AI API Gateway with OpenAI-compatible and Claude Messages-compatible endpoints
The lowest-cost inference endpoints
Stage
Not given
Not given
Founded
Not given
Not given
Based in
Not given
Not given
Pricing model
Paid
Paid
Pricing
Pay as you go with transparent pricing. Pricing varies by model: GPT-6 Astra $1.00 input / $5.00 output per 1M tokens, GPT-5.6 Sol $0.50 input / $3.00 output per 1M tokens, Claude Fable 5 $2.00 input / $10.00 output per 1M tokens, Claude Opus 5 $1.00 input / $5.00 output per 1M tokens, Grok 4.5 $0.4
Not given
Key features
OpenAI-compatible endpoints
Claude Messages-compatible endpoints
Access to GPT, Claude, Grok, and Gemini models
Live model pricing transparency
Usage tracking and console management
Stripe-secured top-ups
ZDR-ready routing
Low-latency upstream routing
Single unified endpoint
Model catalog with open models
GPU price comparison across providers
Price transparency before launch
Dedicated, non-shared endpoints
OpenAI-compatible API
Endpoint monitoring and status tracking
Credit-based billing with held estimates
Automatic refunds for failed launches
What makes it different
Up to 90% cost savings on frontier models
Security-first with ZDR data-retention control
Sub-2 second response time
Compatible with existing SDKs
Transparent, no lock-in pricing
Lowest-cost GPU inference compared across providers
Dorbit