Fireworks AI alternative.
Fireworks speed, plus the frontier catalog it doesn't have.

from fireworks.client import Fireworks

client = Fireworks(api_key="fw_...")

r = client.chat.completions.create(
    model="accounts/fireworks/models/llama-4-scout",
    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="meta/llama-4-scout-17b-16e-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)

• Frontier + open-weight under one schema — you stop maintaining two integrations.
• Every modality, including voice, audio, music, STT — not just text + image.
• Sub-account API, cost-tags, eval-driven routing — Fireworks is provider-only.
• 5% flat fee at top-up; pass-through pricing otherwise.
• OpenAI-compatible — no Fireworks-specific SDK, just change base_url.

• Fireworks has custom-model hosting and fine-tune-as-a-service; roadmap on Enterprise.