DeepSeek has launched a newer model, DeepSeek V3.1 Terminus, we suggest considering this model 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
Analysis of API providers for DeepSeek V3.1 (Reasoning) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Amazon Bedrock, SambaNova, Novita, Google Vertex.
Fastest
Google Vertex
SambaNova
Amazon
NovitaOutput speed
Total 4 providers
Lowest Latency
Google VertexAmazonNovitaSambaNovaTime to first token
Total 4 providers
Lowest Price
NovitaAmazonGoogle 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 Google Vertex (301.1 t/s), SambaNova (168.1 t/s), Amazon (150.9 t/s). Speed varies significantly across providers, with a 582% difference between the fastest and slowest.
- For latency, Google Vertex (0.60s), Amazon (0.66s), Novita (1.15s) offer the lowest time to first token.
- For pricing, Novita (0.45), Amazon (0.85), Google Vertex (0.88) offer the lowest blended prices per 1M tokens. Prices vary up to 7.5x across providers.
- Google Vertex offers the best performance with both the highest speed and lowest latency. For cost optimization, Novita provides the most competitive pricing.
Pricing
Pricing: Input and Output Prices: DeepSeek V3.1 Providers
Price per token included in the request/message sent to the API, represented as USD per million Tokens.
Price per token generated by the model (received from the API), represented as USD per million Tokens.
Speed vs. Price: DeepSeek V3.1 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek V3.1 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Latency vs. Output Speed: DeepSeek V3.1 Providers
Tokens per second received while the model is generating tokens (ie. after first chunk has been received from the API for models which support streaming).
Time to first token received, in seconds, after API request sent. For reasoning models which share reasoning tokens, this will be the first reasoning token. For models which do not support streaming, this represents time to receive the completion.
Price per token, represented as USD per million Tokens. Price is a blend of Input & Output token prices (3:1 ratio).
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token: DeepSeek V3.1 Providers
Time to first answer token received, in seconds, after API request sent. For reasoning models, this includes the 'thinking' time of the model before providing an answer. For models which do not support streaming, this represents time to receive the completion.
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
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: DeepSeek V3.1 Providers
Seconds to receive a 500 token response. Key components:
- Input time: Time to receive the first response token
- Thinking time (only for reasoning models): Time reasoning models spend outputting tokens to reason prior to providing an answer. Amount of tokens based on the average reasoning tokens across a diverse set of 60 prompts (methodology details).
- Answer time: Time to generate 500 output tokens, based on output speed
For fair comparison, the number of reasoning tokens is standardized across all providers for each model based on the model's representative query token counts.
Figures represent median (P50) measurement over the past 72 hours to reflect sustained changes in performance.
API Features
Function (Tool) Calling & JSON Mode: DeepSeek V3.1 Providers
SambaNovaIndicates whether the provider supports function calling in their API. Function calling is also known as 'Tool Calling'.
Indicates whether the provider supports JSON mode in their API. When JSON mode is enabled, the models will always return a valid JSON object.
Context Window: DeepSeek V3.1 Providers
Maximum number of combined input & output tokens. Output tokens commonly have a significantly lower limit (varied by model).
While models have their own context window, in cases this is limited by providers.
Summary Table of Key Comparison Metrics
FAQ
Common questions about DeepSeek V3.1 (Reasoning) providers
DeepSeek V3.1 (Reasoning) is available through 4 API providers: Amazon, SambaNova, Novita, and Google Vertex. 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 fastest providers for DeepSeek V3.1 (Reasoning) by output speed are Google Vertex (301.1 t/s), SambaNova (168.1 t/s), and Amazon (150.9 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 DeepSeek V3.1 (Reasoning) are Google Vertex (0.60s), Amazon (0.66s), and Novita (1.15s). Lower latency means faster initial response time.
The most affordable providers for DeepSeek V3.1 (Reasoning) by blended price are Novita ($0.45 per 1M tokens), Amazon ($0.85 per 1M tokens), and Google Vertex ($0.88 per 1M tokens). Blended price uses a 3:1 input to 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).
Output speed for DeepSeek V3.1 (Reasoning) varies significantly across providers. Google Vertex is the fastest at 301.1 t/s, which is 6.8x faster than Novita at 44.1 t/s.
1 of 4 providers support JSON mode for DeepSeek V3.1 (Reasoning): SambaNova.
All 4 providers of DeepSeek V3.1 (Reasoning) support function calling (tool use).
For DeepSeek V3.1 (Reasoning), Google Vertex offers the best performance with highest speed and lowest latency. For cost optimization, Novita provides the most competitive pricing.
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 →