Claude 3.5 Sonnet (June): API Provider Benchmarking & Analysis
Analysis of API providers for Claude 3.5 Sonnet (June '24) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Amazon Bedrock, Anthropic, and Google.
Anthropic has launched a newer model, Claude 3.7 Sonnet. We suggest considering this model instead of Claude 3.5 Sonnet (June). See the following pages for a comparison of Claude 3.7 Sonnet to other models and Claude 3.7 Sonnet API provider benchmarks.
Comparison Summary
Output Speed (tokens/s):
Google Vertex (66 t/s) and Anthropic (65 t/s) are the fastest providers of Claude 3.5 Sonnet (June), followed by & 
Amazon (44 t/s).Latency (TTFT): Anthropic (0.48s) and Amazon (0.84s) have the lowest latency for Claude 3.5 Sonnet (June), followed by & Google Vertex (0.91s).Blended Price ($/M tokens): Amazon ($6.00) and Google Vertex ($6.00) are the most cost-effective providers for Claude 3.5 Sonnet (June), followed by & Anthropic ($6.00).Input Token Price: Amazon ($3.00) and offer the lowest input token prices for Claude 3.5 Sonnet (June), followed by .
Google Vertex (66 t/s) and Anthropic (65 t/s) are the fastest providers of Claude 3.5 Sonnet (June), followed by & Amazon (44 t/s).Latency (TTFT): Anthropic (0.48s) and Amazon (0.84s) have the lowest latency for Claude 3.5 Sonnet (June), followed by & Google Vertex (0.91s).Blended Price ($/M tokens): Amazon ($6.00) and Google Vertex ($6.00) are the most cost-effective providers for Claude 3.5 Sonnet (June), followed by & Anthropic ($6.00).Input Token Price: Amazon ($3.00) and offer the lowest input token prices for Claude 3.5 Sonnet (June), followed by .Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
Estimate (independent evaluation forthcoming)
