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 Results for other workloads are historical and no longer updated.
DeepSeek has launched a newer release, DeepSeek V4 Pro 0424. We suggest considering it instead.
DeepSeek V3.2 (Reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V3.2 (Reasoning) for your use-case.
Fastest
Amazon
DigitalOcean
DeepInfra (FP4)
SiliconFlow (FP8)Output speed
Total 7 providers
Lowest Latency
AmazonDigitalOceanDeepInfra (FP4)SiliconFlow (FP8)Time to first answer token
Total 7 providers
Lowest Price
DeepSeekDeepInfra (FP4)SiliconFlow (FP8)DigitalOcean
FireworksBlended price (per 1M tokens)
Total 7 providers
DeepSeek V3.2 is available through 7 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 Amazon (57.5 t/s), DigitalOcean (31.7 t/s), and DeepInfra (FP4) (21.7 t/s). Speed varies significantly across providers, with a 171% difference between the fastest and slowest.
- For latency, Amazon (36.44s), DigitalOcean (64.25s), and DeepInfra (FP4) (93.90s) offer the lowest time to first answer token.
- For pricing, DeepSeek (0.11), DeepInfra (FP4) (0.18), and SiliconFlow (FP8) (0.19) offer the lowest blended prices per 1M tokens. Prices vary up to 29.2x across providers.
- Amazon offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepSeek provides the most competitive pricing.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Pricing: Cache Discount
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek V3.2 (Reasoning)
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer 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 DeepSeek V3.2 (Reasoning) providers
DeepSeek V3.2 (Reasoning) is available through 7 API providers: SambaNova, DeepInfra (FP4), Amazon, Fireworks, DigitalOcean, DeepSeek, and SiliconFlow (FP8). Each provider offers different performance characteristics and pricing.
DeepSeek V3.2 (Reasoning) is currently available through 7 API providers that we benchmark and track.
The fastest providers for DeepSeek V3.2 (Reasoning) by output speed are Amazon (57.5 t/s), DigitalOcean (31.7 t/s), and DeepInfra (FP4) (21.7 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The providers with the lowest time to first answer token for DeepSeek V3.2 (Reasoning) are Amazon (36.44s), DigitalOcean (64.25s), and DeepInfra (FP4) (93.90s). Lower latency means faster initial response time.
The most affordable providers for DeepSeek V3.2 (Reasoning) by blended price are DeepSeek ($0.11 per 1M tokens), DeepInfra (FP4) ($0.18 per 1M tokens), and SiliconFlow (FP8) ($0.19 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 DeepSeek V3.2 (Reasoning) are DeepInfra (FP4) ($0.26 per 1M input tokens), SiliconFlow (FP8) ($0.27 per 1M input tokens), and DeepSeek ($0.28 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V3.2 (Reasoning) are DeepInfra (FP4) ($0.38 per 1M output tokens), DeepSeek ($0.42 per 1M output tokens), and SiliconFlow (FP8) ($0.42 per 1M output tokens).
Output speed for DeepSeek V3.2 (Reasoning) varies significantly across providers. Amazon is the fastest at 57.5 t/s, which is 2.7x faster than SiliconFlow (FP8) at 21.2 t/s.
6 of 7 providers support JSON mode for DeepSeek V3.2 (Reasoning): SambaNova, DeepInfra (FP4), Fireworks, DigitalOcean, DeepSeek, and SiliconFlow (FP8).
All 7 providers of DeepSeek V3.2 (Reasoning) support function calling (tool use).
When choosing a provider for DeepSeek V3.2 (Reasoning), 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 DeepSeek V3.2 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview