Honest Metered Pricing
Pay strictly for the tokens you consume. No monthly commitments, no credit packs, no hidden markups.
Flash
$0.66 / 1M tokens
High-speed inference for lightweight tasks, chat agents, and real-time processing.
- • Sub-second response times
- • 128K context window
- • Zero log retention
Most Popular
Pro
$2.50 / 1M tokens
Smart routing & deep reasoning models for complex engineering, analysis, and writing.
- • Deep reasoning & coding
- • Native tool & function calling
- • 100% Green compute
Ultra
$8.00 / 1M tokens
Multimodal vision, screenshots, and synthesis at the lowest price in its class.
- • Maximum intelligence depth
- • Broad multi-modal context
- • Priority gateway queue
Auto Router
Included with every key
Our proprietary smart routing sends every request to the best engine for the job at the cheapest price. You pay only the engine it routes to. No extra charge for routing.