Kimi K2.5 FP4 is Moonshot AI (Kimi)'s language model with a 262K context window, starting at $0.5 / 1M input and $2.80 / 1M output. A large language model in the Kimi K2 series quantized to FP4 precision for reduced memory footprint and faster inference.
Specifications
Canonical IDmoonshot-kimi-k2-5-fp4
TypeLanguage
StatusActive
CreatorMoonshot AI (Kimi)Moonshot AI (Kimi)
Providers
Context Window262K tokens
Input ModalitiesText
Output ModalitiesText

Capabilities

Input1/5
Text
Image·
Audio·
Video·
PDF·
Output1/5
Text
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Pricing by Provider

US Dollar ($)
Per 1M tokens
ProviderStandard
Input
$ / 1M
Output
$ / 1M
Together AI logo
Together AI
together_ai/moonshotai/Kimi-K2.5-fp4
$0.5$2.80

Cost Calculator

US Dollar ($)
Preset:

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
Kimi K31.0M$2.83$14.13Available
Kimi K3 Batch1.0M$3.00$15.00Available
Kimi K3 Coding1.0M$0.440$1.61Available
Kimi K3 Fast1.0M$4.50$22.50Available
Kimi K3 US1.0M$3.30$16.50Available
Kimi K2.7 Code HighSpeed262K$1.90$8.00Available
Kimi K2.7 Code262K$0.680$3.21Deprecated
Kimi K2 Thinking Turbo262K$1.15$8.00Deprecated
Kimi K2 Turbo256KAvailable
Kimi K2.5 FP4262K$0.500$2.80Current
Kimi K2.5 Non-ReasoningAvailable

Model IDs

moonshot-kimi-k2-5-fp4
together_ai/moonshotai/Kimi-K2.5-fp4