GPT-OSS 120B
Open GPT reasoning model for self-hosted agents and controllable deployments
- Released
- Aug 5 2025
- Modality
- Text
- Context
- 125K tokens
- Price in / cached input / out
- $0.097 / $0.053 / $0.73per 1M tokens
Quickstart
OpenAI-compatible: change the base URL, and the setup is complete.
from openai import OpenAI
import os
client = OpenAI(
base_url="https://api.you.com/v1",
api_key=os.environ["YOU_API_KEY"],
)
response = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "Summarize this support ticket in two sentences."}],
)
print(response.choices[0].message.content)Specifications
Technical details, capabilities, pricing, and data handling.
Model info
- Input Modality
- Text
- Output Modality
- Text
- Context Window
- 125K
- Parameters
- 117B total / 5.1B active
- License
- Apache 2.0
Capabilities
- Reasoning
- Supported
- Function calling
- Supported
- Structured outputs
- Supported
- Web search grounding
- Not supported
Pricing
- Input
- $0.097
- Cached input
- $0.053
- Output
- $0.73
Data handling
- Zero data retention
- Supported
- No training on customer data
- Supported
- Regions
- US
Providers
Access models through multiple providers with automatic routing and built-in failover.
| Provider | ZDR | No training | Region |
|---|---|---|---|
| You Inference | Yes | Yes | US |
| Parasail | Yes | Yes | US |
When to use GPT-OSS 120B
Guidance based on the specifications and benchmarks on this page.
Best for
- Low-cost reasoning at scaleOpenAI reports near-parity with o4-mini on core reasoning benchmarks while activating only 5.1B parameters per token.
- Agentic tool use workflowsNative function calling, web browsing, Python execution, and Structured Outputs, with adjustable reasoning effort.
- Self-hosting and fine-tuningApache 2.0 weights run on a single 80GB GPU and can be fine-tuned on a single H100 node.
Consider alternatives for
- You need image understandingGPT-OSS 120B is text-only, trained on a mostly English, text-only dataset.
- You need over 128K contextThe model natively supports context lengths of up to 128K tokens.
- You need top expert-level reasoningIt scores 19.0% on Humanity's Last Exam with tools, below OpenAI o3's 24.9% in the same release.
Benchmarks
GPT-OSS 120B results alongside comparable models
| Benchmark | GPT-OSS 120BOpenAI | DeepSeek V4 ProDeepSeek | DeepSeek V4.1 FlashDeepSeek | Kimi K3Moonshot AI | Qwen3.8 MaxAlibaba | GLM 5.3Z.ai |
|---|---|---|---|---|---|---|
| GPQA Diamond | 80.1% | 90.1% | 90.9% | 93.5% | 92.6% | Not evaluated |
| Humanity's Last Exam | 14.9% | 37.7% | 36.8% | 43.5% | 43.6% | Not evaluated |
| Humanity's Last Exam (with tools) | 19% | 48.2% | 63.9% | 56% | 56.2% | 62.5% |
| AIME 2025 | 92.5% | Not evaluated | Not evaluated | Not evaluated | Not evaluated | Not evaluated |
Scores are self-reported by each model’s developer, so settings may vary between models. Sources: GPT-OSS 120B (model card), DeepSeek V4 Pro (Hugging Face), DeepSeek V4.1 Flash (Hugging Face), Kimi K3 (Hugging Face), Qwen3.8 Max (Hugging Face), Qwen3.8 Max (release post), GLM 5.3 (Hugging Face).
Give GPT-OSS 120B access to the live web
Ground responses with fresh web information and cited sources using You.com Search, without changing models or adding another integration.
What error do I get installing psycopg2 on Python 3.13?
LLM + You.com Web Search
psycopg2 on Python 3.13
Short answer:
psycopg2 installs fine today. 2.9.10 added 3.13 support in Oct 2024. 12
The error you hit is almost certainly missing build step:
pg_config executable not found
Fix:
pip install -U psycopg2-binary
LLM (LLM only)
When trying to install psycopg2 on Python 3.13, you will most likely hit one of these errors:
1. No pre-built wheel available
pip cannot find a binary wheel because the psycopg2 project hasn’t yet published wheels for Python 3.13.
What you should do
Downgrade Python — use Python 3.12 or earlier until psycopg2 officially supports 3.13.
Explore popular models
Explore all models2.4-trillion-parameter MoE flagship for coding, professional work, multimodal understanding, and long-horizon agentic workflows
Flagship GLM model for long-horizon coding, agents, and complex project delivery
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
DeepSeek V4.1 Flash model for reasoning and agentic coding
Build with Inference Router
Tell us what you run today, and a solutions engineer will show you what it costs on open-weight models.