DeepSeek V4 Pro pricing & specs

DeepSeek · released 2026-04-24 · ● verified 2026-10-11 · deprecated

This model is deprecated. Cheapest compatible replacement: Qwen3.7 Flash.

input / 1M$0.435via NVIDIA
output / 1M$0.87via NVIDIA
context1.05M
max output393.2K

// price history ($/1M tokens)

$1.0005
input $/1Moutput $/1M2026-04-24 → 2026-10-11

// cheaper or similar alternatives

modelinoutctxvs DeepSeek V4 Pro
Qwen3.7 Flash$0.03$0.131M−89.9%
Qwen Turbo$0.05$0.201M−83.9%
DeepSeek V4 Flash 0731$0.06$0.181.05M−83.4%
DeepSeek V4 Flash$0.09$0.181.05M−79.3%
Qwen Flash$0.05$0.401M−74.7%
DeepSeek V4 Pro vs DeepSeek V4 Pro →

// price by host

hostin $/1Mout $/1M
NVIDIA$0.435$0.87
DeepInfra$1.30$2.60
Novita AI$1.60$3.20
Azure$1.74$3.48
Baseten$1.74$3.48
Nebius$1.75$3.50

// faq

How much does DeepSeek V4 Pro cost?

DeepSeek V4 Pro costs $0.435 per million input tokens and $0.87 per million output tokens (cheapest tracked host: NVIDIA). At 50M input and 10M output tokens per month that is about $30.45.

What is the context window of DeepSeek V4 Pro?

1.05M tokens, with up to 393.2K output tokens per request.

Does DeepSeek V4 Pro support prompt caching?

Yes. Cached input tokens cost $0.00363 per million.

What are cheaper alternatives to DeepSeek V4 Pro?

Qwen3.7 Flash ($0.03 in / $0.13 out), Qwen Turbo ($0.05 in / $0.20 out), DeepSeek V4 Flash 0731 ($0.06 in / $0.18 out) offer the same input types and capabilities for less.

Is DeepSeek V4 Pro open weights?

Yes. It is available from 6 tracked hosts; the cheapest is NVIDIA at $0.435 input and $0.87 output per million tokens.

// spec sheet

input / 1M
$0.435
output / 1M
$0.87
cache read / 1M
$0.00363
blended (3:1)
$0.5438
context
1.05M
max output
393.2K
input types
text
reasoning
yes
tool calling
yes
structured output
yes
open weights
yes
knowledge cutoff
2025-05
price source
NVIDIA

report a data error

// cost calculator

modelin $/1Mout $/1M= monthly
Qwen3.7 Flash$0.03$0.13$2.80
Qwen Turbo$0.05$0.20$4.50
DeepSeek V4 Flash 0731$0.06$0.18$4.80
DeepSeek V4 Pro$0.435$0.87$30.45

Base-tier list prices. Long-context tiers, caching and batch discounts are not included.