A heavyweight open-weight GPT reasoning model that runs on a single GPU.
Technical Specifications
- Provider
- OpenAI
- Category
- open-source
- Release Date
- 2025-08
- Batch API Discount
- 50% off async batch
- Consumer Subscription
- Free / Self-Hosted
- Reasoning Effort Control
- Configurable (Low / Med / High)
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- gpt-oss-120b
- Supported SDK & API Protocol
- OpenAI Responses API & Chat Completions v1
- Lifecycle & Deprecation Status
- Active GA (Guaranteed support through 2027+)
- Production Rate Limits (RPM & TPM)
- Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($0.15/1M in) across full 131K window
- Prompt Cache Write & TTL Policy
- Automatic prefix caching at $0.015/1M (no extra cache-write fee)
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Native Web Search tool + Hosted Code Interpreter & File Search RAG
- Fine-Tuning & Distillation Support
- Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
- Minimum GPU VRAM Requirement
- 73 GB VRAM (4-bit Quantized) · 252 GB VRAM (Native BF16)
- Supported Inference Engines
- vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
- System Card & Safety Framework
- OpenAI Preparedness Framework Audited & System Card Published
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
GPT-OSS 120B Cost, Context, Hardware & API Integration
Pay-as-you-go API is cheaper for this volume (saves $6.05/mo vs $20 flat plan).
Break-even point: ~717 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to GPT-OSS 120B:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 45.5%
- GPQA Diamond
- 68.5%
- MMLU-Pro
- 80.5%
- HumanEval
- 89.5%
- Humanity's Last Exam
- 9.8%
- Terminal-Bench
- 30.5%
- SciCode
- 33%
- LiveCodeBench
- 58.5%
- AIME
- 84.5%
- Long-Context Reasoning
- 71%
- Chatbot Arena Elo
- 1330pts
Strengths
- o4-mini-class performance with fully open weights
- Runs on a single high-memory GPU thanks to MoE routing
- Strong tool calling for self-hosted agents
- Near-o4-mini quality on private infrastructure
Limitations & Trade-offs
- Still behind proprietary frontier models on reasoning
- Text-only modality support
- Requires serious GPU memory to self-host
Editorial Assessment
The strongest open-weight pick from OpenAI to date.
Best for: Self-hosted agents that need near-frontier quality on private data
Compare GPT-OSS 120B
Frequently Asked Questions about GPT-OSS 120B
How much does the GPT-OSS 120B API cost per 1M tokens?+
GPT-OSS 120B by OpenAI is priced at $0.15 per 1M input tokens and $0.6 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.015 per 1M tokens, and asynchronous Batch API requests receive a 50% discount.
Should I use a $20/month subscription or the GPT-OSS 120B pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in GPT-OSS 120B's context window?+
GPT-OSS 120B features a 131K tokens context window, which equals approximately 98,304 English words or ~262 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 32,768 tokens.
Can I run GPT-OSS 120B locally on my own GPU (Open Weights)?+
Yes, GPT-OSS 120B (117B (5.1B active MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.
Does OpenAI train on data sent to the GPT-OSS 120B API, and is commercial use allowed?+
100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.
How does GPT-OSS 120B perform on coding and reasoning benchmarks?+
GPT-OSS 120B achieves a composite Intelligence Index of 56/100, scoring 45.5% on SWE-bench Verified, 68.5% on GPQA Diamond, 80.5% on MMLU-Pro, and 1330 pts on Chatbot Arena Elo.
What is GPT-OSS 120B best used for?+
GPT-OSS 120B is best suited for: Self-hosted agents that need near-frontier quality on private data. Assessment: The strongest open-weight pick from OpenAI to date.
OpenAI Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to OpenAI's flagship reasoning tier:
GPT-6 Astra
GPT-6.1 Sol
GPT-6 Sol
GPT-6 Luna
GPT-5.6 Sol
GPT-5.6 Terra
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to GPT-OSS 120B:
The basic unit of text that a language model processes, typically representing about 3 to 4 English characters or roughly 0.75 words. For example, the sentence "Artificial intelligence is fast" breaks down into about 5 tokens.
A standardized evaluation suite used to objectively measure and rank an AI model's capabilities across specific tasks — such as SWE-bench Verified for software engineering, AIME for competitive math, or MMLU for general knowledge.
The maximum number of tokens a model can consider at once — both the input it reads and the output it writes. A 1,000,000-token context window can hold roughly 750,000 English words in a single request.
An AI model trained via reinforcement learning to spend dynamic compute thinking through complex logic, math, and architectural problems before outputting a solution. Examples include OpenAI o1, o3, and DeepSeek R1.
A step-by-step reasoning technique where an AI model generates intermediate problem-solving thoughts before arriving at a final answer. Native reasoning models like OpenAI o3 and DeepSeek R1 use CoT to solve complex math and coding challenges.
The ability of a language model to recognize when an external capability is needed and output structured JSON arguments to invoke external APIs, databases, or terminal commands. The runtime executes the tool and passes results back to the model.
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Sources: OpenAI open-weight model card (Hugging Face) & official pricing↗