-even

Fixed hardware cost overtakes metered cloud APIs at scale

0 bytes

Of your data leave your network — air-gap capable

Bring OpenAI-Class AI In-House

Self-host gpt-oss with full data sovereignty, fixed cost, and the OpenAI-compatible workflow your team already knows.