This model is deprecated. We still benchmark its performance, but less often: every 18 hours instead of every 6.
Mistral has launched a newer release, Mistral Medium 3.1. We suggest considering it instead.
Mistral Medium 3 API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Mistral Medium 3 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
Mistral Medium 3 is available through Azure.
Pricing
Cost per Intelligence Index Task: Mistral Medium 3
Pricing: Cache Hit, Input, and Output: Mistral Medium 3
Output Speed vs. Cost per Task: Mistral Medium 3
Speed
Average of the single-request and multi-turn agentic workloads measured
Output Speed: Mistral Medium 3
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Mistral Medium 3
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Mistral Medium 3
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Mistral Medium 3 providers
Mistral Medium 3 is available through 1 API provider: Azure. Each provider offers different performance characteristics and pricing.
Mistral Medium 3 is currently available through 1 API provider that we benchmark and track.
The provider with the lowest time to first answer token for Mistral Medium 3 is Azure (5.22s). Lower latency means faster initial response time.
The most affordable provider for Mistral Medium 3 by blended price is Azure ($0.56 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 Mistral Medium 3 is Azure ($0.40 per 1M input tokens).
The provider with the lowest output token pricing for Mistral Medium 3 is Azure ($2.00 per 1M output tokens).
The only provider of Mistral Medium 3 supports JSON mode for structured output.
The only provider of Mistral Medium 3 supports function calling (tool use).
When choosing a provider for Mistral Medium 3, 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 Mistral Medium 3's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview