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 Results for other workloads are historical and no longer updated.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 model, DeepSeek V3.1 Terminus. We suggest considering it instead.
For more information, see comparison of DeepSeek V3.1 Terminus to other models and API provider benchmarks for DeepSeek V3.1 Terminus.
DeepSeek V3.1 (Reasoning) API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of DeepSeek V3.1 (Reasoning) for your use-case.
Fastest
SambaNova
Amazon
NovitaOutput speed
Total 4 providers
Lowest Latency
SambaNovaAmazonNovitaTime to first answer token
Total 4 providers
Lowest Price
NovitaAmazon
Google VertexSambaNovaBlended price (per 1M tokens)
Total 4 providers
DeepSeek V3.1 is available through 4 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 SambaNova (115.4 t/s), Amazon (105.1 t/s), and Novita (36.0 t/s).
- For latency, SambaNova (20.65s), Amazon (20.86s), and Novita (58.86s) offer the lowest time to first answer token.
- For pricing, Novita (0.34), Amazon (0.69), and Google Vertex (0.71) offer the lowest blended prices per 1M tokens. Prices vary up to 9.2x across providers.
- SambaNova offers the best performance with both the highest speed and lowest latency. For cost optimization, Novita 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: DeepSeek V3.1 (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 V3.1 (Reasoning) providers
DeepSeek V3.1 (Reasoning) is available through 4 API providers: Amazon, Google Vertex, SambaNova, and Novita. Each provider offers different performance characteristics and pricing.
DeepSeek V3.1 (Reasoning) is currently available through 4 API providers that we benchmark and track.
The most affordable providers for DeepSeek V3.1 (Reasoning) by blended price are Novita ($0.34 per 1M tokens), Amazon ($0.69 per 1M tokens), and Google Vertex ($0.71 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 V3.1 (Reasoning) are Novita ($0.27 per 1M input tokens), Amazon ($0.58 per 1M input tokens), and Google Vertex ($0.60 per 1M input tokens).
The providers with the lowest output token pricing for DeepSeek V3.1 (Reasoning) are Novita ($1.00 per 1M output tokens), Amazon ($1.68 per 1M output tokens), and Google Vertex ($1.70 per 1M output tokens).
3 of 4 providers support JSON mode for DeepSeek V3.1 (Reasoning): Google Vertex, SambaNova, and Novita.
All 4 providers of DeepSeek V3.1 (Reasoning) support function calling (tool use).
When choosing a provider for DeepSeek V3.1 (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 V3.1 (Reasoning)'s intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview