Magistral Small 1.2 API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Magistral Small 1.2 for your use-case.
Lowest Time per Task
Time per Intelligence Index task (minutes)
Total 1 provider
Lowest Cost per Task
Cost per Intelligence Index task
Total 1 provider
Magistral Small 1.2 is available through Amazon.
Pricing
Cost per Intelligence Index Task: Magistral Small 1.2
Pricing: Cache Hit, Input, and Output: Magistral Small 1.2
Output Speed vs. Cost per Task: Magistral Small 1.2
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Magistral Small 1.2
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Magistral Small 1.2
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Magistral Small 1.2
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Magistral Small 1.2 providers
Magistral Small 1.2 is available through 1 API provider: Amazon. Each provider offers different performance characteristics and pricing.
Magistral Small 1.2 is currently available through 1 API provider that we benchmark and track.
The provider with the lowest time to first answer token for Magistral Small 1.2 is Amazon (3.06s). Lower latency means faster initial response time.
The most affordable provider for Magistral Small 1.2 by blended price is Amazon ($0.60 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for Magistral Small 1.2 is Amazon ($0.50 per 1M input tokens).
The provider with the lowest output token pricing for Magistral Small 1.2 is Amazon ($1.50 per 1M output tokens).
The only provider of Magistral Small 1.2 supports function calling (tool use).
When choosing a provider for Magistral Small 1.2, consider: time per task (how quickly the provider completes an Intelligence Index task), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Magistral Small 1.2's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview