Kimi K2 Instruct 0905

Released
2025-09-05
Last refreshed
2026-10-07
Status
Researched 163d ago
Open sourceCommercial use: permittedLong context
Moonshot AI releases · 7 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
Pretrained
Created by
Moonshot AI

Lossless long-context AI innovation

Beijing, China
Founded 2023
Website
Pricing
Output / 1M
$2.50
Input / 1M
$0.600

Cheapest of 3 routes · Fireworks AI

Providers(3)
Fireworks AINVIDIA NIMOpenRouter
View 3 provider routes

About

Kimi K2 Instruct 0905 is Moonshot AI's Kimi K2 model. It offers a 131K-token context window.

Providers(3)

Compare all 3

Compare API pricing across 3 tracked provider routes for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Fireworks AI$0.600$2.50
Serverless
OpenRouter$0.600$2.50
Serverless
NVIDIA NIM--
ServerlessPartial

Available via routers & gateways(2)

OpenRouter

Hybrid

Unified hybrid gateway to 500+ models from 80+ providers via a single OpenAI-compatible API, with an optional Auto Router that selects a model per prompt from market spend data.

Passthrough + feeFireworks 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; deprecated in favor of NVIDIA NeMo Switchyard.

Free OSSNVIDIA NIM

Capabilities

No model capability flags are currently sourced.

Benchmark peer barsfor Long context

No task-mapped benchmark peers are available for this model yet.

Migration checks

No linked migration route is available for this model yet.