Last refreshed 2026-05-14. Next refresh: weekly.
Why use Llama 3.1 Nemotron 70B Reward on NVIDIA NIM?
NVIDIA NIM offers Llama 3.1 Nemotron 70B Reward with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: nvidia/llama-3.1-nemotron-70b-rewardModel ID
nvidia/llama-3.1-nemotron-70b-rewardRequest example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
nvidia/llama-3.1-nemotron-70b-reward.Gotchas
- Use provider model ID "nvidia/llama-3.1-nemotron-70b-reward", not the LLMReference slug "llama-3.1-nemotron-70b-reward".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 4xH100 |
Capabilities
No model capability flags are currently sourced.
About Llama 3.1 Nemotron 70B Reward
NVIDIA reward model based on Llama 3.1 70B, used for RLHF and preference ranking.
FAQ
What is the context window for Llama 3.1 Nemotron 70B Reward on NVIDIA NIM?
Llama 3.1 Nemotron 70B Reward supports a 4,000 token context window on NVIDIA NIM.
What API model ID do I use for Llama 3.1 Nemotron 70B Reward on NVIDIA NIM?
Use the model ID nvidia/llama-3.1-nemotron-70b-reward when calling NVIDIA NIM's API.
Who created Llama 3.1 Nemotron 70B Reward?
Llama 3.1 Nemotron 70B Reward was created by NVIDIA AI as part of the Nemotron 3 model family.
Is Llama 3.1 Nemotron 70B Reward open source?
Llama 3.1 Nemotron 70B Reward is open source according to the seed data.
Model Specs
Released2024-10-01
Parameters70B
Context4K
ArchitectureDecoder Only