DeepSeek V3.1
deepseek/deepseek-v3.1
DeepSeek-V3.1 is a hybrid model that supports both thinking mode and non-thinking mode. DeepSeek-V3.1 is fine-tuned on top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint using a two-phase long-context extension approach, following the methodology outlined in the original DeepSeek-V3 report. We have expanded our dataset by collecting additional long documents and substantially extending both training phases. The 32K extension phase has been increased tenfold to 630 billion tokens, while the 128K extension phase has been extended by 3.3 times to 209 billion tokens.
Price
| Input | $0.27/百万 tokens |
| Cached writes(5m) | $1/百万 tokens |
| Cached reads | $1/百万 tokens |
| Output | $1/百万 tokens |
Use the following code example to integrate our API:
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="<Your API Key>",
5 base_url="https://api.jiekou.ai/openai"
6)
7
8response = client.chat.completions.create(
9 model="deepseek/deepseek-v3.1",
10 messages=[
11 {"role": "system", "content": "You are a helpful assistant."},
12 {"role": "user", "content": "Hello, how are you?"}
13 ],
14 max_tokens=32768,
15 temperature=0.7
16)
17
18print(response.choices[0].message.content)Information
Provider
Quantification
fp8
Supported features
Context length
163840
Maximum output
32768
Function call
Support
Structured output
Support
Reasoning
Support
serverless
Support
Input Capabilities
text
Output Capabilities
text