GPT-OSS 120B is an open-weight Mixture-of-Experts language model released by OpenAI in August 2025 under the Apache 2.0 license. It has 116.8B total parameters with 5.1B active per token across 36 layers, allowing it to run on a single 80GB GPU. The model reaches near-parity with OpenAI o4-mini on core reasoning benchmarks and outperforms similarly sized open models on reasoning tasks. It offers strong tool use with function calling and structured outputs, making it well suited to agentic and complex reasoning workflows. Its MoE design selects the top 4 of 128 experts per token and uses grouped query attention with rotary positional embeddings over a 128k context window.
GPT OSS 120B runs on 11 different routes through the Opper gateway. Compare residency, ZDR, and training posture at a glance โ full data-handling detail per route below.
| Provider | Region | Zero data retention | Training | Input | Output |
|---|---|---|---|---|---|
| AWS Bedrock | EU | Zero data retention | No | $0.15 | $0.60 |
| Berget | EU | Zero data retention | No | $0.35 | $1.05 |
| Cerebras | US | Enterprise | No | $0.35 | $0.75 |
| Evroc | EU | Zero data retention | No | $0.22 | $0.86 |
| Fireworks | US | Enterprise | No | $0.15 | $0.60 |
| Geodd | EU/EEA | Zero data retention | No | $0.04 | $0.18 |
| Geodd | US | Zero data retention | No | $0.04 | $0.18 |
| Groq | US | Enterprise | No | $0.15 | $0.60 |
| Infercom | EU | Zero data retention | No | $0.24 | $0.64 |
| Nebius | EU | Enterprise | No | $0.15 | $0.60 |
| Novita | US | Enterprise | No | $0.05 | $0.25 |
Training posture across routes: No training on prompts by default.
Each route hosting GPT OSS 120B has its own privacy posture, residency, and GDPR terms. Postures are maintained by Opper with a last-verification timestamp.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. EU; DPA available.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. EEA; SCCs.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. US; SCCs.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Zero data retention is on by default on Pay-as-you-go โ no action required. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. EU; DPA available.
Zero data retention is available via Opper Enterprise contract. No training on customer data. US; SCCs; DPA available.
Independent benchmark scores โ composite indices for reasoning, coding, and math, plus individual eval scores where available.
Call GPT OSS 120B through the Opper gateway with one API key. Let your coding agent set it up, or call it directly โ Opper is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.
Copy this and paste it into your coding agent โ Claude Code, Cursor, Codex, and more โ and it'll wire up Opper for you.
import OpenAI from "openai";const client = new OpenAI({apiKey: process.env.OPPER_API_KEY,baseURL: "https://api.opper.ai/v3/compat",});const completion = await client.chat.completions.create({model: "aws/gpt-oss-120b-eu",messages: [{ role: "user", content: "Hello" }],});console.log(completion.choices[0].message.content);
Side-by-side on privacy, EU hosting, pricing, and benchmarks.
