Models/DeepSeek

DeepSeek

DeepSeek models, pricing, and protocols

20 currently available models with pricing synced from the MoleAPI console.

20 models

deepseek-v4-flash-90%Official profile verified

DeepSeek V4-Flash is the fast, economical open-weight V4 model. It supports a 1M context window, thinking and non-thinking modes, and OpenAI- and Anthropic-compatible APIs.

Success: 92.8%
Avg latency: 13.4s

View model

defaultx1

Input$0.22 / 1M tokens

Output$0.67 / 1M tokens

Cache read$0.0075 / 1M tokens

Cache write$0.275 / 1M tokens

discountx0.8

Input$0.176 / 1M tokens

Output$0.536 / 1M tokens

Cache read$0.006 / 1M tokens

Cache write$0.22 / 1M tokens

relayx0.3

Input$0.066 / 1M tokens

Output$0.201 / 1M tokens

Cache read$0.0023 / 1M tokens

Cache write$0.0825 / 1M tokens

tempx0.1

Input$0.022 / 1M tokens

Output$0.067 / 1M tokens

Cache read$0.0008 / 1M tokens

Cache write$0.0275 / 1M tokens

AA index 40openaiopenai-responseanthropicgeminiopenai-response-compactopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

deepseek-v4-pro-90%Official profile verified

DeepSeek V4-Pro is the Pro model in DeepSeek's V4 family. DeepSeek's update notes confirm access through both OpenAI Chat Completions and Anthropic interfaces.

Success: 100.0%
Avg latency: 33.9s

View model

defaultx1

Input$0.67 / 1M tokens

Output$1.34 / 1M tokens

Cache read$0.02 / 1M tokens

Cache write$0.83 / 1M tokens

tempx0.1

Input$0.067 / 1M tokens

Output$0.134 / 1M tokens

Cache read$0.002 / 1M tokens

Cache write$0.083 / 1M tokens

AA index 43openaiopenai-responseopenai-response-compactanthropicgeminiopenai-alpha-searchOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare

deepseek-v4-flash-vision-exp-70%

deepseek-v4-flash-vision-exp is a DeepSeek model available through MoleAPI with openai, openai-response, anthropic, gemini access. It fits OpenAI compatible, Responses API, Anthropic compatible, Gemini compatible workflows, with pricing synced from the MoleAPI console.

Success: 99.6%
Avg latency: 14.2s

View model

defaultx1

Input$0.22 / 1M tokens

Output$0.67 / 1M tokens

Cache read$0.0075 / 1M tokens

Cache write$0.275 / 1M tokens

discountx0.8

Input$0.176 / 1M tokens

Output$0.536 / 1M tokens

Cache read$0.006 / 1M tokens

Cache write$0.22 / 1M tokens

relayx0.3

Input$0.066 / 1M tokens

Output$0.201 / 1M tokens

Cache read$0.0023 / 1M tokens

Cache write$0.0825 / 1M tokens

openaiopenai-responseanthropicgeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleVisionPrompt cacheCompare

deepseek-v4-flash-260425Official profile verified

DeepSeek V4-Flash is the fast, economical open-weight V4 model. It supports a 1M context window, thinking and non-thinking modes, and OpenAI- and Anthropic-compatible APIs.

View model

defaultx1

Input$0.22 / 1M tokens

Output$0.67 / 1M tokens

Cache read$0.0075 / 1M tokens

Cache write$0.275 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v4-pro-260425Official profile verified

DeepSeek V4-Pro is the Pro model in DeepSeek's V4 family. DeepSeek's update notes confirm access through both OpenAI Chat Completions and Anthropic interfaces.

Success: 100.0%
Avg latency: 76.4s

View model

defaultx1

Input$0.67 / 1M tokens

Output$1.34 / 1M tokens

Cache read$0.02 / 1M tokens

Cache write$0.83 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v3.2-70%Official profile verified

DeepSeek V3.2 is a reasoning-first open model for agent scenarios, using sparse attention for efficient long context and supporting tools in thinking and non-thinking modes.

View model

defaultx1

Input$0.29 / 1M tokens

Output$0.435 / 1M tokens

Cache read$0.145 / 1M tokens

discountx0.8

Input$0.232 / 1M tokens

Output$0.348 / 1M tokens

Cache read$0.116 / 1M tokens

relayx0.3

Input$0.087 / 1M tokens

Output$0.1305 / 1M tokens

Cache read$0.0435 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v3.2-exp

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.3 / 1M tokens

Output$0.45 / 1M tokens

openaiOpenAI compatibleCompare

deepseek-v3.1

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.56 / 1M tokens

Output$1.68 / 1M tokens

Cache read$0.28 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v3.1-terminus

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.58 / 1M tokens

Output$1.74 / 1M tokens

Cache read$0.464 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v3

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.29 / 1M tokens

Output$1.16 / 1M tokens

Cache read$0.0362 / 1M tokens

openaiOpenAI compatiblePrompt cacheCompare

deepseek-v3-1-terminus

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.56 / 1M tokens

Output$1.68 / 1M tokens

openaiOpenAI compatibleCompare

deepseek-v3-2-251201Official profile verified

DeepSeek V3.2 is a reasoning-first open model for agent scenarios, using sparse attention for efficient long context and supporting tools in thinking and non-thinking modes.

View model

defaultx1

Input$0.29 / 1M tokens

Output$0.435 / 1M tokens

Cache read$0.145 / 1M tokens

openaiOpenAI compatibleCompare

deepseek-v2.5

DeepSeek model by DeepSeek for general chat, writing, coding assistance, and tool-assisted workflows.

View model

defaultx1

Input$0.192 / 1M tokens

Output$0.192 / 1M tokens