GPT-OSS 120B
oah/gpt-oss-120bDeploy GPT-OSS 120B with built-in PII redaction and Hub governance. 120B parameters. Available on Managed Credits and BYOK.
Groq
Input: $0.15/MOutput: $0.60/M
Why deploy GPT through AI Security Gateway?
Automatic PII Redaction
Every GPT request is scanned for 28+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Smart Cost Routing
GPT is available across 2 providers. Our Smart Router picks the cheapest one per-request. 30% managed markup / 0% on Pro BYOK.
Zero Code Changes
Change two lines in your OpenAI SDK — base_url and api_key — and every request flows through AISG. Full backward compatibility.
Full Observability
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
GPT Strengths
- Industry-leading instruction following and reasoning
- Best-in-class tool/function calling support
- GPT-4.1: enhanced coding and long-context performance
- GPT-4o-mini: strong quality at a fraction of full GPT-4 cost
- Widest ecosystem of tutorials, plugins, and integrations
Available GPT Models (9)
GPT-OSS 20B
oah/gpt-oss-20bDeploy GPT-OSS 20B with built-in PII redaction and Hub governance. 20B parameters. Available on Managed Credits and BYOK.
Groq
Input: $0.07/MOutput: $0.30/M
GPT-4.1
oah/gpt-4.1Deploy GPT-4.1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $2.00/MOutput: $8.00/M
GPT-4.1 Mini
oah/gpt-4.1-miniDeploy GPT-4.1 Mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $0.40/MOutput: $1.60/M
GPT-4.1 Nano
oah/gpt-4.1-nanoDeploy GPT-4.1 Nano with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $0.10/MOutput: $0.40/M
GPT-4o
oah/gpt-4oDeploy GPT-4o with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $2.50/MOutput: $10.00/M
GPT-4o Mini
oah/gpt-4o-miniDeploy GPT-4o Mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $0.15/MOutput: $0.60/M
o3-mini
oah/o3-miniDeploy o3-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $1.10/MOutput: $4.40/M
o4-mini
oah/o4-miniDeploy o4-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
OpenAI
Input: $1.10/MOutput: $4.40/M
GPT Pricing Comparison (per 1M tokens, USD)
Input / Output pricing by provider. Managed Mode adds a 30% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | Groq | OpenAI |
|---|---|---|---|---|---|
GPT-OSS 120B oah/gpt-oss-120b | 120B | — | No | $0.15/$0.60 | — |
GPT-OSS 20B oah/gpt-oss-20b | 20B | — | No | $0.07/$0.30 | — |
GPT-4.1 oah/gpt-4.1 | — | — | No | — | $2.00/$8.00 |
GPT-4.1 Mini oah/gpt-4.1-mini | — | — | No | — | $0.40/$1.60 |
GPT-4.1 Nano oah/gpt-4.1-nano | — | — | No | — | $0.10/$0.40 |
GPT-4o oah/gpt-4o | — | — | No | — | $2.50/$10.00 |
GPT-4o Mini oah/gpt-4o-mini | — | — | No | — | $0.15/$0.60 |
o3-mini oah/o3-mini | — | — | No | — | $1.10/$4.40 |
o4-mini oah/o4-mini | — | — | No | — | $1.10/$4.40 |
GPT Direct vs AI Security Gateway
What you get at each pricing tier. Hub adds security, governance, and multi-provider routing on top of raw API access.
| Mode | What You Pay | PII Redaction | Budget Caps | Routing | Audit Trail |
|---|---|---|---|---|---|
| Direct to OpenAI | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 30% markup | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
| Hub — Pro BYOK ($29/mo) | Direct to provider (0% markup) | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
Popular Use Cases
1
Complex multi-step reasoning tasks
2
Production chatbots requiring top-tier instruction following
3
Code generation and analysis
4
Structured output / function calling pipelines
Integration — 2 Lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.aisecuritygateway.ai/v1",
api_key="your_hub_api_key"
)
# Use any virtual model name from the pricing table above
response = client.chat.completions.create(
model="oah/gpt-oss-120b",
messages=[{"role": "user", "content": "Hello!"}]
)Use any virtual model name from the pricing table above (prefixed with oah/). Works with the standard OpenAI SDK. Every request is PII-scanned before reaching OpenAI (Closed Source).
Frequently Asked Questions
What is the GPT-4 API cost on AI Security Gateway?
GPT-4 API cost depends on the variant. In Managed Mode, we add a 30% markup on OpenAI's published API pricing. With Pro BYOK ($29/mo), you use your own OpenAI key and pay OpenAI directly at 0% markup — plus the full DLP firewall. Check the pricing table above for current per-token rates.
Is AI Security Gateway the cheapest GPT-4 provider?
In Pro BYOK mode, you pay OpenAI directly at 0% markup — so you get OpenAI's own pricing plus 28+ PII entity redaction, budget caps, and audit logging at no extra per-token cost. The $29/mo subscription is the only fee.
What is OpenAI API pricing in 2026?
OpenAI API pricing varies by model: GPT-4.1 is the newest flagship, GPT-4o balances cost and quality, and GPT-4o-mini is the most affordable. The pricing table above shows live rates. Through AISG, you get the same models with added PII protection.
Can I use GPT-4 with PII redaction?
Yes. Every GPT request through AI Security Gateway is automatically scanned for 28+ PII entity types. Sensitive data is redacted before the prompt reaches OpenAI's servers.
Is GPT-4o-mini good enough for production?
For many use cases, yes. GPT-4o-mini offers strong instruction following at roughly 1/10th the cost of full GPT-4. Our Smart Router can intelligently select between variants based on your cost/quality preferences.
Does OpenAI see my prompts when using BYOK?
In BYOK mode, prompts go from AISG (after PII redaction) to OpenAI using your API key. OpenAI processes the request per their API data usage policy — API data is not used for training by default.
Deploy GPT with Enterprise-Grade Security
Get started with 1,000,000 free credits. Every GPT request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about GPT updates:
Explore Other Model Families
🦙Llama
Meta's open-weights Llama family is the most widely deployed open-source LLM series. Compare Llama API pricing across Gr…
💎Gemini
Google's Gemini family offers powerful multimodal capabilities with large context windows. Compare Gemini API pricing an…
🤖Claude
Anthropic's Claude family is built with safety and reliability at its core. Compare Claude API pricing and Claude Sonnet…
🔍DeepSeek
DeepSeek has rapidly risen as a leading open-source model family, known for exceptional coding performance and cost effi…
🌀Mistral
Mistral AI's model family spans from compact open-weights models to powerful commercial variants. Compare Mistral API pr…
Model registry last updated: 2026-04-18T17:41:46.389Z. Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.