Vergleichen und testen Sie Open-Weight-Modelle für Text, Code, Sprache und Bild – ohne Registrierung. Gehen Sie anschließend mit derselben OpenAI-kompatiblen API in Produktion.
gpt-oss-120b ist ein hochmodernes Modell, das für allgemeines Schlussfolgern (Reasoning), das Befolgen von Anweisungen und erweiterte Agent-Funktionen entwickelt wurde. Es glänzt in vielseitigen Use Cases und bietet starke Leistung sowohl für allgemeine als auch für spezialisierte Anwendungen.
First install the requests library:
pip install requestsNext, export your access token to the OVH_AI_ENDPOINTS_ACCESS_TOKEN environment variable:
export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>If you do not have an access token key yet, follow the instructions in the AI Endpoints – Getting Started.
Finally, run the following Python code:
import os
import requests
headers = {
"Content-Type": "application/json",
"Authorization": f"Bearer {os.getenv('OVH_AI_ENDPOINTS_ACCESS_TOKEN')}",
}
# With /chat/completions
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/chat/completions"
payload = {
"max_tokens": 512,
"messages": [
{
"content": "Explain gravity to a 6 years old",
"role": "user"
}
],
"model": "gpt-oss-120b",
"temperature": 0,
}
response = requests.post(url, json=payload, headers=headers)
if response.status_code == 200:
# Handle response
response_data = response.json()
# Parse JSON response
choices = response_data["choices"]
for choice in choices:
text = choice["message"]["content"]
# Process text and finish_reason
print(text)
reasoning_text = choice["message"]["reasoning_content"]
# Process reasoning_content
print(reasoning_text)
else:
print("Error:", response.status_code, response.text)
# With /responses
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1/responses"
payload = {
"max_output_tokens": 512,
"input": [
{
"content": "Explain gravity to a 12 years old",
"type": "message",
"role": "user"
}
],
"reasoning": {
"effort": "low"
},
"store": False,
"model": "gpt-oss-120b",
"temperature": 0,
}
response = requests.post(url, json=payload, headers=headers)
if response.status_code == 200:
# Handle response
response_data = response.json()
# Process reasoning_content
reasoning_content = response_data["output"][0]["content"][0]["text"]
print(f"** REASONING ** \n {reasoning_content}")
# Process text
text_content = response_data["output"][1]["content"][0]["text"]
print(f"** CONTENT ** \n {text_content}\n")
else:
print("Error:", response.status_code, response.text)The gpt-oss-120b API is compatible with the OpenAI specification.
First install the openai library:
pip install openaiNext, export your access token to the OVH_AI_ENDPOINTS_ACCESS_TOKEN environment variable:
export OVH_AI_ENDPOINTS_ACCESS_TOKEN=<your-access-token>Finally, run the following Python code:
import os
from openai import OpenAI
url = "https://oai.endpoints.kepler.ai.cloud.ovh.net/v1"
client = OpenAI(
base_url=url,
api_key=os.getenv("OVH_AI_ENDPOINTS_ACCESS_TOKEN")
)
def chat_completion(new_message: str) -> str:
history_openai_format = [{"role": "user", "content": new_message}]
choice = client.chat.completions.create(
model="gpt-oss-120b",
messages=history_openai_format,
temperature=0,
max_tokens=1024,
reasoning_effort="low", # Either low, medium, or high
).choices.pop()
print(f"** REASONING ** \n {choice.message.reasoning_content}\n")
print(f"** CONTENT ** \n {choice.message.content}")
def responses(new_message: str) -> str:
response_output = client.responses.create(
model="gpt-oss-120b",
input=new_message,
temperature=0,
max_output_tokens=1024,
store=False,
reasoning={"effort": "low"},
store=False
).output
reasoning_content = response_output[0].content[0]["text"]
print(f"** REASONING ** \n {reasoning_content}")
text_content = response_output[1].content[0].text
print(f"** CONTENT ** \n {text_content}\n")
if __name__ == '__main__':
# With chat completion endpoint
chat_completion("Explain gravity for a 6 years old")
# With responses endpoint
responses("Explain gravity for a 12 years old")When using AI Endpoints, the following rate limits apply:
If you exceed this limit, a 429 error code will be returned.
If you require higher usage, please get in touch with us to discuss increasing your rate limits.
Want to explore the full capabilities of the LLM API? Dive into our dedicated Structured Output and Function Calling guides.
For a broader overview of AI Endpoints, explore the full AI Endpoints Documentation.
Reach out to our support team or join the OVHcloud Discord #ai-endpoints channel to share your questions, feedback, and suggestions for improving the service, to the team and the community.
New to AI Endpoints? This guide walks you through everything you need to get an access token, call AI models, and integrate AI APIs into your apps with ease.
Tutorial startenExplore what AI Endpoints can do. This guide breaks down current features, future roadmap items, and the platform's core capabilities so you know exactly what to expect.
Tutorial startenRunning into issues? This guide helps you solve common problems on AI Endpoints, from error codes to unexpected responses. Get quick answers, clear fixes, and helpful tips to keep your…
Tutorial startenLearn how to use Structured Output with OVHcloud AI Endpoints.
Tutorial startenLearn how to use Function Calling with OVHcloud AI Endpoints.
Tutorial startenLearn how to use OVHcloud AI Endpoints Virtual Models.
Tutorial starten