Mistral Large 2 (Nov '24): API Provider Benchmarking & Analysis
Analysis of API providers for Mistral Large 2 (Nov '24) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Microsoft Azure and Mistral.
Comparison Summary
Output Speed (tokens/s): Mistral (45 t/s) is the fastest provider of Mistral Large 2 (Nov '24), followed by 
Azure (37 t/s).Latency (TTFT): Mistral (0.38s) has the lowest latency for Mistral Large 2 (Nov '24), followed by Azure (0.48s).Blended Price ($/M tokens): Mistral ($3.00) is the lowest price provider of Mistral Large 2 (Nov '24) with an Input Token Price of $2.00 and an Output Token Price of $6.00, followed by Azure ($3.00).Input Token Price: Mistral ($2.00) and Azure ($2.00) offer the lowest input token prices for Mistral Large 2 (Nov '24).Output Token Price: Mistral ($6.00) and Azure ($6.00) offer the lowest output token prices for Mistral Large 2 (Nov '24).
Mistral (45 t/s) is the fastest provider of Mistral Large 2 (Nov '24), followed by Azure (37 t/s).Latency (TTFT): Mistral (0.38s) has the lowest latency for Mistral Large 2 (Nov '24), followed by Azure (0.48s).Blended Price ($/M tokens): Mistral ($3.00) is the lowest price provider of Mistral Large 2 (Nov '24) with an Input Token Price of $2.00 and an Output Token Price of $6.00, followed by Azure ($3.00).Input Token Price: Mistral ($2.00) and Azure ($2.00) offer the lowest input token prices for Mistral Large 2 (Nov '24).Output Token Price: Mistral ($6.00) and Azure ($6.00) offer the lowest output token prices for Mistral Large 2 (Nov '24).Highlights
Intelligence
Artificial Analysis Intelligence Index; Higher is better
