Kimi K2.6

Creator

Kimi

Released

2026-04-20

Intelligence

44.2

Artificial Analysis Index

Coding

61.8

Artificial Analysis Index

In $/1M

$0.95

input tokens

Out $/1M

$4.00

output tokens

Blended $/1M

$1.71

3:1 blended

Speed

0

tokens / sec

Profile

License, openness, and modality — the governance layer.

License

Modified MIT License

non-commercial

Weights

Open

downloadable

Modalities

Image · Text · Video

Parameters

1T

total

Kimi K2.6 is Moonshot AI's open-source, native multimodal agentic model focused on state-of-the-art coding, long-horizon execution, and agent swarm capabilities. It scales horizontally to 300 sub-agents executing 4,000 coordinated steps, dynamically decomposing tasks into parallel, domain-specialized subtasks. K2.6 unifies text, image, and video input with thinking and non-thinking modes, supports a 256K context, and powers proactive 24/7 background agents that manage schedules, execute code, and orchestrate cross-platform operations without human oversight.

Capability profile

Category strength across 20 domains, via LLM Stats.

legal
100finance
100agents
100reasoning
100general
100math
80search
80vision
80
multimodal
80frontend development
80biology
70physics
70chemistry
70code
60tool calling
60
Via LLM Stats

Benchmark breakdown

Independent evaluation scores, normalized to 0–100.

GPQA Diamond
91
Humanity’s Last Exam
36
MMLU-Pro
SciCode
54
LiveCodeBench
MATH-500
AIME 2025
τ²-Bench (agentic)
96
Terminal-Bench Hard
44
IFBench
76
Via Artificial Analysis

Providers

Inference hosts serving this model — their own pricing and measured performance, cheapest input first.

ProviderIn $/1MOut $/1MThroughputLatencyStatus
DeepInfra$0.75$3.50active
Fireworks$0.95$4.00active
Moonshot AI$0.95$4.00active
Novita$0.95$4.00active
Together$1.20$4.50active
All providers

5 hosts · via LLM Stats

© 2026 NYSGPT2525 LLC