ZappushZappush
SkillsUse CasesBenchmarkCommunity
← DeepSeek Models

DeepSeek

Deepseek V4 Flash

deepseek/deepseek-v4-flash

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

Input

$0.1400

per 1M tokens

Output

$0.2800

per 1M tokens

Cache Read

-

not available

Cache Write

-

not available

Quality Benchmarks

FrontierValue: 471.5

Coding

Code generation, completion, debugging

57.7

Math

Competition math, calculus, olympiad

79.6

Reasoning

Logic, spatial, puzzle solving

71.7

Language

Summarization, paraphrase, writing

66.6

Overall

68.9

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

Capabilities

VisionTool UseReasoningPrompt Caching

Similar Price Range

Qwen3.5 35b A3b

Qwen

$0.1400 in$1.00 out262.1K

Deepseek V3.1 Nex N1

Nex-agi

$0.1350 in$0.5000 out131.1K

Qwen3 235b A22b Thinking 2507

Qwen

$0.1495 in$1.50 out131.1K

More from DeepSeek

Deepseek Chat V3.1

$0.1500 / $0.7500

Deepseek Chat V3 0324

$0.2000 / $0.7700

Deepseek V3.2

$0.2520 / $0.3780

Deepseek V3.2 Exp

$0.2700 / $0.4100

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