Skip to content
Dashboard

DeepSeek V4 Pro

DeepSeek V4 Pro is DeepSeek's April 23, 2026 top-tier model in the V4 series. It pairs a hybrid attention architecture with a context window of 1.0M tokens and targets complex reasoning, multi-step problem solving, and agentic tasks.

ReasoningTool UseImplicit Caching
index.ts
import { streamText } from 'ai'
const result = streamText({
model: 'deepseek/deepseek-v4-pro',
prompt: 'Why is the sky blue?'
})

Providers

Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.

Provider
Context
Max Output
Latency
Throughput
Input
Output
Cache
Web Search
Capabilities
ZDR
No Training
Regional Inference
Release Date
DeepSeek
75% off
Legal:Terms
Privacy
1M384K
1.8s
83tps
$1.74/M$0.43/M
$3.48/M$0.87/M
Read:$0.0/M
Write:
04/23/2026
Fireworks
Legal:Terms
Privacy
1M1M
1.0s
71tps
$1.74/M
$3.48/M
Read:$0.14/M
Write:
04/23/2026
Novita AI
Legal:Terms
Privacy
1M393K
2.1s
60tps
$1.74/M
$3.48/M
Read:$0.14/M
Write:
04/23/2026
DeepInfra
Legal:Terms
Privacy
66K66K
1.0s
75tps
$1.74/M
$3.48/M
Read:$0.14/M
Write:
04/23/2026
Baseten
Legal:Terms
Privacy
1M1M
1.5s
107tps
$1.74/M
$3.48/M
Read:$0.15/M
Write:
US
04/23/2026
Together AI
Legal:Terms
Privacy
1M1M
0.9s
53tps
$2.10/M
$4.40/M
Read:$0.2/M
Write:
04/23/2026
Azure
Legal:Terms
Privacy
1M128K
0.6s
103tps
$1.74/M
$3.48/M
04/23/2026