Open-source engine for faster local language model inference with bit-for-bit identical output
The same API as OpenRouter at the provider's list price, with 0% platform fee and no subscription.
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Open source
Not given
Pricing
Not given
Prepaid credit from $5 USD (whole dollars), no platform fee. Own provider keys are free with no fee at any volume. First top-up bonus: $5 extra on a first top-up of $5 or more. Up to 20% bonus credit on top-ups through referrals (1% per person referred who pays $20+), posting about plaingateway, or
Key features
Speculative decoding for faster token generation
Prompt caching for context reuse
Real-time prompt processing while typing
Concurrent request batching
Bit-for-bit identical output verification
Multi-GPU and multi-backend support (CUDA, Vulkan)
Vision model support with image encoding
Mixture-of-experts model support
RAD-1 automatic draft token generation
Cross-platform support for Windows and Linux
0% platform fee with no markup
Bring your own provider keys at no cost
Up to 20% bonus credit on top-ups
Referral program earning 10% for 12 months
Encrypted key storage
No data retention for requests
Compatible with coding agents and IDEs
First top-up bonus of $5
What makes it different
Exact deterministic inference: all default optimizations preserve bit-for-bit identical output compared to plain decoding
4.5× faster performance on editing tasks on small models compared to llama.cpp
Verifiable reproducibility through receipt system that records all request parameters
Nine optimization techniques enabled by default with ability to disable each individually
No dependency on draft models or external selections for speculative decoding
Free when using your own provider keys with no fee at any volume
Transparent provider list pricing with no hidden costs
Kinetic
plaingateway