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 Results for other workloads are historical and no longer updated.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 model, Mistral Small 4. We suggest considering it instead.
For more information, see comparison of Mistral Small 4 to other models and API provider benchmarks for Mistral Small 4.
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
Mistral
DeepInfra (FP8)Output speed
Total 2 providers
Lowest Latency
MistralDeepInfra (FP8)Time to first token
Total 2 providers
Lowest Price
DeepInfra (FP8)MistralBlended price (per 1M tokens)
Total 2 providers
Mistral Small 3.2 is available through 2 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.
- For output speed, the top providers are Mistral (147.7 t/s) and DeepInfra (FP8) (30.4 t/s).
- For latency, Mistral (0.73s) and DeepInfra (FP8) (0.97s) offer the lowest time to first token.
- For pricing, DeepInfra (FP8) (0.09) and Mistral (0.12) offer the lowest blended prices per 1M tokens.
- Mistral offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepInfra (FP8) provides the most competitive pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Mistral Small 3.2
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Token
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
Key Comparison Metrics & API Features
Frequently Asked Questions
Common questions about Mistral Small 3.2 providers
Mistral Small 3.2 is available through 2 API providers: DeepInfra (FP8) and Mistral. Each provider offers different performance characteristics and pricing.
Mistral Small 3.2 is currently available through 2 API providers that we benchmark and track.
The fastest providers for Mistral Small 3.2 by output speed are Mistral (147.7 t/s) and DeepInfra (FP8) (30.4 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first token for Mistral Small 3.2 are Mistral (0.73s) and DeepInfra (FP8) (0.97s). Lower latency means faster initial response time.
The most affordable providers for Mistral Small 3.2 by blended price are DeepInfra (FP8) ($0.09 per 1M tokens) and Mistral ($0.12 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The providers with the lowest input token pricing for Mistral Small 3.2 are DeepInfra (FP8) ($0.07 per 1M input tokens) and Mistral ($0.10 per 1M input tokens).
The providers with the lowest output token pricing for Mistral Small 3.2 are DeepInfra (FP8) ($0.20 per 1M output tokens) and Mistral ($0.30 per 1M output tokens).
Prices for Mistral Small 3.2 vary up to 1.4x across providers. The most affordable is DeepInfra (FP8) at $0.09 per 1M tokens, while Mistral charges $0.12 per 1M tokens.
Output speed for Mistral Small 3.2 varies significantly across providers. Mistral is the fastest at 147.7 t/s, which is 4.9x faster than DeepInfra (FP8) at 30.4 t/s.
All 2 providers of Mistral Small 3.2 support JSON mode for structured output.
All 2 providers of Mistral Small 3.2 support function calling (tool use).
For Mistral Small 3.2, Mistral offers the best performance with highest speed and lowest latency. For cost optimization, DeepInfra (FP8) provides the 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