We are partnering with MiniMax to bring MiniMax M2.7 to Lilac.
Serverless inference, no cold starts.
Shared endpoints backed by idle enterprise GPUs. Warm capacity and token pricing — no dedicated GPUs to manage.
Pay per token. No commitments.
Shared warm endpoints across our open-weight model catalog — no container spin-up, no cold starts.
| Model | Status | Context | Input | Cache | Output |
|---|---|---|---|---|---|
| MiniMax M2.7 | Live now | FP8 | 200K | $0.30/M | $0.055/M |
| Kimi K2.6 | Live now | INT4 | 262K | $0.70/M | $0.20/M |
| GLM 5.1 | Live now | FP8 | 203K | $0.90/M | $0.27/M |
| Gemma 4 (31B) | Live now | BF16 | 262K | $0.11/M | - |
More models are coming soon and will be added as they go live.
One base URL change.
Keep the OpenAI SDK and point it at Lilac. Your existing code just works.
from openai import OpenAI
client = OpenAI(
base_url="<BASE_URL>",
api_key="sk_...",
)
response = client.chat.completions.create(
model="openai/gpt-5.4",
messages=[{"role": "user","content": "Hello!"}],
)
Start running inference in minutes.
No contracts, no commitments. Swap your base URL and pay less for the same output quality.
Frequently asked questions
Is this really serverless?
Yes. No infrastructure to provision or maintain — just an API call.
How do you avoid cold starts?
Traffic routes to already-running shared capacity, not freshly spun containers.