Moonshot AI

MoonshotAI: Kimi K2.6

by Moonshot AItext+image->text22 endpoints
Neura Intelligence Index
72.9/ 100
Rank
#65
Confidence
high
Benchmarks
10(26% coverage)

Overview

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and...

Capabilities

Text generation
Image understanding
Tool use / Function calling
Structured output
Extended reasoning
Prompt caching
Long context
Top-P sampling
Stop sequences
Deterministic seed
Log probabilities

Modalities

Input
TextImage
Output
Text

Technical Specifications

Context Window
262.1K tokens
Max Output
235.9K tokens
Tokenizer
Other
Uptime (24h)
10000.0%
Parameters
1000000000000B
License
modified_mit_licenseOpen Weights
Country
🇨🇳CN
Release Date
April 20, 20265mo

Supported Parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Benchmark Performance

coding

BenchmarkScoreSource
SWE-bench Verified
80.2
verified
SWE-Bench Pro
58.6
verified
SciCode
52.2
verified

reasoning

BenchmarkScoreSource
GPQA Diamond
90.5
verified
Humanity's Last Exam
36.4
verified

multimodal

BenchmarkScoreSource
CharXiv Reasoning
86.7
verified
MMMU-Pro
80.1
verified

agent

BenchmarkScoreSource
BrowseComp
86.3
verified
Toolathlon
50
verified
APEX Agents
27.9
verified

Performance Over Time

Pricing

Per 1M tokens
Input$0.95
Output$4.00
Cache read$0.16
Added
April 20, 2026
Last synced 9/20/2026