Build with model APIs
Call models through one API, compare capabilities and pricing, and track every request.
ExploreAccess models through one API, earn from API services and GPU capacity, and manage enterprise tokens, budgets and local models with AIGate.
Call models through one API, compare capabilities and pricing, and track every request.
ExploreSupply API services or GPU capacity after integration testing and review.
ExploreManage budgets and access across cloud APIs and local models.
ExploreKeep your SDK. Set the base URL and choose a model ID. Track spend, requests and cache billing by model and key.
from openai import OpenAI
client = OpenAI(
base_url="https://api.openllm.dev/v1",
api_key="YOUR_API_KEY"
)
models = client.models.list()
# Choose an available model ID from the catalog.
print([model.id for model in models.data])Manage purchased APIs, team budgets, employee keys and local models together. Configure and review spare capacity for platform supply, with internal workloads taking priority.