deepseek
DeepSeek DeepSeek V3.1
deepseek/deepseek-chat-v3.1
Input$0.210 /1M tokens
·Output$0.790 /1M tokens
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Code Examples
import requests
response = requests.post(
"https://neurongate.net/v1/chat/completions",
headers={
"Authorization": "Bearer ng-your-api-key",
"Content-Type": "application/json"
},
json={
"model": "deepseek/deepseek-chat-v3.1",
"messages": [
{"role": "user", "content": "Hello!"}
]
}
)
print(response.json()["choices"][0]["message"]["content"])Pricing Details
| Example | Cost |
|---|---|
| 1K input tokens (short prompt) | $0.00021 |
| 1K in + 500 out (typical response) | $0.00061 |
| 10K in + 2K out (document analysis) | $0.00368 |
| 100K in + 10K out (large context) | $0.0289 |
Prices in USD. Billed per actual token usage. Prepay with USDT, USDC, ETH, or BTC.
Frequently Asked Questions
Capabilities
Streaming
YesFunction Calling / Tools
YesVision (Image Input)
NoAudio Processing
NoContext Window
164K tokens
~123K words of text
Max output
33K tokens
Modalities
Input
text
Output
text