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 Results for other workloads are historical and no longer updated.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 3.2. We suggest considering it instead.
Mistral Small 3.1 API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Mistral Small 3.1 for your use-case.
Fastest
Multiverse Computing
DeepInfraOutput speed
Total 3 providers
Lowest Latency
DeepInfraMultiverse ComputingTime to first token
Total 3 providers
Lowest Price
DeepInfraMultiverse Computing
CloudflareBlended price (per 1M tokens)
Total 3 providers
Mistral Small 3.1 is available through 3 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 Multiverse Computing (76.0 t/s) and DeepInfra (39.9 t/s).
- For latency, DeepInfra (0.91s) and Multiverse Computing (1.05s) offer the lowest time to first token.
- For pricing, DeepInfra (0.06), Multiverse Computing (0.12), and Cloudflare (0.37) offer the lowest blended prices per 1M tokens.
- DeepInfra offers both the lowest latency and best pricing, making it attractive for cost-conscious applications. Multiverse Computing is the fastest option for throughput-intensive workloads.
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 3.1
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 3.1 providers
Mistral Small 3.1 is available through 3 API providers: Cloudflare, DeepInfra, and Multiverse Computing. Each provider offers different performance characteristics and pricing.
Mistral Small 3.1 is currently available through 3 API providers that we benchmark and track.
The fastest providers for Mistral Small 3.1 by output speed are Multiverse Computing (76.0 t/s) and DeepInfra (39.9 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 3.1 are DeepInfra (0.91s) and Multiverse Computing (1.05s). Lower latency means faster initial response time.
The most affordable providers for Mistral Small 3.1 by blended price are DeepInfra ($0.06 per 1M tokens), Multiverse Computing ($0.12 per 1M tokens), and Cloudflare ($0.37 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 3.1 are DeepInfra ($0.05 per 1M input tokens), Multiverse Computing ($0.11 per 1M input tokens), and Cloudflare ($0.35 per 1M input tokens).
The providers with the lowest output token pricing for Mistral Small 3.1 are DeepInfra ($0.10 per 1M output tokens), Multiverse Computing ($0.17 per 1M output tokens), and Cloudflare ($0.56 per 1M output tokens).
Prices for Mistral Small 3.1 vary up to 6.8x across providers. The most affordable is DeepInfra at $0.06 per 1M tokens, while Cloudflare charges $0.37 per 1M tokens.
Output speed for Mistral Small 3.1 varies significantly across providers. Multiverse Computing is the fastest at 76.0 t/s, which is 1.9x faster than DeepInfra at 39.9 t/s.
All 3 providers of Mistral Small 3.1 support JSON mode for structured output.
All 3 providers of Mistral Small 3.1 support function calling (tool use).
The best provider for Mistral Small 3.1 depends on your priorities: Multiverse Computing offers the highest output speed, DeepInfra has the lowest latency, and DeepInfra provides the most competitive pricing.
When choosing a provider for Mistral Small 3.1, 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 3.1's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview