An LLM gateway for Claude, GPT, Gemini and open models at or below list price
Stage
MVP
Not given
Founded
Not given
Not given
Based in
Not given
AE
Pricing model
Paid
Paid
Pricing
One-time plans starting at $10 (100,000 credits), $100 (1,000,000 credits), and $1,000 (11,000,000 credits with 10% extra). Credits do not expire.
Per million tokens, with live pricing capped at list price. Models range from $0.07-$0.27 per million input tokens and $0.23-$1.08 per million output tokens. For example: Claude Opus 5.5 at $1.09 input/$5.45 output per million tokens, GPT-6-Luna at $0.08 input/$0.40 output per million tokens, Deepse
Key features
Structured answers with probability signals
Online playground for testing models
Choice, score, and yes-no decision types
Multiple models available for comparison
API key management
Usage and request history tracking
Works with existing OpenAI and Anthropic SDKs without code changes
Integrates with Cursor, Cline, Claude Code and Vercel AI SDK
Live pricing capped at model provider list price
60+ models including Claude, GPT, Gemini and open-weight models
Intel TDX trusted execution environment with hardware attestation
Pay-as-you-go billing with no top-up fees
Prompt encryption for open models inside TEE enclave
SayGM Desktop AI agent for local file work
Switch models mid-chat in Desktop
Model routing across competing operators for availability
What makes it different
Multiple decision models in one playground and API
Structured answers instead of generated text
Probability signals with confidence scores
Up to 70% discount vs list price on frontier and open models
Sealed privacy with hardware-verified Intel TDX attestation anyone can check
Supports all major model providers in one API without SDK changes
Transparent live pricing that never exceeds official model provider rates
DecisionsApi
SayGM