MoleAPI logo
MoleAPI
AI model gateway
Models/Moonshot

Moonshot

Moonshot models, pricing, and protocols

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

10 models

Compare
M
kimi-k3-70%Official profile verified

Kimi K3 is Moonshot AI's 2.8T-parameter native multimodal reasoning model with a 1M context window, built for long-horizon coding, knowledge work, and deep reasoning.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
discountx0.8
base
Input$2.4 / 1M tokens
Output$12 / 1M tokens
Cache read$0.24 / 1M tokens
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
AA index 57openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
M
kimi-k2.7-code-70%

Kimi coding model by Moonshot for code generation, repository understanding, debugging, and agentic development.

View model
defaultx1
base
Input$0.95 / 1M tokens
Output$4 / 1M tokens
Cache read$0.2 / 1M tokens
Cache write$1 / 1M tokens
discountx0.8
base
Input$0.76 / 1M tokens
Output$3.2 / 1M tokens
Cache read$0.16 / 1M tokens
Cache write$0.8 / 1M tokens
relayx0.3
base
Input$0.285 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.06 / 1M tokens
Cache write$0.3 / 1M tokens
openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleCodingPrompt cacheCompare
M
kimi-k2.6-70%Official profile verified

Kimi K2.6 is a practical Moonshot AI model for multimodal understanding, coding, long-context analysis, and agent workflows.

View model
defaultx1
base
Input$0.95 / 1M tokens
Output$4 / 1M tokens
Cache read$0.1 / 1M tokens
Cache write$1 / 1M tokens
discountx0.8
base
Input$0.76 / 1M tokens
Output$3.2 / 1M tokens
Cache read$0.08 / 1M tokens
Cache write$0.8 / 1M tokens
relayx0.3
base
Input$0.285 / 1M tokens
Output$1.2 / 1M tokens
Cache read$0.03 / 1M tokens
Cache write$0.3 / 1M tokens
openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
M
kimi-k2.5-70%Official profile verified

Kimi K2.5 is Moonshot AI's native multimodal open model, supporting image and text input, thinking and fast modes, tools, and agent tasks.

View model
defaultx1
base
Input$0.58 / 1M tokens
Output$3.045 / 1M tokens
Cache read$0.1 / 1M tokens
discountx0.8
base
Input$0.464 / 1M tokens
Output$2.436 / 1M tokens
Cache read$0.08 / 1M tokens
relayx0.3
base
Input$0.174 / 1M tokens
Output$0.9135 / 1M tokens
Cache read$0.03 / 1M tokens
openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
M
kimi-k2.7-code-highspeed

kimi-k2.7-code-highspeed · Coding model for writing, reviewing and debugging software.

View model
defaultx1
Input$75 / 1M tokens
Output$75 / 1M tokens
openaiOpenAI compatibleCodingCompare
M
kimi-k2.5-turboOfficial profile verified

Kimi K2.5 is Moonshot AI's native multimodal open model, supporting image and text input, thinking and fast modes, tools, and agent tasks.

View model
defaultx1
base
Input$0.58 / 1M tokens
Output$3.045 / 1M tokens
Cache read$0.1 / 1M tokens
openaiOpenAI compatibleCompare
M
kimi-k2-instruct-0905

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

View model
defaultx1
base
Input$0.58 / 1M tokens
Output$2.32 / 1M tokens
openaiOpenAI compatibleCompare
M
kimi-k2-thinking

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

View model
defaultx1
base
Input$0.58 / 1M tokens
Output$2.32 / 1M tokens
Cache read$0.145 / 1M tokens
openaiOpenAI compatibleReasoningPrompt cacheCompare
M
kimi-for-coding-70%

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

View model
defaultx1
base
Input$0.6 / 1M tokens
Output$3 / 1M tokens
Cache read$0.1 / 1M tokens
Cache write$0.8 / 1M tokens
discountx0.8
base
Input$0.48 / 1M tokens
Output$2.4 / 1M tokens
Cache read$0.08 / 1M tokens
Cache write$0.64 / 1M tokens
relayx0.3
base
Input$0.18 / 1M tokens
Output$0.9 / 1M tokens
Cache read$0.03 / 1M tokens
Cache write$0.24 / 1M tokens
openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatiblePrompt cacheCompare
M
k3-70%Official profile verified

Kimi K3 is Moonshot AI's 2.8T-parameter native multimodal reasoning model with a 1M context window, built for long-horizon coding, knowledge work, and deep reasoning.

View model
defaultx1
base
Input$3 / 1M tokens
Output$15 / 1M tokens
Cache read$0.3 / 1M tokens
discountx0.8
base
Input$2.4 / 1M tokens
Output$12 / 1M tokens
Cache read$0.24 / 1M tokens
relayx0.3
base
Input$0.9 / 1M tokens
Output$4.5 / 1M tokens
Cache read$0.09 / 1M tokens
openaianthropicopenai-responsegeminiOpenAI compatibleResponses APIAnthropic compatibleGemini compatibleCompare