Last refreshed 2026-05-20. Next refresh: weekly.
Why use DeepSeek V3.2 on NVIDIA NIM?
NVIDIA NIM offers DeepSeek V3.2 with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare DeepSeek V3.2 across 7 providers to find the best fit for your use caseSetup recipe
Docs fallbackUse the provider REST API or SDKCreate a provider API keymodel: deepseek-ai/deepseek-v3_2deepseek-ai/deepseek-v3_2Request example
deepseek-ai/deepseek-v3_2.Gotchas
- Use provider model ID "deepseek-ai/deepseek-v3_2", not the LLMReference slug "deepseek-v3.2".
Compare DeepSeek V3.2 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.56 | $1.68 |
| NVIDIA NIM | — | — |
| AWS Bedrock | $0.62 | $1.85 |
| OpenRouter | $0.25 | $0.38 |
| Microsoft Foundry | — | — |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
About DeepSeek V3.2
DeepSeek V3.2 is DeepSeek's DeepSeek V3 model. It offers a 160K-token context window with weights openly available for self-hosting and scores 70 on SWE-bench Verified.
FAQ
What is the context window for DeepSeek V3.2 on NVIDIA NIM?
DeepSeek V3.2 supports a 160k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other DeepSeek V3.2 providers?
DeepSeek V3.2 is available from 7 providers. The cheapest input pricing is $0.252/1M tokens from OpenRouter.
What API model ID do I use for DeepSeek V3.2 on NVIDIA NIM?
Use the model ID deepseek-ai/deepseek-v3_2 when calling NVIDIA NIM's API.
Who created DeepSeek V3.2?
DeepSeek V3.2 was created by DeepSeek as part of the DeepSeek V3 model family.
Is DeepSeek V3.2 open source?
DeepSeek V3.2 is open source under MIT according to the seed data.