ZappushZappush
SkillsUse CasesBenchmarkCommunity
← DeepSeek Models

DeepSeek

Deepseek V4 Pro

deepseek/deepseek-v4-pro

1.0M context·384K max output·text->text

Input

$0.4350

per 1M tokens

Output

$0.8700

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

FrontierValue: 119.7

Coding

Code generation, completion, debugging

62.0

Math

Competition math, calculus, olympiad

90.7

Reasoning

Logic, spatial, puzzle solving

84.7

Language

Summarization, paraphrase, writing

68.4

Overall

76.4

Source: LiveBench (livebench.ai) / Scores 0-100

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

Kimi K2.5

Moonshot

$0.4400 in$2.00 out262.1K

Qwen3 235b A22b

Qwen

$0.4550 in$1.82 out131.1K

Mimo V2.5

Xiaomi

$0.4000 in$2.00 out1.0M

More from DeepSeek

Deepseek V4 Flash

$0.1400 / $0.2800

Deepseek Chat V3.1

$0.1500 / $0.7500

Deepseek Chat V3 0324

$0.2000 / $0.7700

Deepseek V3.2

$0.2520 / $0.3780

Deploy your AI agent for $33/mo flat.

Managed Telegram bot hosting. We handle the infrastructure.

Any model. Any channel. Zero infrastructure.

Deploy Your Agent
Zappush© 2026 Zappush
HomeSkillsUse CasesBenchmarkGuarantee