GPT OSS 120B

by OpenAI

All OpenAI releases

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.

Key info

Input
Output
Features
Context window
128K
Max output
8K
Input price
$0.15 /1M
Output price
$0.60 /1M
Released
  • EU/EEA residency available
  • US residency available
  • Zero data retention on pay-as-you-go
  • No training by default
  • no-KYC deposit available

Available routes

GPT OSS 120B runs on 14 different routes through the qynio gateway. Compare residency, zero retention, and training posture at a glance โ€” full data-handling detail per route below.

ProviderRegionZero data retentionTrainingInputOutput
EUZero data retentionNo$0.15$0.60
EUZero data retentionNo$0.23$0.87
MultiNot by defaultNo$0.10$0.50
USZero data retentionNo$0.35$0.75
USNot by defaultNo$0.06$0.39
EUZero data retentionNo$0.23$0.93
MultiZero data retentionNo$0.15$0.60
EU/EEAZero data retentionNo$0.04$0.18
USZero data retentionNo$0.04$0.18
USNot by defaultNo$0.15$0.60
EUZero data retentionNo$0.26$0.69
EUNot by defaultNo$0.15$0.60
USZero data retentionNo$0.05$0.25
EUZero data retentionNo$1.16$4.88

Uptime and availability

GPT OSS 120B runs on 7 independently monitored routes through the qynio gateway. A direct integration leaves you on one of them, the gateway serves whichever is healthy.

100%effective uptime, last 30 days
Averaged across these routes on their own, a single provider reached 99.43% over the same window.
Daily status through the gateway, which serves each request from whichever route is healthy.
7 monitored providers serve GPT OSS 120B.

Measured over the last 30 days from each provider's official status feed via StatusGator. Refreshed hourly. 6 further routes for this model are not on the board yet and are not counted above. See uptime for every provider qynio monitors.

Data handling per route

Each route hosting GPT OSS 120B has its own privacy posture, residency, and no-KYC terms. Postures are maintained by qynio with a last-verification timestamp.

AWS Bedrock โ€” Sweden๐Ÿ‡ธ๐Ÿ‡ช

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

Berget โ€” Sweden๐Ÿ‡ธ๐Ÿ‡ช

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

BytePlus โ€” Multi-region

Zero data retention is not on by default โ€” abuse monitoring, 180-day retention. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
Not by default โ€” abuse monitoring, 180-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (180-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Cerebras โ€” United States๐Ÿ‡บ๐Ÿ‡ธ

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. US; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

DigitalOcean โ€” United States๐Ÿ‡บ๐Ÿ‡ธ

Zero data retention is not on by default โ€” a moderation hold applies. No training on customer data. US; dpf sccs; deposit available.

Zero data retention
Not by default โ€” a moderation hold applies. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Holds content for review
Caching
Content cached for replay
Subprocessor access
No subprocessor reads content
no-KYC deposit
deposit available
Transfer mechanism
dpf sccs

evroc โ€” Sweden๐Ÿ‡ธ๐Ÿ‡ช

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
No hold on content
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

Fireworks โ€” Multi-region

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. GLOBAL; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Subprocessors may read content
no-KYC deposit
deposit available
Transfer mechanism
wallets

Geodd โ€” Norway๐Ÿ‡ณ๐Ÿ‡ด

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EEA; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
No hold on content
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Geodd โ€” United States๐Ÿ‡บ๐Ÿ‡ธ

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. US; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
No hold on content
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Groq โ€” United States๐Ÿ‡บ๐Ÿ‡ธ

Zero data retention is not on by default โ€” abuse monitoring, 30-day retention. No training on customer data. US; wallets; deposit available.

Zero data retention
Not by default โ€” abuse monitoring, 30-day retention. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring (30-day retention)
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Infercom โ€” Germany๐Ÿ‡ฉ๐Ÿ‡ช

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
No subprocessor reads content
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

Nebius โ€” Finland๐Ÿ‡ซ๐Ÿ‡ฎ

Zero data retention is not on by default โ€” abuse monitoring. No training on customer data. EU; deposit available.

Zero data retention
Not by default โ€” abuse monitoring. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
Abuse monitoring
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

Novita โ€” United States๐Ÿ‡บ๐Ÿ‡ธ

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. US; wallets; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
Not established
Caching
Not established
Subprocessor access
Not established
no-KYC deposit
deposit available
Transfer mechanism
wallets

Regolo โ€” Italy๐Ÿ‡ฎ๐Ÿ‡น

Zero data retention is on by default on Pay-as-you-go โ€” no action required. No training on customer data. EU; deposit available.

Zero data retention
On by default on Pay-as-you-go. Derived from the logging and moderation facts.
Training
No training on customer data.
Logging
None
Moderation
No hold on content
Caching
Not established
Subprocessor access
No subprocessor reads content
no-KYC deposit
deposit available
Transfer mechanism
Not applicable โ€” data stays in EU

Benchmarks

Independent benchmark scores โ€” composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#240 of 630 LLMs
TierEfficient
Output speed152 tok/s
First token0.52s
Intelligence Index24.1
Coding Index30.4
Math Index93.4
Reasoning & knowledge
MMLU-Pro
81%
GPQA Diamond
78%
Humanity's Last Exam
20%
Long-context reasoning
51%
Coding
LiveCodeBench
88%
SciCode
39%
Agentic & tool use
Terminal-Bench Hard
23%
ฯ„ยฒ-Bench Telecom
66%
Math & instruction following
AIME 2025
93%
IFBench
69%

Get started

Call GPT OSS 120B through the qynio gateway with one API key. Let your coding agent set it up, or call it directly โ€” qynio is drop-in compatible with the OpenAI, Anthropic, and Google AI SDKs.

Set it up with your agent

Copy this and paste it into a coding agent like Claude Code, Cursor or Codex and it'll wire up qynio for you.

Or call it directly

import OpenAI from "openai";
const client = new OpenAI({
apiKey: process.env.QYN_API_KEY,
baseURL: "https://api.qyn.io/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);

Compare GPT OSS 120B withโ€ฆ

Side-by-side on privacy, crypto rails, pricing, and benchmarks.

Other models from OpenAI

Start building with 700+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation