MoleAPI logo
MoleAPI
AI model gateway
Models/DeepSeek

DeepSeek

DeepSeek models, pricing, and protocols

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

15 models

Compare
D
deepseek-v4.1-flash-70%

deepseek-v4.1-flash · Reasoning model for analysis and solving complex questions.

View model
defaultx1
peak
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.006 / 1M tokens
off_peak
Input$0.15 / 1M tokens
Output$0.6 / 1M tokens
Cache read$0.003 / 1M tokens
discountx0.8
peak
Input$0.24 / 1M tokens
Output$0.96 / 1M tokens
Cache read$0.0048 / 1M tokens
off_peak
Input$0.12 / 1M tokens
Output$0.48 / 1M tokens
Cache read$0.0024 / 1M tokens
relayx0.3
peak
Input$0.09 / 1M tokens
Output$0.36 / 1M tokens
Cache read$0.0018 / 1M tokens
off_peak
Input$0.045 / 1M tokens
Output$0.18 / 1M tokens
Cache read$0.0009 / 1M tokens
openaiopenai-responseanthropicgeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
D
deepseek-v4-flash-70%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.

View model
defaultx1
base
Input$0.22 / 1M tokens
Output$0.67 / 1M tokens
Cache read$0.0075 / 1M tokens
Cache write$0.275 / 1M tokens
discountx0.8
base
Input$0.176 / 1M tokens
Output$0.536 / 1M tokens
Cache read$0.006 / 1M tokens
Cache write$0.22 / 1M tokens
relayx0.3
base
Input$0.066 / 1M tokens
Output$0.201 / 1M tokens
Cache read$0.0023 / 1M tokens
Cache write$0.0825 / 1M tokens
AA index 40openaiopenai-responseanthropicgeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
D
deepseek-v4-flash-vision-exp-70%

deepseek-v4-flash-vision-exp · Vision-language model for image understanding and text responses.

View model
defaultx1
base
Input$0.22 / 1M tokens
Output$0.67 / 1M tokens
Cache read$0.0075 / 1M tokens
Cache write$0.275 / 1M tokens
Image input$0.275 / 1M tokens
discountx0.8
base
Input$0.176 / 1M tokens
Output$0.536 / 1M tokens
Cache read$0.006 / 1M tokens
Cache write$0.22 / 1M tokens
Image input$0.22 / 1M tokens
relayx0.3
base
Input$0.066 / 1M tokens
Output$0.201 / 1M tokens
Cache read$0.0023 / 1M tokens
Cache write$0.0825 / 1M tokens
Image input$0.0825 / 1M tokens
openaiopenai-responseanthropicgeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleVisionPrompt cacheCompare
D
deepseek-v4-pro-70%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.

View model
defaultx1
peak
Input$1.32 / 1M tokens
Output$4 / 1M tokens
Cache read$0.044 / 1M tokens
off_peak
Input$0.66 / 1M tokens
Output$2 / 1M tokens
Cache read$0.022 / 1M tokens
discountx0.8
peak
Input$1.056 / 1M tokens
Output$3.2 / 1M tokens
Cache read$0.0352 / 1M tokens
off_peak
Input$0.528 / 1M tokens
Output$1.6 / 1M tokens
Cache read$0.0176 / 1M tokens
relayx0.3
peak
Input$0.396 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.0132 / 1M tokens
off_peak
Input$0.198 / 1M tokens
Output$0.6 / 1M tokens
Cache read$0.0066 / 1M tokens
AA index 43openaiopenai-responseanthropicOpenAI compatibleResponses APIAnthropic compatiblePrompt cacheCompare
D
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
base
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
D
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.

View model
defaultx1
peak
Input$1.32 / 1M tokens
Output$4 / 1M tokens
Cache read$0.044 / 1M tokens
off_peak
Input$0.66 / 1M tokens
Output$2 / 1M tokens
Cache read$0.022 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
D
deepseek-v3.2Official 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
base
Input$0.29 / 1M tokens
Output$0.435 / 1M tokens
Cache read$0.145 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
D
deepseek-v3.1

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

View model
defaultx1
base
Input$0.56 / 1M tokens
Output$1.68 / 1M tokens
Cache read$0.28 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
D
deepseek-v3.1-terminus

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

View model
defaultx1
base
Input$0.58 / 1M tokens
Output$1.74 / 1M tokens
Cache read$0.464 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
D
deepseek-v3

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

View model
defaultx1
base
Input$0.29 / 1M tokens
Output$1.16 / 1M tokens
Cache read$0.0362 / 1M tokens
openaiOpenAI compatiblePrompt cacheCompare
D
deepseek-flash-70%

deepseek-flash · Reasoning model for analysis and solving complex questions.

View model
defaultx1
peak
Input$0.3 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.006 / 1M tokens
off_peak
Input$0.15 / 1M tokens
Output$0.6 / 1M tokens
Cache read$0.003 / 1M tokens
discountx0.8
peak
Input$0.24 / 1M tokens
Output$0.96 / 1M tokens
Cache read$0.0048 / 1M tokens
off_peak
Input$0.12 / 1M tokens
Output$0.48 / 1M tokens
Cache read$0.0024 / 1M tokens
relayx0.3
peak
Input$0.09 / 1M tokens
Output$0.36 / 1M tokens
Cache read$0.0018 / 1M tokens
off_peak
Input$0.045 / 1M tokens
Output$0.18 / 1M tokens
Cache read$0.0009 / 1M tokens
openaiopenai-responseanthropicgeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
D
deepseek-r1-0528

DeepSeek reasoning model by DeepSeek for complex problem solving, analysis, coding, and agent workflows.

View model
defaultx1
base
Input$0.574 / 1M tokens
Output$2.294 / 1M tokens
Cache read$0.1148 / 1M tokens
openaiOpenAI compatibleReasoningPrompt cacheCompare
D
deepseek-r1-0528-turbo

DeepSeek reasoning model by DeepSeek for complex problem solving, analysis, coding, and agent workflows.

View model
defaultx1
base
Input$1 / 1M tokens
Output$3 / 1M tokens
openaiOpenAI compatibleReasoningCompare
D
deepseek-r1-distill-llama-70b

DeepSeek reasoning model by DeepSeek for complex problem solving, analysis, coding, and agent workflows.

View model
defaultx1
base
Input$0.7 / 1M tokens
Output$2.5669 / 1M tokens
Cache read$0.35 / 1M tokens
openaiOpenAI compatibleReasoningPrompt cacheCompare
D
deepseek-ocr

DeepSeek vision model by DeepSeek for document parsing, OCR, tables, charts, and layout understanding.

View model
defaultx1
base
Input$0 / 1M tokens
Output$0 / 1M tokens
openaiOpenAI compatibleCompare