Last refreshed 2026-05-19. Next refresh: weekly.
Why use Nemotron 4 340B on NVIDIA NIM?
NVIDIA NIM offers Nemotron 4 340B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare Nemotron 4 340B across 2 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: nemotron-4-340bnemotron-4-340bRequest example
nemotron-4-340b.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare Nemotron 4 340B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| DeepInfra | $4.20 | $4.20 |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
Capabilities
About Nemotron 4 340B
Nemotron 4 340B is NVIDIA AI's Nemotron-4 model. It is deprecated (originally released 2025-02-27); use it only for reproducing earlier results or evaluating drift over time.
FAQ
What is the context window for Nemotron 4 340B on NVIDIA NIM?
Nemotron 4 340B supports a 4k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other Nemotron 4 340B providers?
Nemotron 4 340B is available from 2 providers. The cheapest input pricing is $4.20/1M tokens from DeepInfra.
Who created Nemotron 4 340B?
Nemotron 4 340B was created by NVIDIA AI as part of the Nemotron-4 model family.
Is Nemotron 4 340B open source?
Nemotron 4 340B has open weights under NVIDIA Open Model according to the seed data, but that does not necessarily mean an OSI-approved open-source license.