DeepSeek V3.1: API Provider Performance Benchmarking & Price Analysis | Artificial Analysis
K
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.
•
Open weights model
•
Released August 2025
DeepSeek V3.1 (Non-reasoning) API Provider Benchmarking & Analysis
Analysis of API providers for DeepSeek V3.1 (Non-reasoning) across performance metrics including latency (time to first token), output speed (output tokens per second), price and others. API providers benchmarked include Novita, Amazon Bedrock, DeepInfra (FP4), CoreWeave, Google Vertex, SambaNova, Baseten (FP8).
Fastest
1
SambaNova
181.1 t/s
2
Amazon
137.6 t/s
3
Baseten (FP8)
121.7 t/s
4
Google Vertex
112.7 t/s
5
CoreWeave
47.9 t/s
Output speed
Total 7 providers
Lowest Latency
1
Google Vertex
0.79 s
2
Baseten (FP8)
0.89 s
3
CoreWeave
1.37 s
4
Amazon
1.48 s
5
DeepInfra (FP4)
1.59 s
Time to first answer token
Total 7 providers
Lowest Price
1
DeepInfra (FP4)
$0.21
2
Baseten (FP8)
$0.42
3
CoreWeave
$0.66
4
Novita
$0.66
5
Amazon
$0.69
Blended price (per 1M tokens)
Total 7 providers
DeepSeek V3.1 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 SambaNova (181.1 t/s), Amazon (137.6 t/s), Baseten (FP8) (121.7 t/s). Speed varies significantly across providers, with a 278% difference between the fastest and slowest.
- For latency, Google Vertex (0.79s), Baseten (FP8) (0.89s), CoreWeave (1.37s) offer the lowest time to first token.
- For pricing, DeepInfra (FP4) (0.21), Baseten (FP8) (0.42), CoreWeave (0.66) offer the lowest blended prices per 1M tokens. Prices vary up to 3.3x across providers.
Model ComparisonAPI Provider Benchmarks
Highlights
Speed
Output tokens per second · Higher is better
End-to-End Response Time
Seconds · Lower is better
Updated
Price
USD per 1M tokens (blended) · Lower is better
PricingUpdatedSpeedLatencyEnd-to-End Response TimeAPI FeaturesSummary Table of Key Comparison Metrics
Prompt Options
Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.
PricingUpdated
Speed
Measured by Output Speed (tokens per second)
Output Speed: DeepSeek V3.1 Providers
7 of 7 providers
Output tokens per second · Higher is better · 10,000 Input Tokens
Output Speed
Median
Latency vs. Output Speed: DeepSeek V3.1 Providers
7 of 7 providers
Latency: seconds to first token received · Output speed: output tokens per second · 10,000 Input Tokens
Most attractive quadrant
Size represents Price (USD per M Tokens)
Amazon
Baseten (FP8)
CoreWeave
DeepInfra (FP4)
Google Vertex
Novita
SambaNova
Output Speed
Latency (Time to First Token)
Price
Median
Latency
Measured by Time (seconds) to First Token
Time to First Token: DeepSeek V3.1 Providers
7 of 7 providers
Seconds to first token received · Lower is better · 10,000 Input Tokens
Latency (Time to First Token)
Median
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 output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 Input Tokens
7 of 7 providers
Outputting time'Thinking' time (reasoning models)Input processing time
End-to-End Response Time
Standardized Reasoning Tokens
Median
API Features
Function (Tool) Calling & JSON Mode: DeepSeek V3.1 Providers
7 of 7 providers
Models| Function calling| JSON Mode
Novita Amazon DeepInfra (FP4) CoreWeave Google Vertex SambaNova Baseten (FP8)
Function (Tool) Calling
JSON Mode
Context Window: DeepSeek V3.1 Providers
7 of 7 providers
Context window: tokens limit · Higher is better
Context Window
Provider Context Window Variance
Summary Table of Key Comparison Metrics
Frequently Asked Questions
Common questions about DeepSeek V3.1 (Non-reasoning) providers