Model | Time to First Token | Overall Latency | Failure Timeline |
---|---|---|---|
Claude Haiku 3.5 AWS Bedrock - us-west-2, Anthropic, AWS Bedrock - us-east-1 | Chart unavailable | Chart unavailable | Chart unavailable |
Claude Sonnet 3.7 AWS Bedrock - us-east-1, AWS Bedrock - us-west-2, Anthropic | Chart unavailable | Chart unavailable | Chart unavailable |
Claude Sonnet 4 AWS Bedrock - us-west-2, Anthropic, AWS Bedrock - us-east-1 | Chart unavailable | Chart unavailable | Chart unavailable |
GPT-4.1 OpenAI, Azure - West US, Azure - East US | Chart unavailable | Chart unavailable | Chart unavailable |
GPT-4.1 mini Azure - East US, Azure - West US, OpenAI | Chart unavailable | Chart unavailable | Chart unavailable |
GPT-4o OpenAI, Azure - East US | Chart unavailable | Chart unavailable | Chart unavailable |
Gemini 2.5 Flash Google - AppStudio, Google Vertex AI - us-east5 | Chart unavailable | Chart unavailable | Chart unavailable |
Last updated: August 21, 2025 at 6:10 AM UTC