Kimi K2 Instruct

Name: Kimi K2 Instruct
Author: Moonshot AI

Released

2025-09-05

Last refreshed

2026-10-07

Status

Researched 136d ago

Open sourceCommercial use: permittedRAGLong contextClassificationJSON / Tool use

Moonshot AI releases · 6 in the last 12 months · this family litChangelog →

Specifications

Family: Kimi K2
Released: 2025-09-05
Context: 128K
Parameters: 1T total, 32B active (MoE)
Architecture: Decoder Only
Specialization: general
Openness: Open source
License: MITOSI-approvedPermitted
Weights: Unknown
Code: Unknown
Training: Fine-tuned

Created by

Moonshot AI

Lossless long-context AI innovation

Beijing, China

Founded 2023

Website

Pricing

Output / 1M

$2.30

Input / 1M

$0.570

Cheapest of 6 routes · Novita AI

Providers(6)

Fireworks AI Together AI NVIDIA NIM Vercel AI Gateway Novita AI Featherless

View 6 provider routes

About

Kimi K2 Instruct is an instruction-tuned language model from Moonshot AI, available via Fireworks AI.

Providers(6)

Compare all 6

Compare API pricing across 6 tracked provider routes for input and output tokens, batch, and cached reads when available.

Provider	Input / 1M	Output / 1M	Route
Novita AI	$0.570	$2.30	Serverless
Vercel AI Gateway	$0.570	$2.30	Serverless
Featherless	$0.600	$2.50	Serverless
Fireworks AI	$0.600	$2.50	Serverless
Together AI	$1.20	$4.50	Serverless
NVIDIA NIM	-	-	ServerlessPartial

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 400+ models from 60+ providers via a single OpenAI-compatible API, with optional auto-routing that selects the best model per prompt.

PassthroughTogether AIFireworks AI

NVIDIA LLM Router Blueprint

Router

NVIDIA's open-source AI blueprint for LLM routing that selects the optimal model per prompt via intent classification or neural auto-routing; being deprecated 2026-06-20.

Free OSSNVIDIA NIM