GPT-5.2 Codex vs GPT OSS Safeguard 120B
openai/gpt-5.2-codex · openai/gpt-oss-safeguard-120b
As of November 1, 2026, GPT OSS Safeguard 120B is the cheaper API on UberLLM: $0.0024 per million input tokens and $0.0096 per million output, versus $0.4375 / $3.50 for GPT-5.2 Codex, about 100% 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 GPT OSS Safeguard 120B to cut cost; choose GPT-5.2 Codex when context size wins. GPT-5.2 Codex carries the larger context window (256,000 vs 128,000 tokens), which can matter for long-document work.
GPT-5.2 Codex vs GPT OSS Safeguard 120B, side by side
| Spec | GPT-5.2 Codex | GPT OSS Safeguard 120B |
|---|---|---|
| Price · input / 1M | $0.4375 | $0.0024 |
| Price · output / 1M | $3.50 | $0.0096 |
| Context length | 256,000 | 128,000 |
| Max output tokens | 65,536 | 16,000 |
| Input modalities | text, image | text |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | — |
| Reasoning | Yes | — |
| % off list | 75% off | 98.4% 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-5.2 Codex vs GPT OSS Safeguard 120B — FAQ
Is GPT-5.2 Codex or GPT OSS Safeguard 120B cheaper?
GPT OSS Safeguard 120B is cheaper on a blended token mix, by about 100%. 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-5.2 Codex and GPT OSS Safeguard 120B?
GPT-5.2 Codex: $0.4375 in / $3.50 out per 1M tokens. GPT OSS Safeguard 120B: $0.0024 in / $0.0096 out per 1M tokens. That's roughly a 100% blended difference. Prices are live; UberLLM adds no fee.
Can I use both GPT-5.2 Codex and GPT OSS Safeguard 120B 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.