Last refreshed 2026-05-19. Next refresh: weekly.
Why use DeepSeek Coder 6.7B on NVIDIA NIM?
NVIDIA NIM offers DeepSeek Coder 6.7B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare DeepSeek Coder 6.7B 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: deepseek-coder-6.7bdeepseek-coder-6.7bRequest example
deepseek-coder-6.7b.Gotchas
No curated gotchas have been sourced for this exact provider/model route yet.
Compare DeepSeek Coder 6.7B Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Fireworks AI | $0.20 | $0.20 |
| NVIDIA NIM | — | — |
Pricing
| Type | Rate |
|---|---|
| GPU Hour Rate | $1.00/GPU·hr |
| GPU Config | 1xH100 |
Capabilities
No model capability flags are currently sourced.
About DeepSeek Coder 6.7B
DeepSeek Coder 6.7B is DeepSeek's DeepSeek Coder model focused on code generation and software engineering. It is deprecated (originally released 2024-03-07); use it only for reproducing earlier results or evaluating drift over time.
FAQ
What is the context window for DeepSeek Coder 6.7B on NVIDIA NIM?
DeepSeek Coder 6.7B supports a 4k token context window on NVIDIA NIM.
How does NVIDIA NIM compare to other DeepSeek Coder 6.7B providers?
DeepSeek Coder 6.7B is available from 2 providers. The cheapest input pricing is $0.20/1M tokens from Fireworks AI.
Who created DeepSeek Coder 6.7B?
DeepSeek Coder 6.7B was created by DeepSeek as part of the DeepSeek Coder model family.
Is DeepSeek Coder 6.7B open source?
DeepSeek Coder 6.7B has open weights under DeepSeek License according to the seed data, but that does not necessarily mean an OSI-approved open-source license.