Helicone alternative.
Observability plus the routing Helicone doesn't do.

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://oai.helicone.ai/v1",
    api_key="sk-openai-...",
    default_headers={
        "Helicone-Auth": "Bearer sk-helicone-...",
    },
)

r = client.chat.completions.create(
    model="gpt-5.4",
    messages=[{"role": "user", "content": "Hello"}],
)

# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI

client = OpenAI(
    base_url="https://api.aigateway.sh/v1",
    api_key="sk-aig-...",
)

r = client.chat.completions.create(
    model="openai/gpt-5.4",
    messages=[{"role": "user", "content": "Hello"}],
)

• Not a proxy — a real aggregator with 1150+ models under one schema.
• Eval-driven routing and replay, not just logs.
• Caching at the edge (exact + semantic), 50% off cached requests.
• Sub-account API for scoped keys per end user.
• First-class video, image, audio, voice endpoints — Helicone is text-only observability.

• Helicone's prompt-versioning UI is more mature; we match on Enterprise.