Last refreshed 2026-05-19. Next refresh: weekly.
Why use Dracarys Llama 3.1 70B Instruct on NVIDIA NIM?
NVIDIA NIM offers Dracarys Llama 3.1 70B Instruct with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Setup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: meta/llama-3.1-70b-instructmeta/llama-3.1-70b-instructRequest example
meta/llama-3.1-70b-instruct.Gotchas
- Use provider model ID "meta/llama-3.1-70b-instruct", not the LLMReference slug "dracarys-llama-3.1-70b-instruct".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 4xH100 |
Capabilities
No model capability flags are currently sourced.
About Dracarys Llama 3.1 70B Instruct
Abacus AI Dracarys fine-tune of Llama 3.1 70B for enhanced instruction following.
FAQ
What is the context window for Dracarys Llama 3.1 70B Instruct on NVIDIA NIM?
Dracarys Llama 3.1 70B Instruct supports a 8k token context window on NVIDIA NIM.
What API model ID do I use for Dracarys Llama 3.1 70B Instruct on NVIDIA NIM?
Use the model ID meta/llama-3.1-70b-instruct when calling NVIDIA NIM's API.
Who created Dracarys Llama 3.1 70B Instruct?
Dracarys Llama 3.1 70B Instruct was created by Abacus.AI as part of the Dracarys model family.
Is Dracarys Llama 3.1 70B Instruct open source?
Dracarys Llama 3.1 70B Instruct has open weights under Llama 3 Community according to the seed data, but that does not necessarily mean an OSI-approved open-source license.