MiniMax M2.7 API

    MiniMax M2.7 API.

    $0.30/M input, $0.055/M cached input, $1.20/M output (FP8) for coding agents and tool-use workloads.

    Get Started

    Point your OpenAI SDK at api.getlilac.com/v1 and request minimaxai/minimax-m2.7.

    Model pricing

    Pay per token. No commitments.

    Lilac served MiniMax M2.7 at a sustained 60 tok/s/user at 160-way concurrency, with 100% request success, 98.80% tool-call match, 99.80% schema accuracy, and 0% error-only reasoning in the MiniMax Provider Verifier.

    Model
    Context
    Input
    Cache
    Output
    MiniMax M2.7

    Live now

    FP8
    200K
    $0.30/M
    $0.055/M
    $1.20/M
    Kimi K2.6

    Live now

    INT4
    262K
    $0.70/M
    $0.20/M
    $3.50/M
    GLM 5.1

    Live now

    FP8
    203K
    $0.90/M
    $0.27/M
    $3.00/M
    Gemma 4 (31B)

    Live now

    BF16
    262K
    $0.11/M
    -
    $0.35/M
    OpenAI-compatibleShared warm endpointsNo contractsNo minimums

    More models are coming soon and will be added as they go live.

    Integration

    One base URL change.

    Keep the OpenAI SDK and point it at Lilac. Your existing code just works.

    inference.py

    from openai import OpenAI

    client = OpenAI(

    base_url="https://api.openai.com/v1",

    api_key="sk_...",

    )

    response = client.chat.completions.create(

    model="openai/gpt-5.4",

    messages=[{"role": "user", "content": "Hello!"}],

    )

    # Same code. Same SDK. Fraction of the price.

    01

    Standard OpenAI client -- just change the base URL.

    02

    Commercially licensed MiniMax access through Lilac.

    03

    Built for coding, long-horizon tasks, and tool-heavy agents.

    Frequently asked questions

    How do I call the API?

    Set base_url to https://api.getlilac.com/v1 in the OpenAI SDK, model name minimaxai/minimax-m2.7.

    How much does it cost?

    $0.30/M input, $0.055/M cached input, and $1.20/M output.

    Can I use MiniMax M2.7 commercially through Lilac?

    Yes. Lilac hosts MiniMax M2.7 commercially through our partnership with MiniMax.

    Start running inference in minutes.

    No contracts, no commitments. Swap your base URL and pay less for the same output quality.

    Get Started

    No commitment required.