FAST & FRUGAL · 薄
Llama
5 models from Meta, living in Silvergrass Fields.
| Model | Context | Input | Output | Accepts |
|---|---|---|---|---|
| Llama Guard 4 12Bmeta-llama/llama-guard-4-12b | 164K | $0.180 | $0.180 | text, images |
| Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | 131K | $0.100 | $0.320 | text |
| Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct | 60K | $0.030 | $0.200 | text |
| Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instruct | 131K | $0.050 | $0.340 | text |
| Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | 131K | $0.050 | $0.080 | text |
Questions and answers
Which Llama model has the largest context window?
Llama Guard 4 12B (Meta), with 164K tokens.
Which Llama model is cheapest per input token?
Llama 3.2 1B Instruct, at $0.030 per million input tokens ($0.200 per million output tokens).
Which Llama models accept images?
Llama Guard 4 12B (1 of 5).
Which Llama models support reasoning?
None in the 2026-10-24 snapshot.
Answers are computed from the 2026-10-24 catalog snapshot.