One API key for DeepSeek, GLM, Kimi, Qwen, Llama, Gemma and more
Foundation model for mobile, wearables, robots, smart home, automotive and microcontrollers
Stage
Startup
Startup
Founded
Not given
Not given
Based in
GB
Not given
Pricing model
Freemium
Open source
Pricing
Free: $0.25 credit on sign-up (one per person). Pay as you go: from $5 top up, per-token pricing. $0.182 per million tokens from (DeepSeek V4.1 Flash input), $0.195 per million tokens from (GLM-5.3 Flash, MiniMax input), $0.234 per million tokens from (Gemma 4 31B input), $0.325 per million tokens f
Not given
Key features
Support for 25+ chat models from multiple providers
Image generation with FLUX and Stable Diffusion
Video generation with Wan 2.2
Speech synthesis with ElevenLabs and Qwen
Standard chat-completions API format
Server-sent events and streaming
Function calling and JSON mode
Per-API-key spending limits
Embeddings and reranking
In-browser chat interface
Tool calling with function selection and argument filling
Structured extraction with guaranteed JSON parsing
Text embeddings for local semantic search and matching
Confidence scoring for routing and gating calls
Laddered subnetwork architecture from 2 to 20 layers
LoRA fine-tuning support for customization
400-4k tokens per second inference speed on Raspberry Pi 5
Python package with pip install and Hugging Face distribution
What makes it different
Single API key to access 25+ models from 17 different providers
No subscriptions, pay only per token used
Prompts and responses are never stored
Works with existing tools by changing base URL
Pricing starts from $0.182 per million tokens
Beats models 10x its size on mobile tool calling benchmarks
Matches models 2-3x larger on structured extraction tasks
Entire model in a single 8-29 MB binary for tiny devices
Simple Attention Network architecture uses 2x fewer MFLOPs than transformers
Fine-tuned subnetworks outperform larger models like DeepSeek V4 Flash
Solo Router