DeepSeek Coder 6 7B Instruct
Open weights
API id
deepseek-coder-6.7b-instructInput / 1M
-
not listed
Output / 1M
-
not listed
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published
Where to run it
1 host serve DeepSeek Coder 6 7B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
NVIDIA NIMInference deepseek-coder-6.7b-instruct | - | deepseek-coder-6.7b-instruct |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: DeepSeek License (MIT code)Runtimes: SGLang, TGI, vLLM
Similar models
This model has no listed price, so these are current models with similar capabilities.
Smaller DeepSeek models
No similar DeepSeek model keeps its key capabilities.
Other frontier labs
Open-weight picks
Model line
Newer and older versions, at each lab's own price.
- UndatedDeepSeek Coder 6 7B InstructLatestNot listed
- UndatedDeepSeek Coder 7B Instruct V1.5$0.20 / $0.20
Call it
Using NVIDIA NIM's API.
Python
from litellm import completion
response = completion(
model="nvidia_nim/deepseek-coder-6.7b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
Which APIs offer DeepSeek Coder 6 7B Instruct?
DeepSeek Coder 6 7B Instruct runs on 1 API: NVIDIA NIM.
Is DeepSeek Coder 6 7B Instruct being retired?
No retirement date is scheduled for it on any API we track.
Is there a newer version of DeepSeek Coder 6 7B Instruct?
No. DeepSeek Coder 6 7B Instruct is the newest model in its line.
What is DeepSeek Coder 6 7B Instruct's API model id?
Use deepseek-coder-6.7b-instruct with NVIDIA NIM.
Sources
Raw catalog entry for deepseek-coder-6.7b-instruct on NVIDIA NIM
{
"litellm_provider": "nvidia_nim",
"source": "https://integrate.api.nvidia.com/v1/models"
}