LaunchDevelopersJuly 8, 2026
Together AI launches Provisioned Throughput for open models
Reserved inference capacity with token-based pricing, 99% uptime SLA, and up to 90% lower cost than Claude Opus 4.8. Available today for MiniMax M3 and GLM-5.2.
2 sources
Daily brief
Get tomorrow's AI brief in your inbox
More stories today
- Depth Anything V3 TensorRT ROS 2 node generates metric depth
- ChatGPT reaches 1 billion weekly active users
- Air Canada held liable for chatbot's false refund policy
- Microsoft faces UK probe over Copilot price hikes
- AI Investment Boom Faces Reality Check From Markets and Regulators