This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
Mistral has launched a newer release, Mistral Small 4. We suggest considering it instead.
Mistral Small 3.2 API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Mistral Small 3.2 for your use-case.
Fastest
DeepInfra (FP8)Output speed
Total 1 provider
Lowest Latency
DeepInfra (FP8)Time to first token
Total 1 provider
Lowest Price
DeepInfra (FP8)Blended price (per 1M tokens)
Total 1 provider
Mistral Small 3.2 is available through DeepInfra (FP8).
Pricing
Pricing: Cache Hit, Input, and Output: Mistral Small 3.2
Cost per Intelligence Index Task: Mistral Small 3.2
Output Speed vs. Price: Mistral Small 3.2
Speed
Measured by Output Speed (tokens per second)
Output Speed: Mistral Small 3.2
Time per Intelligence Index Task: Mistral Small 3.2
Cost per Task vs. Time per Task: Mistral Small 3.2
Latency
Measured by Time (seconds) to First Token
Time to First Token: Mistral Small 3.2
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time: Mistral Small 3.2
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Mistral Small 3.2 providers
Mistral Small 3.2 is available through 1 API provider: DeepInfra (FP8). Each provider offers different performance characteristics and pricing.
Mistral Small 3.2 is currently available through 1 API provider that we benchmark and track.
The fastest provider for Mistral Small 3.2 by output speed is DeepInfra (FP8) (50.9 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The provider with the lowest time to first token for Mistral Small 3.2 is DeepInfra (FP8) (1.02s). Lower latency means faster initial response time.
The most affordable provider for Mistral Small 3.2 by blended price is DeepInfra (FP8) ($0.09 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 Small 3.2 is DeepInfra (FP8) ($0.07 per 1M input tokens).
The provider with the lowest output token pricing for Mistral Small 3.2 is DeepInfra (FP8) ($0.20 per 1M output tokens).
The only provider of Mistral Small 3.2 supports JSON mode for structured output.
The only provider of Mistral Small 3.2 supports function calling (tool use).
DeepInfra (FP8) leads across all key metrics for Mistral Small 3.2, offering the fastest speed, lowest latency, and most competitive pricing.
When choosing a provider for Mistral Small 3.2, consider: output speed (for throughput-intensive tasks), 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 Small 3.2's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview