// documentation
Everything you need to ship.
Quickstart in five minutes. Full API reference with typed schemas. SDKs for Python, Node, Go, and Rust. Guides for common patterns.
// five lines to first token
from openai import OpenAI
client = OpenAI(
base_url="https://api.uat.clusterbid.com/v1",
api_key="CLUSTERBID_API_KEY",
)
response = client.chat.completions.create(
model="llama-3.1-405b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)// core reference
Start here.
getting started
Quickstart
API key, first request, streaming, and region selection — working in five minutes.
reference
API Reference
Full OpenAI-compatible Chat Completions spec. All parameters, all response shapes, all error codes.
reference
Model Catalog
Per-model context windows, pricing, region availability, license, and best-for guidance.
infrastructure
Regions and Routing
How region pinning works in code. Base URLs per region. Failover behavior. Testing residency.
fine-tuning
Managed Fine-Tuning
JSONL format, dataset upload, hyperparameters, cost preview, adapter deployment.
dedicated
Dedicated Deployments
Node selection, provisioning, drain, scaling, and migration from the shared API.
// sdks
Use any OpenAI-compatible client.
Python
openai>=1.0 · pip install openai
Node / TS
openai@^4 · npm install openai
Go
openai-go · go get github.com/openai/openai-go
Rust
async-openai · cargo add async-openai
// guides
Common patterns.
Region pinning and data residency
Streaming with server-sent events
Function calling with Llama-3.1
JSON mode and structured output
Rate limits and retry backoff
Migrating from OpenAI to clusterbid
RAG with long-context models
Cost estimation and budgeting
Fine-tuning a domain classifier
Audit logs and compliance exports