AI Rate CardLlama Guard 4 12B vs GPT OSS Safeguard 20B: API price and specs
GPT OSS Safeguard 20B is 51% cheaper than Llama Guard 4 12B on input price.
Llama Guard 4 12B is 28% cheaper than GPT OSS Safeguard 20B on output price.
GPT OSS Safeguard 20B is 36% cheaper than Llama Guard 4 12B on a 1M-in / 200k-out workload.
Llama Guard 4 12B has a 25% larger context than GPT OSS Safeguard 20B.
| Field | Llama Guard 4 12B | GPT OSS Safeguard 20B |
|---|---|---|
| Lowest input, per 1M | $0.14 +105.7% | $0.07 |
| Median input, per 1M | $0.18 +143.7% | $0.07385 |
| Lowest output, per 1M | $0.14 | $0.20 +38.9% |
| Median output, per 1M | $0.18 | $0.21 +17.2% |
| Lowest unit price | — | — |
| Cost of 1M in + 200k out | $0.17 +57.1% | $0.11 |
| Context | 164K | 131K +20% |
| Max output | 131K | 66K +50% |
| Providers | 8 | 7 +12.5% |
| Regions | US | EU, US |
| Accepts | image, text | text |
| Returns | text | text |
| Type | Moderation | Moderation |
| Free option | yes | no |
| Cheapest provider | kilo | 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
Frequently asked questions
Which is cheaper, Llama Guard 4 12B or GPT OSS Safeguard 20B?
GPT OSS Safeguard 20B is 51% cheaper than Llama Guard 4 12B on input price. Llama Guard 4 12B is 28% cheaper than GPT OSS Safeguard 20B on output price. GPT OSS Safeguard 20B is 36% cheaper than Llama Guard 4 12B on a 1M-in / 200k-out workload.
Which has the larger context, Llama Guard 4 12B or GPT OSS Safeguard 20B?
Llama Guard 4 12B: 164K tokens; GPT OSS Safeguard 20B: 131K tokens.
Where can I use both Llama Guard 4 12B and GPT OSS Safeguard 20B?
edenai, kilo, openrouter