gpt-oss-120b API in Europe
The production workhorse - built for agents, not editors.
OpenAI's open-weight model, measured at 713 tokens per second on our EU infrastructure in Munich. Reliable production performance without flagship costs.
OpenAI Quality, Open-Weight Freedom
gpt-oss-120b is OpenAI's first open-weight model - Apache 2.0 licensed, designed for production agentic workloads. It's not the flashiest model, but it's the one you can rely on day after day.
Built-in Reasoning
Chain-of-thought reasoning with adjustable effort levels - optimize for speed or accuracy per task.
Production-Ready
Matches GPT-4o on most tasks. Beats it on reasoning-heavy benchmarks.
Best Value
Best price-to-intelligence ratio per Artificial Analysis.
Efficient by Design
| Total Parameters | 117B |
| Active Parameters | 5.1B per forward pass |
| Architecture | Mixture of Experts (MoE) |
| Experts | 128 experts, Top-4 routing per token |
| Layers | 36 |
| Context Length | 128K tokens |
| License | Apache 2.0 |
Measured on EU Infrastructure
10K input / 1K output, 1 concurrent, 10 requests
Up to 772 tok/s on shorter prompts. Last measured: July 2026.
See full benchmarks and methodologyDeep dives in our glossary
Why It's So Fast
The MoE architecture means you get 117B model quality while only running 5.1B parameters per request - that's why it's so fast.
- 22x fewer active parameters per inference
- Lower memory bandwidth requirements
- Expert routing optimized for each token
- Same quality, fraction of the compute
Not for Developers. For Agents.
"If you're building a public-facing AI agent, gpt-oss is your best bet - it's the best privately hostable model that functions on a single high-end GPU in production."
- Tigris
Reasoning Control
Adjust thinking effort (low/medium/high) per task
Function Calling
Native tool use for agentic workflows
Structured Outputs
JSON mode for reliable parsing
Web Browsing
Built-in capability for research agents
Navigate websites, extract data, and perform multi-step research tasks autonomously.
Code Execution
Python execution for data analysis agents
Run Python in a sandboxed environment for data processing, calculations, and analysis.
The Right Model for the Right Task
Not every request needs your most expensive model. Smart teams use gpt-oss-120b as part of a multi-model strategy.
"The technical quality is undeniable, and the chain-of-thought reasoning system is genuinely innovative in the open-weight space."
- Apatero (2026 Review)
Balanced Mode
In balanced mode: Matches GPT-4o on most tasks
Deep Mode
In deep mode: Beats GPT-4o on reasoning (MATH, HumanEval)
Cost Efficiency
At a fraction of the cost of proprietary models
| Scenario | Model Choice |
|---|---|
| Complex reasoning | gpt-oss-120b (high effort) |
| Standard tasks | gpt-oss-120b (medium effort) |
| Simple queries | gpt-oss-120b (low effort) |
| Premium tasks | MiniMax M2.7 Ultraspeed |
"We optimized workflows twice: once for accuracy + latency, and once for accuracy + cost-capturing the tradeoffs that matter most in real-world deployments."
- DataRobot
OpenAI Open-Weight on EU Infrastructure
Run OpenAI's open-weight model without sending data to the US:
- Hosted in Germany on Infercom-owned infrastructure
- Full GDPR compliance with EU-based DPA
- No US CLOUD Act exposure
- ISO 27001 certified
- Apache 2.0 license - full freedom to deploy
Start Building in Minutes
from openai import OpenAI
client = OpenAI(
api_key="your-infercom-key",
base_url="https://api.infercom.ai/v1"
)
response = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "Your prompt here"}],
max_tokens=4096
)
print(response.choices[0].message.content)OpenAI-compatible API. Drop-in replacement for your existing code.
Pay only for the tokens you use.
gpt-oss-120b: Frequently Asked Questions
713 tokens per second output throughput and 388 ms time to first token, both server-side p50 measured at 10K input / 1K output on our production API in Munich. Shorter prompts peak at up to 772 tok/s. That is up to 10x faster than GPU-based alternatives, and you can reproduce every figure with our open-source benchmark tool.
See the full benchmarksYes. OpenAI released gpt-oss-120b under the Apache 2.0 licence, so the weights are published and you are free to deploy, fine-tune and run the model commercially without a separate agreement. Running it through Infercom simply means we host and operate it for you on EU infrastructure.
What open-weight actually meansYes. Infercom serves gpt-oss-120b from Infercom-owned hardware in a Tier III+ datacenter in Munich, Germany. Requests are processed inside EU jurisdiction with no US CLOUD Act exposure, the infrastructure is ISO 27001 certified, and an EU data processing agreement is available on request. We do not train on your data.
How EU sovereignty works hereYes. Point the OpenAI SDK at https://api.infercom.ai/v1, use your Infercom API key and pass gpt-oss-120b as the model name. Code that already speaks the OpenAI chat completions API works without changes, including streaming, function calling and structured output.
Read the API documentation128K tokens (131,072), shared between your prompt and the model's response. That is room for large codebases, long agent traces and multi-document prompts in a single request.
What a context window isPay-per-token with no minimums and no monthly commitment: EUR 0.22 per million input tokens and EUR 0.59 per million output tokens. You are billed only for what you use, and live usage and spend are visible in the cloud portal.
See full pricingLearn More
Performance Benchmarks
See how gpt-oss-120b performs on our EU infrastructure
MiniMax M2.7 Ultraspeed
When you need SOTA agentic performance
Gemma 4 31B
When you need image and text in the same request
EU Sovereign AI
Where your data lives and who can reach it
API Documentation
Full API reference and integration guides
Pricing
Transparent per-token pricing