•DeepSeek V4 Pro 0813•

Open weights model

•

Released August 2026

DeepSeek V4 Pro 0813 (Max) API Provider Benchmarking & Analysis

Model Comparison

This analysis is intended to support you in choosing the best API provider of DeepSeek V4 Pro 0813 (Max) for your use-case.

Lowest Time per Task

#1
DigitalOceanDigitalOcean
11.4 min
#2
BasetenBaseten
13.9 min
#3
DeepSeekDeepSeek
17.3 min
#4
NebiusNebius
17.9 min
#5
NovitaNovita
20.2 min

Time per Intelligence Index task (minutes)

Total 8 providers

Lowest Cost per Task

#1
DeepSeekDeepSeek
$1.77
#2
NovitaNovita
$1.86
#3
SiliconFlowSiliconFlow
$2.52
#4
GMIGMI
$2.66
#5
DeepInfraDeepInfra
$2.98

Cost per Intelligence Index task

Total 8 providers

DeepSeek V4 Pro 0813 (max) is available through 8 API providers, each offering different performance characteristics and pricing. Below is a comparison of the key metrics across providers.

  • For time per task, DigitalOcean (11.4 min), Baseten (13.9 min), and DeepSeek (17.3 min) finish an Intelligence Index task fastest.
  • For cost per task, DeepSeek ($1.77), Novita ($1.86), and SiliconFlow ($2.52) are the cheapest per Intelligence Index task. Cost varies up to 7.6x across providers.
Inference time (minutes) per Intelligence Index task · Lower is better
Weighted average cost (USD) per Intelligence Index task · Lower is better

Pricing

Cost per Intelligence Index Task: DeepSeek V4 Pro 0813 (Max)

Weighted average cost (USD) per Intelligence Index task · Segmented by token type · Lower is better

Pricing: Cache Hit, Input, and Output: DeepSeek V4 Pro 0813 (Max)

Price (USD per M Tokens) · Lower is better

Output Speed vs. Cost per Task: DeepSeek V4 Pro 0813 (Max)

Output speed: output tokens divided by total request time, including time to first token · Weighted average cost (USD) per Intelligence Index task
Most attractive quadrant
Pareto line

Speed

Average of the single-request and multi-turn agentic workloads measured

Time per Intelligence Index Task: DeepSeek V4 Pro 0813 (Max)

Output tokens divided by end-to-end output speed (minutes per Intelligence Index task) · Lower is better

Latency

Average of the single-request and multi-turn agentic workloads measured

Time to First Answer Token: DeepSeek V4 Pro 0813 (Max)

Seconds until the first answer token after any reasoning · Average of the single-request and multi-turn agentic workloads measured · Lower is better

Reliability

Share of requests the endpoint failed, across all the single-request and multi-turn agentic workloads measured

Endpoint Error Rate: DeepSeek V4 Pro 0813 (Max)

Share of requests the endpoint failed with an error, a rate limit or a timeout · Across all the single-request and multi-turn agentic workloads measured · Lower is better

Caching

Cache Hit Rate: DeepSeek V4 Pro 0813 (Max)

Median across multi-turn agentic session runs in the last four weeks, updated Oct 26, 2026 · Higher is better

Cost per Task vs. Cache Hit Rate: DeepSeek V4 Pro 0813 (Max)

Weighted average cost (USD) per Intelligence Index task · Cache hit rate: median of the last four weeks, updated Oct 26, 2026
Most attractive quadrant

Key Comparison Metrics & API Features

Baseten logoBaseten
$4.95
15.6
45.95
5.6%
1M
Open
DeepInfra logoDeepInfra
$2.98
27.8
74.76
0.0%
1M
Open
DeepSeek logoDeepSeek
$1.77
19.2
55.28
0.0%
1M
Open
DigitalOcean logoDigitalOcean
$4.94
12.5
36.51
3.6%
1M
Open
GMI logoGMI
$2.66
22.9
60.30
0.0%
1M
Open
Nebius logoNebius
$13.43
18.7
48.29
0.7%
1M
Open
Novita logoNovita
$1.86
23.6
67.46
0.0%
1M
Open
SiliconFlow logoSiliconFlow
$2.52
44.1
60.56
0.9%
1M
Open

Frequently Asked Questions

Common questions about DeepSeek V4 Pro 0813 (Max) providers