un seguridad modelo para policy screening, moderation y risk-aware enrutamiento.
Technical Specifications
- Provider
- OpenAI
- Category
- open-source
- Release Date
- 2025-10
- 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-safeguard-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 Safeguard 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 Safeguard 120B:
Benchmark Scores & 6-Axis Capability Radar
- SWE-bench Verified
- 41%
- GPQA Diamond
- 65%
- MMLU-Pro
- 79%
- HumanEval
- 88%
- Humanity's Last Exam
- 9.2%
- Terminal-Bench
- 28%
- SciCode
- 31%
- LiveCodeBench
- 55%
- AIME
- 82%
- Long-Context Reasoning
- 69.5%
- Chatbot Arena Elo
- 1322pts
Strengths
- abierto-weight seguridad classifier you puede audit y fine-tune
- razonamiento traces make moderation decisions explainable
- Fits cleanly en existing moderation canalizaciones
- razonamiento traces make moderation decisions auditable
Limitations & Trade-offs
- no intended as un general-purpose asistente
- Policy categories must be supplied por el operator
Editorial Assessment
un diseñado específicamente abierto seguridad modelo rather que un chat modelo.
Best for: Content moderation, policy screening y seguridad enrutamiento layers
Compare GPT OSS Safeguard 120B
Frequently Asked Questions about GPT OSS Safeguard 120B
How much does the GPT OSS Safeguard 120B API cost per 1M tokens?+
GPT OSS Safeguard 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 Safeguard 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 Safeguard 120B's context window?+
GPT OSS Safeguard 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 Safeguard 120B locally on my own GPU (Open Weights)?+
Yes, GPT OSS Safeguard 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 Safeguard 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 Safeguard 120B perform on coding and reasoning benchmarks?+
GPT OSS Safeguard 120B achieves a composite Intelligence Index of 52/100, scoring 41% on SWE-bench Verified, 65% on GPQA Diamond, 79% on MMLU-Pro, and 1322 pts on Chatbot Arena Elo.
What is GPT OSS Safeguard 120B best used for?+
GPT OSS Safeguard 120B is best suited for: Content moderation, policy screening y seguridad enrutamiento layers. Assessment: un diseñado específicamente abierto seguridad modelo rather que un chat modelo.
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 Safeguard 120B:
La unidad básica de texto que procesa un modelo de lenguaje, que normalmente equivale a 3 o 4 caracteres o aproximadamente 0,75 palabras. Por ejemplo, una frase típica se divide en varios tokens.
Un conjunto estandarizado de pruebas para evaluar y comparar objetivamente las capacidades de distintos modelos de IA en tareas como programación (SWE-bench) o matemáticas avanzadas (AIME).
La cantidad máxima de tokens que un modelo puede considerar a la vez, incluyendo tanto la entrada que lee como la salida que genera. Una ventana de 1.000.000 de tokens puede procesar unas 750.000 palabras en una sola petición.
Un modelo de IA entrenado para invertir cómputo adicional en pensar y validar hipótesis lógicas antes de responder, diseñado para problemas complejos de ingeniería y matemáticas.
Una técnica de razonamiento paso a paso donde el modelo genera pensamientos intermedios antes de formular la respuesta final, mejorando radicalmente la resolución de problemas matemáticos y lógicos.
La capacidad de un modelo de detectar la necesidad de una función externa y emitir argumentos JSON estructurados para ejecutar API, búsquedas web o consultas a bases de datos.
Las puntuaciones de benchmarks, precios por token y límites de tasa evolucionan rápidamente. Verifique siempre las especificaciones actuales en la documentación oficial del proveedor.
Fuentes: OpenAI open-weight model card (Hugging Face) & official pricing↗