large language
DeepSeek V3 0324
DeepSeek V3 0324A state-of-the-art 671B-parameter MoE LLM licensed for commercial use
Model details
View repositoryExample usage
DeepSeek V3 0324 runs using the Baseten Inference Stack and is accessible via an OpenAI-compatible API endpoint.
Input
1# You can use this model with any of the OpenAI clients in any language!
2# Simply change the API Key to get started
3
4from openai import OpenAI
5
6client = OpenAI(
7 api_key="YOUR_API_KEY",
8 base_url="https://inference.baseten.co/v1"
9)
10
11response = client.chat.completions.create(
12 model="deepseek-ai/DeepSeek-V3-0324",
13 messages=[
14 {
15 "role": "user",
16 "content": "Implement Hello World in Python"
17 }
18 ],
19 stream=True,
20 stream_options={
21 "include_usage": True,
22 "continuous_usage_stats": True
23 },
24 top_p=1,
25 max_tokens=1000,
26 temperature=1,
27 presence_penalty=0,
28 frequency_penalty=0
29)
30
31for chunk in response:
32 if chunk.choices and chunk.choices[0].delta.content is not None:
33 print(chunk.choices[0].delta.content, end="", flush=True)JSON output
1{
2 "id": "8456fe51db3548789f199cfb8c8efd35",
3 "object": "text_completion",
4 "created": 1735236968,
5 "model": "deepseek-ai/DeepSeek-V3-0324",
6 "choices": [
7 {
8 "index": 0,
9 "text": "FizzBuzz is a classic programming problem where you print numbers from 1 to 100...",
10 "logprobs": null,
11 "finish_reason": "stop",
12 "matched_stop": 1
13 }
14 ],
15 "usage": {
16 "prompt_tokens": 14,
17 "total_tokens": 240,
18 "completion_tokens": 226,
19 "prompt_tokens_details": null
20 }
21}
