Skip to content

AI API Router Directory

$ 2 entries match — showing 1–2 · sort: Free credits ↓

// the index — expansive, community-regulatedno affiliate ordering · no pay-to-rank · uprouter.online

388 routers & providers · 813 models tracked · $3.8k free credits

  • Official free tierAPI key
    up13msupdated 16h ago
    integrate.api.nvidia.com
    source · build.nvidia.com
    overview

    NVIDIA NIM's hosted API (build.nvidia.com / integrate.api.nvidia.com) serves a broad catalog of open-weight models — Nemotron, Llama, Qwen, DeepSeek, GLM and more — in an OpenAI-compatible shape, with a permanent free tier: API key at sign-up, no card, 40 requests/minute by default (200 RPM granted on request, per NVIDIA's developer forums).

    free quota

    Free tier is rate-limited (40 RPM default, 200 on request) rather than credit-based — no USD value to quantify.

    free models
    Nemotron 3 Nano 30B A3BNemotron 3.5 LightningNemotron 3 SuperNemotron 3 Ultranvidia/llama-3.1-nemotron-ultra-253b-v1gpt-oss-120b+6
    see integrate.api.nvidia.com’s free quota / risk review →
  • Paid APIAPI key
    unknownupdated Sep 6, 2026
    wafer.ai
    source · docs.wafer.ai/wafer-pass
    overview

    Wafer AI provides fast, serverless AI model inference and agent infrastructure. It allows developers to configure AI models with an API key from its dashboard. Features the 'Wafer Pass' for predictable model access and specialized 'Wafer' models optimized for speed.

    free quota

    No public free-tier information found (researched 2026-08-29).

    free models
    DeepSeek Chatqwen/qwen3.5-397b-a17bGLM-5.1kimi-k3
    see wafer.ai’s free quota / risk review →