Provider logo

Kimi K2.5 Thinking

moonshotai/kimi-k2.5:thinking
Provider logo

Kimi K2.5 Thinking

moonshotai/kimi-k2.5:thinking

Kimi K2.5 with thinking mode enabled. Built on Kimi K2 with ~15T mixed visual and text tokens, it excels at general reasoning, visual coding, and agentic tool-calling. Produces reasoning traces for complex multi-step workflows.

Added Jan 26, 2026

Model weights

Context Window

256.0K

Max Output

65.5K

Avg output tokens (7d)

1.2K tokens

48%

Input Price (Auto)

$0.45/1M

Output Price (Auto)

$2.25/1M

Cache Read (Auto)

$0.070/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

36.0

Better than 79% of models compared

Coding Index

46.8

Better than 61% of models compared

Agentic Index

21.7

Better than 52% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

87.9%

Better than 87% of models compared

HLE

Humanity's Last Exam

30.7%

Better than 86% of models compared

IFBench

Instruction-following benchmark

70.2%

Better than 84% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

95.9%

Better than 96% of models compared

AA-LCR

Long context reasoning evaluation

73.0%

Better than 86% of models compared

GDPval-AA

Economically valuable tasks

25.3%

CritPt

Research-level physics reasoning

3.1%

Coding

SciCode

Python programming for scientific computing

49.0%

Better than 89% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

34.8%

Better than 80% of models compared

Knowledge

AA-Omniscience Accuracy

Proportion of correctly answered questions

35.2%

AA-Omniscience Hallucination Rate

Rate of incorrect answers among non-correct responses

65.7%

Last updated Aug 16, 2026

Artificial Analysis

Providers

Choose explicit providers for this model. Auto routing remains available as the default option.

Loading provider options…

Compare Kimi K2.5 Thinking with similar models from the same provider or model family.

Kimi K3

moonshotai/kimi-k3

Kimi K3 is Moonshot AI's open-weight, always-thinking multimodal model for long-context reasoning, coding, tool use, and native image/video understanding.

Kimi K2.7 Code High-Speed

moonshotai/kimi-k2.7-code-highspeed

Kimi K2.7 Code High-Speed is the accelerated coding-focused variant tuned for fast agentic software engineering. It targets roughly 180 tokens per second, with short-context responses reaching up to about 260 tokens per second for rapid coding iterations.

Kimi K2.7 Code

moonshotai/kimi-k2.7-code

Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built for long-horizon software engineering workflows. It supports native image input, tool calling, and forced thinking mode; instant/non-thinking mode is not supported.

Kimi Latest

moonshotai/kimi-latest

Compatibility alias that routes to the newest Kimi model. Currently routes to Kimi K3.

Kimi K2.6

moonshotai/kimi-k2.6

Kimi K2.6 is an open-source, native multimodal agentic model built for long-horizon coding, coding-driven design, and large-scale task orchestration. It can turn simple prompts and visual inputs into production-ready interfaces and full-stack workflows, and is designed to coordinate complex multi-agent plans with thousands of steps across code, documents, and spreadsheets.

Kimi K2.6 Thinking

moonshotai/kimi-k2.6:thinking

Kimi K2.6 Thinking is the reasoning-optimized K2.6 variant for deeper multi-step planning and execution. It is tuned for long-horizon coding and design workflows, including complex orchestration across many specialized sub-agents and autonomous end-to-end output generation.