Last refreshed 2026-05-01. Next refresh: weekly.
Why use Llama 3 Swallow 70B Instruct on NVIDIA NIM?
NVIDIA NIM offers Llama 3 Swallow 70B Instruct 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: tokyotech-llm/llama-3-swallow-70b-instruct-v0.1Model ID
tokyotech-llm/llama-3-swallow-70b-instruct-v0.1Request example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
tokyotech-llm/llama-3-swallow-70b-instruct-v0.1.Gotchas
- Use provider model ID "tokyotech-llm/llama-3-swallow-70b-instruct-v0.1", not the LLMReference slug "llama-3-swallow-70b-instruct".
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 4xH100 |
Capabilities
No model capability flags are currently sourced.
About Llama 3 Swallow 70B Instruct
Japanese bilingual model from Tokyo Tech, fine-tuned from Llama 3 70B.
FAQ
What is the context window for Llama 3 Swallow 70B Instruct on NVIDIA NIM?
Llama 3 Swallow 70B Instruct supports a 4,000 token context window on NVIDIA NIM.
What API model ID do I use for Llama 3 Swallow 70B Instruct on NVIDIA NIM?
Use the model ID tokyotech-llm/llama-3-swallow-70b-instruct-v0.1 when calling NVIDIA NIM's API.
Who created Llama 3 Swallow 70B Instruct?
Llama 3 Swallow 70B Instruct was created by Tokyo Institute of Technology as part of the Swallow model family.
Is Llama 3 Swallow 70B Instruct open source?
Llama 3 Swallow 70B Instruct is open source according to the seed data.
Model Specs
Released2024-06-01
Parameters70B
Context4K
ArchitectureDecoder Only