Pricing
| Tier | Pricing | Cache Read |
|---|---|---|
Tier | Pricing | Cache Read |
| Off-peak · 01:00–04:00, 06:00–10:00 UTC | $0.154$0.308 | $0.0013/M tokens |
| Peak · 10:00–01:00, 04:00–06:00 UTC | $0.308$0.616 | $0.0026/M tokens |
Input Modalities
- Text
Output Modalities
- Text
Capabilities
- Tools
- Tool calling
- Structured outputs
Try this model
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["AIHUBMIX_API_KEY"],
base_url="https://shkq.org/v1",
)
response = client.chat.completions.create(
model="deep-deepseek-v4-flash",
messages=[
{
"role": "user",
"content": "Hello, how are you?"
}
],
max_tokens=1024,
stream=False,
)
print(response.choices[0].message.content)Frequently asked questions
What is Deep Deepseek V4 Flash?
How much does Deep Deepseek V4 Flash cost?
What modalities does Deep Deepseek V4 Flash support?
What capabilities does Deep Deepseek V4 Flash support?
How do I call Deep Deepseek V4 Flash via API?
Who created Deep Deepseek V4 Flash?
Compare Deep Deepseek V4 Flash
More models from DeepSeek
See all DeepSeek models →DeepSeek-V3.2-Exp
DeepSeek-V3.2-Exp
The model DeepSeek-V3.2-Exp is officially named deepseek-chat on the website. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating
DeepSeek V3.2 is DeepSeek's text large language model, designed for reasoning tasks and agentic tool use. It harmonizes high computational efficiency with strong reasoning performance through DeepSeek Sparse Attention (DSA), while providing native support for tools, function calling, and structured outputs.
The model DeepSeek-V3.2-Exp is officially named deepseek-chat on the website. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating
The model DeepSeek-V3.2-Exp-Think is officially named deepseek-reasoner. It is an experimental version. As an intermediate step towards the next-generation architecture, V3.2-Exp introduces DeepSeek Sparse Attention (a sparse attention mechanism) based on V3.1-Terminus, exploring and validating exploratory optimizations for training and inference efficiency on long texts.
© 2023 - 2026 AIHubMix, LLC