Llama 3.1 Swallow 70B Instruct on NVIDIA NIM
Swallow · Tokyo Institute of Technology
ServerlessOpen Weights
Last refreshed 2026-06-30. Next refresh: weekly.
Why use Llama 3.1 Swallow 70B Instruct on NVIDIA NIM?
NVIDIA NIM offers Llama 3.1 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: institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1Model ID
institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1Request example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1.Gotchas
- Use provider model ID "institute-of-science-tokyo/llama-3.1-swallow-70b-instruct-v0.1", not the LLMReference slug "llama-3.1-swallow-70b-instruct".
Capabilities
No model capability flags are currently sourced.
About Llama 3.1 Swallow 70B Instruct
Japanese bilingual model from Institute of Science Tokyo, fine-tuned from Llama 3.1.
Model Specs
Released2025-01-01
Parameters70B
Context4k
ArchitectureDecoder Only
Knowledge cutoff2023