Provider logo

Kimi K2 0905

moonshotai/Kimi-K2-Instruct-0905
Provider logo

Kimi K2 0905

moonshotai/Kimi-K2-Instruct-0905

Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.

Added Sep 25, 2025

Model weights

Context Window

256.0K

Max Output

262.1K

Avg output tokens (7d)

341 tokens

10%

Input Price (Auto)

$0.60/1M

Output Price (Auto)

$2.50/1M

Cache Read (Auto)

$0.30/1M

Capabilities

Benchmarks

Performance metrics and benchmarks

Sourced from Artificial Analysis.

Intelligence Index

24.0

Better than 61% of models compared

Reasoning

GPQA Diamond

Graduate-level scientific reasoning

76.7%

Better than 63% of models compared

HLE

Humanity's Last Exam

6.4%

Better than 44% of models compared

IFBench

Instruction-following benchmark

41.7%

Better than 43% of models compared

T²-Bench Telecom

Conversational AI agents in dual-control scenarios

73.4%

Better than 65% of models compared

AA-LCR

Long context reasoning evaluation

53.7%

Better than 56% of models compared

Coding

SciCode

Python programming for scientific computing

30.7%

Better than 43% of models compared

Terminal-Bench Hard

Agentic coding and terminal use

23.5%

Better than 63% of models compared

LiveCodeBench

Contamination-free coding benchmark

61.0%

Better than 67% of models compared

Math

AIME 2025

American Invitational Mathematics Examination 2025

57.3%

Better than 54% of models compared

Knowledge

MMLU-Pro

Professional and academic subject knowledge

81.9%

Better than 77% of models compared

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 0905 with similar models from the same provider or model family.

Kimi K2 Instruct

moonshotai/kimi-k2-instruct

Kimi K2 0905. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.

Kimi K2 0711

moonshotai/kimi-k2-instruct-0711

Kimi K2 0711 version. Kimi-k2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. Quantized at FP8.

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.