DeepSeek V3.1: API Provider Performance Benchmarking & Price Analysis | Artificial Analysis

Source: original

Artificial 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.

DeepSeek

Open weights model

Released August 2025

DeepSeek V3.1 (Non-reasoning) API Provider Benchmarking & Analysis

Model Comparison

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.

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

Where can I access DeepSeek V3.1 (Non-reasoning)?

How many API providers offer DeepSeek V3.1 (Non-reasoning)?

Which provider is fastest for DeepSeek V3.1 (Non-reasoning)?

Which provider has the lowest latency for DeepSeek V3.1 (Non-reasoning)?

Which provider is cheapest for DeepSeek V3.1 (Non-reasoning)?

Which provider has the lowest input price for DeepSeek V3.1 (Non-reasoning)?

Which provider has the lowest output price for DeepSeek V3.1 (Non-reasoning)?

How much do prices vary across DeepSeek V3.1 (Non-reasoning) providers?

How much does speed vary across DeepSeek V3.1 (Non-reasoning) providers?

Which DeepSeek V3.1 (Non-reasoning) providers support JSON mode?

Which DeepSeek V3.1 (Non-reasoning) providers support function calling?

Which is the best provider for DeepSeek V3.1 (Non-reasoning)?

How do I choose a provider for DeepSeek V3.1 (Non-reasoning)?

Does provider performance for DeepSeek V3.1 (Non-reasoning) change over time?

What are the overall capabilities of DeepSeek V3.1 (Non-reasoning)?