Doubleword
    Total Cost Control

    Scale smarter with latency-based pricing.

    The same model at three speeds. Choose realtime, async or 24-hour batch, and pay less the longer you can wait.

    VOLUME DISCOUNTS

    Need guaranteed, high-volume, high-throughput capacity without rate limits? We provide dedicated throughput for volume customers - with significant volume discounts and guaranteed performance SLAs.

    Talk to us about dedicated capacity →

    Realtime, async and batch inference pricing

    Model44.8intelligence score 44.8

    Low latency inference for short running agents and high priority tasks.

    response = client.chat.completions.create(
    model="zai-org/GLM-5.3",
    messages=messages,
    )
    Cost per 1B in + 1B out
    $5.8K
    Full price, zero wait
    The closed source equivalent
    GPT-5.6 Sol max47intelligence score 47
    Costs $24K realtime.
    You save $18K
    Pay 4.1x less
    INFERENCE ENGINEERING

    Pushing the frontier of Inference Engineering

    Doubleword contributes to the frontier of inference optimization research - building every level of the stack from kernels to scheduling to offer the most efficient inference for high volume workloads.

    Pricing that scales with your workload.

    Choose the model that best fits your business needs.

    Self-Service Inference

    Pay-as-you-go

    Whenever you need it, at the speed and cost that best fits your workload.

    Get started
    • Access to all major open-weight models
    • Usage-based pricing with prepaid credits
    • Prompt caching, tool calling and structured outputs
    • High-throughput async and batch inference
    • Zero Data Retention (ZDR) included
    • Community and standard support

    Dedicated Inference

    Guaranteed capacity

    For specialized workloads requiring dedicated engineering and white-glove support.

    Talk to us
    • Everything available to self-service
    • Dedicated infrastructure for guaranteed, high-throughput real-time capacity without rate limits
    • Custom models
    • Workload-specific inference optimization (e.g., speculators) for improved throughput and reduced token costs
    • Region-locked data processing (e.g., US or EU-based inference)
    • Engineering support for workload optimization
    • White-glove onboarding & Proof of Concept (PoC) support
    • Volume pricing
    • Signed MSA, DPA, and Custom SLAs

    FAQs

    Let there be tokens

    Try Doubleword's OpenAI compatible APIs and get frontier-level intelligence at a fraction of the cost.