NewPoint any agent at UberLLM — one key, every model, list price or less.

GPT OSS Safeguard 120B vs Tencent HY3

openai/gpt-oss-safeguard-120b · tencent/hy3

As of November 1, 2026, Tencent HY3 is the cheaper API on UberLLM: $0.0011 per million input tokens and $0.0043 per million output, versus $0.0024 / $0.0096 for GPT OSS Safeguard 120B, about 55% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and UberLLM adds no fee. Choose Tencent HY3 to cut cost; choose GPT OSS Safeguard 120B when its capabilities fit your task better.

GPT OSS Safeguard 120B vs Tencent HY3, side by side

SpecGPT OSS Safeguard 120BTencent HY3
Price · input / 1M$0.0024$0.0011
Price · output / 1M$0.0096$0.0043
Context length128,000262,144
Max output tokens16,000131,072
Input modalitiestexttext
Output modalitiestexttext
Tools / functionsYesYes
Reasoning—Yes
% off list98.4% off99.2% off

Best prices on UberLLM right now. No UberLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 1, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?

GPT OSS Safeguard 120B vs Tencent HY3 — FAQ

Is GPT OSS Safeguard 120B or Tencent HY3 cheaper?

Tencent HY3 is cheaper on a blended token mix, by about 55%. A request costs what its provider charged, UberLLM adds no fee, and every request is listed with its cost in Activity.

What's the price difference between GPT OSS Safeguard 120B and Tencent HY3?

GPT OSS Safeguard 120B: $0.0024 in / $0.0096 out per 1M tokens. Tencent HY3: $0.0011 in / $0.0043 out per 1M tokens. That's roughly a 55% blended difference. Prices are live; UberLLM adds no fee.

Can I use both GPT OSS Safeguard 120B and Tencent HY3 with one API?

Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.uberllm.dev/v1 and your UberLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.uberllm.dev/v1/messages.

More comparisons