Model comparison
Llama 3.1 70B Dracarys 2 vs dracarys-llama-3.1-70b-instruct
Compare Llama 3.1 70B Dracarys 2 and dracarys-llama-3.1-70b-instruct: input/output $/Mtoken, context window, modalities, and license. OpenRouter-synced pricing.
Abacusai
Llama 3.1 70B Dracarys 2
Open Llama instruction model for multilingual chat, reasoning, and coding
Abacusai
dracarys-llama-3.1-70b-instruct
Open Llama instruction model for multilingual chat, reasoning, and coding
| Metric | Llama 3.1 70B Dracarys 2 | dracarys-llama-3.1-70b-instruct |
|---|---|---|
| Provider | Abacusai | Abacusai |
| Context window | 16,384 | 128,000 |
| Input $/Mtok | $0.493 | $0 |
| Output $/Mtok | $0.493 | $0 |
| Modalities | text | text |
| License | closed | open-weights |
Quick take
On input price, dracarys-llama-3.1-70b-instruct is cheaper at $0/Mtok. For context window, dracarys-llama-3.1-70b-instruct leads with 128,000 tokens.
Pick based on your workload: high-volume cheap inference vs long-document / agent loops. Enterprise DNA can wire either model into Omni with evals, secrets, and job orchestration.