GPT OSS Safeguard 120B
CortecsOpen weights
GPT OSS Safeguard 120B by Cortecs costs $0.18 per 1M input tokens and $0.70 per 1M output tokens, with a 128K-token context window.
Pricing
Input (per 1M tokens)
$0.18
Output (per 1M tokens)
$0.70
Cached input (per 1M)
—
Specifications
- Provider
- Cortecs
- Context window
- 128K tokens
- Parameters
- —
- Released
- Oct 2025
- Open weights
- Yes
- Frontier model
- No
Speed & latency
Time to first token
0.38s
Output speed
121 tok/s
Fastest host: bedrock (via vercel-ai-gateway).
Compare GPT OSS Safeguard 120B with…
FAQ
How much does GPT OSS Safeguard 120B cost?
GPT OSS Safeguard 120B is priced at $0.18 per 1M input tokens and $0.70 per 1M output tokens. Output tokens cost more than input.
What is GPT OSS Safeguard 120B's context window?
GPT OSS Safeguard 120B supports a context window of 128K tokens — the maximum prompt plus response length it can handle in a single request.
Is GPT OSS Safeguard 120B open weight?
Yes — GPT OSS Safeguard 120B has openly available weights.
Data as of 2026-10-14. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.