AI Rate CardGPT OSS Safeguard 120B vs GPT OSS Safeguard 20B: API price and specs
GPT OSS Safeguard 20B is 53% cheaper than GPT OSS Safeguard 120B on input price.
GPT OSS Safeguard 20B is 67% cheaper than GPT OSS Safeguard 120B on output price.
GPT OSS Safeguard 20B is 59% cheaper than GPT OSS Safeguard 120B on a 1M-in / 200k-out workload.
| Field | GPT OSS Safeguard 120B | GPT OSS Safeguard 20B |
|---|---|---|
| Lowest input, per 1M | $0.15 +114.3% | $0.07 |
| Median input, per 1M | $0.15 +103.1% | $0.07385 |
| Lowest output, per 1M | $0.60 +200% | $0.20 |
| Median output, per 1M | $0.60 +184.4% | $0.21 |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.27 +145.5% | $0.11 |
| Context | 131K | 131K |
| Max output | 128K | 66K +48.8% |
| Providers | 6 +14.3% | 7 |
| Regions | EU, US | EU, US |
| Accepts | text | text |
| Returns | text | text |
| Type | Moderation | Moderation |
| Free option | no | no |
| Cheapest provider | amazon-bedrock | amazon-bedrock |
Your own workload: how many tokens the model gets (input) and gives back (output) - for example, in a month. The "Cost" row of the table above is recalculated for these numbers, for each model.
Computed from current offers each time the page opens; the best value of a row is bold, the percent is how far behind the best.
Providers selling both
amazon-bedrock, edenai, trustedrouter, vercel
Frequently asked questions
Which is cheaper, GPT OSS Safeguard 120B or GPT OSS Safeguard 20B?
GPT OSS Safeguard 20B is 53% cheaper than GPT OSS Safeguard 120B on input price. GPT OSS Safeguard 20B is 67% cheaper than GPT OSS Safeguard 120B on output price. GPT OSS Safeguard 20B is 59% cheaper than GPT OSS Safeguard 120B on a 1M-in / 200k-out workload.
Which has the larger context, GPT OSS Safeguard 120B or GPT OSS Safeguard 20B?
GPT OSS Safeguard 120B: 131K tokens; GPT OSS Safeguard 20B: 131K tokens.
Where can I use both GPT OSS Safeguard 120B and GPT OSS Safeguard 20B?
amazon-bedrock, edenai, trustedrouter, vercel