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 Large 4. We suggest considering it instead.
Mistral Large 4 Preview API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Mistral Large 4 Preview 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 Large 4 Preview is available through Mistral.
Pricing
Cost per Intelligence Index Task: Mistral Large 4 Preview
Pricing: Cache Hit, Input, and Output: Mistral Large 4 Preview
Output Speed vs. Cost per Task: Mistral Large 4 Preview
Speed
Average of the single-request and multi-turn agentic workloads measured
Time per Intelligence Index Task: Mistral Large 4 Preview
Latency
Average of the single-request and multi-turn agentic workloads measured
Time to First Answer Token: Mistral Large 4 Preview
Reliability
Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured
Endpoint Error Rate: Mistral Large 4 Preview
Caching
Cache Hit Rate: Mistral Large 4 Preview
Cost per Task vs. Cache Hit Rate: Mistral Large 4 Preview
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Mistral Large 4 Preview providers
Mistral Large 4 Preview is available through 1 API provider: Mistral. Each provider offers different performance characteristics and pricing.
Mistral Large 4 Preview is currently available through 1 API provider that we benchmark and track.
Mistral is the only Mistral Large 4 Preview provider with a measured time per task: 25.0 minutes per Intelligence Index task.
The provider with the lowest time to first answer token for Mistral Large 4 Preview is Mistral (44.55s). Lower latency means faster initial response time.
The most affordable provider for Mistral Large 4 Preview by blended price is Mistral ($0.40 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 Large 4 Preview is Mistral ($0.70 per 1M input tokens).
The provider with the lowest output token pricing for Mistral Large 4 Preview is Mistral ($2.10 per 1M output tokens).
The only provider of Mistral Large 4 Preview supports JSON mode for structured output.
The only provider of Mistral Large 4 Preview supports function calling (tool use).
When choosing a provider for Mistral Large 4 Preview, 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 Large 4 Preview's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview