MoonshotAI: Kimi K3
by Moonshot AItext+image->text1 endpoint
Neura Intelligence Index
90.6/ 100
Rank
#6—
Confidence
highBenchmarks
8(21% coverage)
Overview
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Capabilities
Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Modalities
Input
TextImage
Output
Text
Technical Specifications
Context Window
1.0M tokens
Tokenizer
Other
Uptime (24h)
9996.8%
Parameters
2800000000000B
License
unknownOpen Weights
Country
Supported Parameters
frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningreasoning_effortresponse_formatstopstructured_outputstool_choicetools
Benchmark Performance
reasoning
| Benchmark | Score | Source |
|---|---|---|
| GPQA Diamond | 93.5 | verified |
| Humanity's Last Exam | 56 | verified |
multimodal
| Benchmark | Score | Source |
|---|---|---|
| CharXiv Reasoning | 91.3 | verified |
Performance Over Time
Pricing
Per 1M tokens
Input$3.00
Output$15.00
Cache read$0.30