LLM Reference
NVIDIA NIM

DeepSeek Coder 6.7B on NVIDIA NIM

DeepSeek Coder · DeepSeek

ProvisionedOpen Weights

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 case
Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: deepseek-coder-6.7b
Model ID
deepseek-coder-6.7b

Request example

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID 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

ProviderInput (per 1M)Output (per 1M)
Fireworks AI$0.20$0.20
NVIDIA NIM

Pricing

TypeRate
GPU Hour Rate$1.00/GPU·hr
GPU Config1xH100

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.

Get Started

Model Specs

Released2024-03-07
Parameters6.7B
Context4k
ArchitectureDecoder Only