Check.AI

Model reference · Synced 2025-04-29

Kimi K2 Instruct

Kimi K2 Instruct is an AI model from iFlow. 128K context window. Capabilities: reasoning, tool calling, open weights. Available on 17 providers. Cheapest listing: $0 input / $0 output per 1M tokens.

Quick facts

→ Add Kimi K2 Instruct to the comparison tool

Provider pricing

Same model, different providers, different prices. Cheapest first.

ProviderInput / 1MOutput / 1MContextListed
iFlow $0 $0 128K 2024-12-01
Nvidia $0 $0 128K 2025-01-01
NanoGPT $0.1 $2 256K 2025-07-01
IO.NET $0.39 $1.9 33K 2024-09-05
OpenCode Zen $0.4 $2.5 262K 2025-09-05
Deep Infra $0.5 $2 131K 2025-07-11
OpenRouter $0.55 $2.2 131K 2025-07-11
Vultr $0.55 $2.75 254K 2026-01-27
FastRouter $0.55 $2.2 131K 2025-07-11
Cortecs $0.551 $2.65 131K 2025-07-11
Jiekou.AI $0.57 $2.3 131K 2026-01
NovitaAI $0.57 $2.3 131K 2025-07-11
Fireworks AI $1 $3 128K 2025-07-11
Hugging Face $1 $3 131K 2025-07-14
Vercel AI Gateway $1 $3 131K 2025-07-14
LLM Gateway $1 $3 131K 2025-07-11
Groq $1 $3 131K 2025-07-14

Prices synced daily from models.dev + provider docs.

How to use this model

If you're picking Kimi K2 Instruct for a project, the three things that matter most:

Related models

FAQ

How much does Kimi K2 Instruct cost? $0 input / $0 output per 1M tokens at the cheapest listing. See the table above for other providers.

What is the context window? 128K tokens.

Which providers offer it? NanoGPT, OpenRouter, Fireworks AI, IO.NET, Jiekou.AI, iFlow, Hugging Face, NovitaAI, Deep Infra, OpenCode Zen, and others — see the full table above.

Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.