Anfragen an DeepSeek-Modelle stellen

Arbeiten mit DeepSeek in Python

James Chapman

AI Curriculum Lead, DataCamp

Rückblick

Ein Computer sendet eine Anfrage an die Together.ai-API, die das Modell sowie Daten und Modellparameter enthält.

Eine Anfrage erstellen

from openai import OpenAI

# An DeepSeek-API senden: base_url="https://api.deepseek.com"
client = OpenAI(api_key="<TogetherAI API Key>", base_url="https://api.together.xyz/v1")

Anfragen mit der Bibliothek openai erstellen
OpenAI: Entwickler von KI-Modellen und -Apps (z. B. ChatGPT)
base_url: Anfrage vom OpenAI- zum DeepSeek-Provider umleiten
api_key: API-Authentifizierung (siehe Doku des Providers)

¹ https://platform.deepseek.com/api_keys

Eine Anfrage erstellen

from openai import OpenAI
# An DeepSeek-API senden: base_url="https://api.deepseek.com"
client = OpenAI(api_key="<TogetherAI API Key>", base_url="https://api.together.xyz/v1")


response = client.chat.completions.create(

    model="deepseek-ai/DeepSeek-V4.1-Flash",

    messages=[{"role": "user",
               "content": "In one sentence, what is hallucination in AI?"}]

)


print(response)

Die Antwort

ChatCompletion(id='onVWeEx-gBAtS-a09121fcae54578c', choices=[Choice(finish_reason='stop', index=0,
logprobs=None, message=ChatCompletionMessage(content='Hallucination in AI is when a model confidently
generates information that sounds plausible but is factually incorrect, misleading, or entirely
fabricated.', refusal=None, role='assistant', annotations=None, audio=None, function_call=None,
tool_calls=[]), seed=None)], created=1781018557, model='deepseek-ai/DeepSeek-V4.1-Flash',
object='chat.completion', moderation=None, service_tier=None, system_fingerprint='default',
usage=CompletionUsage(completion_tokens=28, prompt_tokens=15, total_tokens=43,
completion_tokens_details=None, prompt_tokens_details=PromptTokensDetails(audio_tokens=None,
cached_tokens=0)), prompt=[])

Die Antwort

ChatCompletion(id='onVWeEx-gBAtS-a09121fcae54578c',
               choices=[Choice(finish_reason='stop', index=0, logprobs=None,
                               message=ChatCompletionMessage(content='Hallucination in AI refers...',
                               refusal=None, role='assistant', annotations=None, audio=None,
                               function_call=None, tool_calls=[]), seed=None)],
               created=1781018557,
               model='deepseek-ai/DeepSeek-V4.1-Flash',
               object='chat.completion',
               moderation=None,
               service_tier=None,
               system_fingerprint='default',
               usage=CompletionUsage(completion_tokens=28, prompt_tokens=15, total_tokens=43,
                                     completion_tokens_details=None,
                                     prompt_tokens_details=PromptTokensDetails(audio_tokens=None,
                                          cached_tokens=0)),
               prompt=[])

Die Antwort interpretieren

print(response.choices)

[Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(
content='Hallucination in AI refers to the generation of false or nonsensical information
that is presented as factual, often due to limitations in training data, model biases, or
inference errors.', refusal=None, role='assistant', annotations=None, audio=None,
function_call=None, tool_calls=[]), seed=None)]

Die Antwort interpretieren

print(response.choices[0])

Choice(finish_reason='stop', index=0, logprobs=None, message=ChatCompletionMessage(
content='Hallucination in AI refers to the generation of false or nonsensical information
that is presented as factual, often due to limitations in training data, model biases, or
inference errors.', refusal=None, role='assistant', annotations=None, audio=None,
function_call=None, tool_calls=[]), seed=None)

Die Antwort interpretieren

print(response.choices[0].message)

ChatCompletionMessage(content='Hallucination in AI refers to the generation of false or
nonsensical information that is presented as factual, often due to limitations in training
data, model biases, or inference errors.', refusal=None, role='assistant', annotations=None,
audio=None, function_call=None, tool_calls=[])

print(response.choices[0].message.content)

Hallucination in AI refers to the generation of false or nonsensical information that is
presented as factual, often due to limitations in training data, model biases, or inference
errors.

API-Nutzungskosten

Für DeepSeek:
- Provider (z. B. together.ai)
- Modell
- Größere Eingaben + Ausgaben = höhere Kosten

Eine Mautstraße.

¹ https://api-docs.deepseek.com/quick_start/pricing

Lass uns üben!

Arbeiten mit DeepSeek in Python