Provider pricing

Kluster.ai AI API pricing

Kluster.ai is a distributed inference provider founded in 2024 and headquartered in San Francisco. Aggregates idle GPU capacity to deliver discounted Llama, DeepSeek, and Qwen inference with batch and adaptive endpoints.

Founded2024
HeadquartersSan Francisco, CA
Tracked modelsDirectory

Best for

Throughput-heavy workloads optimizing for $/token.

Strengths

  • Up to 50% cheaper than centralized inference clouds
  • Adaptive inference auto-tunes for cost vs latency
  • Batch API with bulk discounts
  • Listed in the TokenCost AI providers directory