DeepSeek V4 Pro is DeepSeek's language model with a 1.0M context window and up to 384K output tokens, available from 8 providers, starting at $0.435 / 1M input and $0.87 / 1M output. A large-scale Mixture-of-Experts LLM from DeepSeek with 1.6T total and 49B activated parameters, supporting a 1M-token context window for advanced reasoning and tool-use tasks.
Specifications
Canonical IDdeepseek-v4-pro
TypeLanguage
StatusActive
CreatorDeepSeekDeepSeek
Providers
Context Window1.0M tokens
Max Output384K tokens
Input ModalitiesImagePDFText
Output ModalitiesText
Reasoning Effortsdefault
Parameters862B
HuggingFace Likes2,540
HuggingFace Downloads (30d)78,864
HuggingFace Downloads (all-time)78,864
Release Date · 3 months ago
Benchmarks
Intelligence Index
44.3
#19
Coding Index
59.4
#22
GPQA
0.9
#34
HLE
0.4
#23
IFBench
0.8
#18
Time to First Token
1.01s
#361
SciCode
0.5
#26
LCR
0.7
#52
TerminalBench Hard
0.5
#21
TAU2
1.0
#15
Output TPS
64.8
#170

Capabilities

Input3/5
Text
Image
Audio·
Video·
PDF
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities7/13
Reasoning
Adaptive Reasoning·
Function Calling
Parallel Function Calling
Structured Outputs
Native JSON Schema
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching
Assistant Prefill

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandardBatch
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Input
$ / 1M
Output
$ / 1M
Cache Read
$ / 1M
Alibaba Qwen logo
Alibaba Qwen
deepseek-v4-pro
$2.40$4.80N/A$1.20$2.40N/A
Azure AI Foundry logo
Azure AI Foundry
azure_ai/deepseek-v4-pro
$1.74$3.48N/A
DeepSeek logo
DeepSeek
deepseek-v4-pro
$0.435$0.87$0.00363$0.217$0.435$0.00181
Fireworks AI logo
Fireworks AI
fireworks_ai/deepseek-v4-pro
$1.74$3.48$0.145
Hugging Face logo
Hugging Face
novita:deepseek/deepseek-v4-pro
$1.60$3.20N/A
Hugging Face logo
Hugging Face
together_ai:deepseek-ai/DeepSeek-V4-Pro
$1.74$3.48N/A
OpenRouter logo
OpenRouter
deepseek/deepseek-v4-pro
$0.435$0.87$0.00363
Tencent logo
Tencent
tencent/deepseek-v4-pro
$0.435$0.87$0.00363
Vercel AI Gateway logo
Vercel AI Gateway
deepseek/deepseek-v4-pro
$0.435$0.87$0.0036

Cost Calculator

US Dollar ($)
Preset:

Cheapest Instances to Run It

Cloud GPU instances that can host DeepSeek V4 Pro, ranked by cheapest on-demand price. The model needs about 2068 GB of GPU memory at FP16 precision (estimated from its parameter count), so treat the fit as guidance rather than a guarantee.

All clouds
FP16 (full precision)
US Dollar ($)
Instance
Cloud
GPU
VRAM
Price
Cheapest region
p6-b300.48xlargeAWS8× B3002149 GB$142.42/hrus-east-1

Other Models

ModelTierReleasedContextInput / 1MOutput / 1M
DeepSeek V4 FlashFlash1.0M$0.098$0.196
DeepSeek V4 Flash ThinkingFlash200K$0.250$1.75

Model IDs

accounts/fireworks/models/deepseek-v4-pro
azure_ai/deepseek-v4-pro
deepseek-ai/DeepSeek-V4-Pro
deepseek-v4-pro
deepseek-v4-pro-high
deepseek-v4-pro-non-reasoning
deepseek/deepseek-v4-pro
fireworks_ai/accounts/fireworks/models/deepseek-v4-pro
fireworks_ai/deepseek-v4-pro
tencent/deepseek-v4-pro