Doubleword
    Pricing

    Same intelligence. Up to 99% cheaper.

    One API. Open-weight models. Pick your delivery window — Async or Overnight — and pay only for what you use.

    Start building — freeTalk to sales
    Per-token pricing

    Same Intelligence. Fraction of the price.

    Cost to process 1 billion tokens in + 1 billion tokens out at comparable intelligence.

    Model
    Anthropic
    $30K
    OpenAI
    $15.8K
    Industry Average
    $5.2K
    Doubleword
    $4.1K
    $0$7.5K$15K$22.5K$30K

    Intelligence via Artificial Analysis Index v4.0 · Hover any bar for full pricing details · Want access to a model you don't see here — just ask us!

    No credit card required · No minimum spend · Pay only for tokens used

    Start building

    Three speeds. One API.

    Pick the delivery window that fits your workflow. All tiers use the same OpenAI-compatible API.

    Real Time

    Iterate on prompts with real-time responses. Full price, zero wait.

    Async Inference

    up to 50% off RT

    Background agents that need results fast. High throughput inference.

    Overnight (~24 hours)

    up to 80% off RT

    Big batch jobs where cost matters most. Deepest discounts.

    Full pricing

    Model-by-model breakdown

    ModelSLAInput $/MTokOutput $/MTokCost / 1B in+outvs Big Token
    DeepSeek-V4-ProNewHigh throughput API$1.31$2.75$4.1K86% cheaperTry Model API
    ↳Batch$1.05$2.20$3.3K89% cheaper
    DeepSeek-V4-FlashNewHigh throughput API$0.10$0.20$30089% cheaperTry Model API
    ↳Batch$0.07$0.14$21093% cheaper
    Kimi-K2.6NewHigh throughput API$0.70$3.00$3.7K79% cheaperTry Model API
    ↳Batch$0.45$2.00$2.5K86% cheaper
    GLM-5.2-FP8NewHigh throughput API$1.05$3.30$4.3K76% cheaperTry Model API
    ↳Batch$0.70$2.20$2.9K84% cheaper
    GLM-5.1-FP8High throughput API$1.05$3.30$4.3K76% cheaperTry Model API
    ↳Batch$0.70$2.20$2.9K84% cheaper
    Qwen3.5-397B-A17BHigh throughput API$0.30$1.80$2.1K93% cheaperTry Model API
    ↳Batch$0.15$1.20$1.3K96% cheaper
    Qwen3.6-35B-A3B-FP8NewHigh throughput API$0.07$0.30$37098% cheaperTry Model API
    ↳Batch$0.05$0.20$25099% cheaper
    Qwen3.5-35B-A3B-FP8High throughput API$0.07$0.30$37094% cheaperTry Model API
    ↳Batch$0.05$0.20$25096% cheaper
    Qwen3.5-4BHigh throughput API$0.05$0.08$13099% cheaperTry Model API
    ↳Batch$0.04$0.06$10099% cheaper
    Qwen3.5-9BHigh throughput API$0.04$0.35$39094% cheaperTry Model API
    ↳Batch$0.03$0.29$32095% cheaper
    Gemma-4-31BNewHigh throughput API$0.11$0.30$41093% cheaperTry Model API
    ↳Batch$0.07$0.20$27096% cheaper
    Nemotron-3-Ultra-550B-A55BNewHigh throughput API$0.37$1.87$2.2K93% cheaperTry Model API
    ↳Batch$0.25$1.25$1.5K95% cheaper
    Nemotron-3-Super-120B-A12BHigh throughput API$0.23$0.56$79087% cheaperTry Model API
    ↳Batch$0.15$0.38$53091% cheaper
    GPT-OSS-20BHigh throughput API$0.03$0.20$23098% cheaperTry Model API
    ↳Batch$0.02$0.15$17098% cheaper
    Qwen3-VL-235B-A22BHigh throughput API$0.15$0.55$70069% cheaperTry Model API
    ↳Batch$0.10$0.40$50078% cheaper
    Qwen3-VL-30B-A3BHigh throughput API$0.07$0.30$37075% cheaperTry Model API
    ↳Batch$0.05$0.20$25083% cheaper
    Qwen3-14B-FP8High throughput API$0.03$0.30$33078% cheaperTry Model API
    ↳Batch$0.02$0.20$22085% cheaper
    DeepSeek-OCR-2OCRHigh throughput API$0.08$0.08$160—Try Model API
    ↳Batch$0.05$0.05$100—
    olmOCR-2-7BOCRHigh throughput API$0.15$0.15$300—Try Model API
    ↳Batch$0.10$0.10$200—
    LightOnOCR-2-1BOCRHigh throughput API$0.08$0.08$160—Try Model API
    ↳Batch$0.05$0.05$100—
    Qwen3-Embedding-8BHigh throughput API$0.03—$30—Try Model API
    ↳Batch$0.02—$20—

    No surprises. No lock-in.

    No credit card required
    No minimum spend
    Pay only for tokens used
    Results stream as they're ready
    OpenAI-compatible API
    Cancel or retry any batch, any time

    Stop overpaying for inference.

    Run your background agents and workloads at a fraction of the price and double the scale.

    Run a sample jobSavings Calculator

    If you can wait an hour, you can save a lot.