Mastra launches Mastra Gateway with one key for 500+ models
Start here
Mastra launched the Mastra Gateway, a hosted version of its model router that lets developers call more than 500 language, voice, video and decision models from providers including Anthropic, OpenAI and Typesafe AI through a single API key and a single bill. The gateway adds built-in failover across multiple inference providers, per-key spend limits (hourly, daily, weekly, monthly or lifetime) and allowed-model controls, plus US/EU region routing with a dedicated EU endpoint and observability traces for every inference call. Mastra says it will charge no credit card fees on inference spending until December 31, 2026, and platform credits can be used with auto-top-up.
Generated from reports · updated 1 h ago
Report timeline
Follow the reports to see the event from different sides.
- Mastra BlogMastra launches Mastra Gateway with one key for over 500 models
Mastra launched the Mastra Gateway, a hosted version of its model router that gives developers access to more than 500 language, voice, video and decision models from providers including Anthropic, OpenAI and Typesafe AI through a single API key and a single bill. The gateway adds built-in failover across multiple inference providers, per-key spend limits and allowed-model controls, US/EU region routing with a dedicated EU endpoint, and observability traces for every inference call. Mastra is waiving credit card fees on inference spending until December 31, 2026.
Heat for this event
Not enough continuous observations yet to draw a trend.