DeepSeek V4 Pro

mit

DeepSeek-V4-Pro-0813 hybrid model with both non-thinking and thinking (default) modes.

Context
1M
Max output
384K
Input price
$1.74/1M tokens
Output price
$3.48/1M tokens

Capabilities

Reasoning & Interaction
Reasoning
Tool Calling
Output Control
JSON Mode
Infrastructure
Streaming
Fine-tuning

Details

Model IDdeepseek-v4-pro
Provider OpenCode Zen
Creator DeepSeek
Familydeepseek
Licensemit
Statusactive
Typechat
Input modalitiestext
Output modalitiestext
Open weightYes
Parameters—
Architecture—
Context window1M tokens
Max input—
Max output384K tokens
Reasoning tokensYes
Knowledge cutoff—
Release date
Sourceofficial

Pricing

Input
$1.74
Output
$3.48
Cache write
—
Cache read
$0.14
Batch in
—
Batch out
—

Family Comparison: deepseek

ModelContextMax outPricing
DeepSeek V4 Flash Free———
DeepSeek V4.1 Flash Free——$0$0
DeepSeek V4 Flash Vision Exp——$0.14$0.28
DeepSeek V4 Flash——$0.14$0.28
DeepSeek V4.1 Flash——$0.3$1.2
DeepSeek V4 Pro1M384K$1.74$3.48

API

GET/v1/models/opencode/deepseek-v4-pro

DeepSeek V4 Pro

deepseek-v4-pro

DeepSeek-V4-Pro-0813 hybrid model with both non-thinking and thinking (default) modes.

Changes · 3 entries
deepseek-v4-procreateca7a400Nov 2, 2026, 03:02 AM
deepseek-v4-proupdateb2f45bfOct 29, 2026, 03:29 AM
created_byunknown→deepseek
deepseek-v4-procreateab879c8Jun 18, 2026, 08:32 AM