someaistuff.
moonshotaiListed Jul 11, 2025

MoonshotAI: Kimi K2 0711

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

Compare
Context window131.1K
Max output98.3K
Provider endpoints4
Benchmark results0
Tool callingOpen weights
Measured performance

Benchmark results

All leaderboards ↗
—

No published results in this index yet

Scores appear here when an evaluation matches this exact model.

Access & cost

Prices across providers

4 quotes

Your token mix

USD · listed token rates

$1.145
Novita · via OpenRouternovita/fp8 · quantization=fp8
$1.145

OpenRouter

Catalog quote
Input
$0.57
Output
$2.30
USD / 1M tokens
131.1K context98.3K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2

novita

via Hugging Face
Input
$0.57
Output
$2.30
USD / 1M tokens
131.1K contextPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/Kimi-K2-Instruct

Novita

via OpenRouter

novita/fp8 · quantization=fp8

Input
$0.57
Output
$2.30
USD / 1M tokens
131.1K context98.3K max outputPrice source ↗Checked Oct 17, 2026
Endpoint IDmoonshotai/kimi-k2::novita/fp8

Model specifications

Developer
moonshotai
Modality
Language
Context
131,072 tokens
Maximum output
98,304 tokens
Weights
Open weights
Provider listed
Jul 11, 2025
First discovered
Oct 16, 2026

Exact identities

  • openroutermoonshotai/kimi-k2
  • huggingfacemoonshotai/Kimi-K2-Instruct

Sources

OpenRouter ↗Hugging Face ↗

Updated Oct 17, 2026

More from moonshotai

View all ↗
moonshotaiListed Jul 16

MoonshotAI: Kimi K3 (batch)

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...

1M contextImage inputVideo inputNo reported score
No reported score
$2.28in$11.40out/ 1M tokens · USDDeepInfra · via OpenRouter · 2 endpointsdeepinfra/bf16 · quantization=bf16
+Compare
moonshotaiListed Jun 11

MoonshotAI: Kimi K2.7 Code

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal…

262.1K contextImage inputTool callingNo reported score
No reported score
$0.67in$3.40out/ 1M tokens · USDExperiential · 18 endpointsStandard list rate
+Compare