Open weights model

Released April 2026

DeepSeek V4 Pro (Reasoning, High Effort) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Pro (Reasoning, High Effort) for your use-case.

Fastest

#1
BasetenBaseten
137.3 t/s
#2
NebiusNebius
120.4 t/s
#3
AzureAzure
86.1 t/s
#4
Bitdeer AIBitdeer AI
77.5 t/s
#5
DeepSeekDeepSeek
70.9 t/s

Output speed

Total 8 providers

Lowest Latency

#1
BasetenBaseten
15.09 s
#2
NebiusNebius
17.86 s
#3
AzureAzure
24.75 s
#4
Bitdeer AIBitdeer AI
28.07 s
#5
DeepSeekDeepSeek
29.86 s

Time to first answer token

Total 8 providers

Lowest Price

#1
DeepSeekDeepSeek
$0.18
#2
DeepInfra (FP4)DeepInfra (FP4)
$0.59
#3
Bitdeer AIBitdeer AI
$0.66
#4
SiliconFlow (FP8)SiliconFlow (FP8)
$0.71
#5
NovitaNovita
$0.73

Blended price (per 1M tokens)

Total 8 providers

DeepSeek V4 Pro (high) is available through 8 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 Baseten (137.3 t/s), Nebius (120.4 t/s), and Azure (86.1 t/s). Speed varies significantly across providers, with a 202% difference between the fastest and slowest.
  • For latency, Baseten (15.09s), Nebius (17.86s), and Azure (24.75s) offer the lowest time to first answer token.
  • For pricing, DeepSeek (0.18), DeepInfra (FP4) (0.59), and Bitdeer AI (0.66) offer the lowest blended prices per 1M tokens. Prices vary up to 10.9x across providers.
  • Baseten offers the best performance with both the highest speed and lowest latency. For cost optimization, DeepSeek provides the most competitive pricing.

Highlights

Output tokens per second · Higher is better
Seconds · Lower is better
USD per 1M tokens (blended) · Lower is better

Update: Default performance benchmarking workload has updated to 10k input tokens to better reflect production use cases. You can still select different workloads above.

Pricing

Pricing: Cache Hit, Input, and Output

Price (USD per M Tokens) · Lower is better · 10,000 input tokens

Pricing: Blended Price

Blended at 7:2:1 (cache-input-output) · USD per 1M tokens (blended) · Lower is better

Pricing: Cache Discount

1 - (cache hit price / input price) · Higher is better

Output Speed vs. Price

Blended at 7:2:1 (cache-input-output) · Output speed: output tokens per second · USD per 1M tokens (blended)
Most attractive quadrant
Pareto line

Speed

Measured by Output Speed (tokens per second)

Output Speed: DeepSeek V4 Pro (Reasoning, High Effort)

Output speed: output tokens per second · 10,000 input tokens

Latency vs. Output Speed

Latency: seconds to first token received · Output speed: output tokens per second · 10,000 input tokens
Most attractive quadrant

Latency

Measured by Time (seconds) to First Token

Time to First Answer Token

Seconds to first token received · Lower is better · 10,000 input tokens

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

Seconds to output 500 tokens, including reasoning model 'thinking' time · Lower is better · 10,000 input tokens

Key Comparison Metrics & API Features

DeepInfra logoDeepInfra
65.5k
Open
--
43
1.33
59.43
46.44
Microsoft Azure logoMicrosoft Azure
1M
Open
--
72
1.72
36.11
27.49
DeepSeek logoDeepSeek
1M
Open
--
65
1.58
39.90
30.63
Bitdeer AI logoBitdeer AI
1M
Open
--
45
3.01
57.93
43.90
SiliconFlow logoSiliconFlow
1.05M
Open
--
46
2.07
55.88
43.01
Nebius logoNebius
1M
Open
--
114
1.43
23.26
17.45
Novita logoNovita
1.05M
Open
--
66
1.83
39.71
30.28
Baseten logoBaseten
1M
Open
--
130
0.63
19.82
15.34

Frequently Asked Questions

Common questions about DeepSeek V4 Pro (Reasoning, High Effort) providers