from gradient import Gradient
inference_key = "YOUR_GRADIENT_INFERENCE_KEY"
inference_client = Gradient(
inference_key=inference_key,
)
inference_response = inference_client.chat.completions.create(
messages=[{
"role": "user",
"content": "What is the capital of France?",
}
],
model="openai-gpt-5",
)
print(inference_response.choices[0].message.content)
Why GPT-5?
The latest model from OpenAI, GPT-5 brings major improvements in reasoning, specialization, and overall performance. It excels at complex tasks like financial planning, medical document analysis, code generation, and creative content creation. Whether you’re building advanced copilots, research tools, or generative experiences, GPT-5 makes it easier to deliver high-quality, domain-aware results, faster and with greater accuracy.
Agent-ready: Use GPT-5 as the brain behind your Gradient AI Platform agents.
BYO OpenAI Key: Prefer your own OpenAI billing setup? No problem. You can bring your own OpenAI key and use GPT-5 within your Gradient AI Platform agent workflow
Deploy today
This release is ideal for developers who need production-ready access to cutting-edge models without GPU setup or model management.
You can start using GPT-5 on the Gradient AI Platform now:
Amit is a Developer Advocate at DigitalOcean 🐳, where he helps developers build and ship better apps on the cloud. Compulsive Seinfeld quoter. LEGO nerd. 🧱 AMA.
From GPU-powered inference and Kubernetes to managed databases and storage, get everything you need to build, scale, and deploy intelligent applications.