HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

Kimi K2 Instruct

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

Kimi K2 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Trained with the Muon optimizer, Kimi K2 achieves exceptional performance across frontier knowledge, reasoning, and coding tasks while being...

Start for free ← All models
moonshotai/Kimi-K2-Instruct On request
text->text · moonshotai · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
—
Parameters
131K
Context window
1236GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Context window 131,072 tokens
Minimum VRAM 1236 GB
Architecture DeepseekV3ForCausalLM (vLLM)
License open-weights
Modality text->text
Released July 2025
Publisher moonshotai ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Dedicated GPU · per hour
from €54,00 per hour
Your own vLLM instance on European cloud (1236 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

62.7 / 100 · Measured

Measured by Epoch AI across 7 benchmarks, with a range.

Range 57.8 to 65.2 · Rank 119 of 277 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 15-10-2026

LiveBench · 48.1
Reasoning 42.2
Coding 74.3
Agentic coding 31.7
Mathematics 58.2
Data analysis 43.3
Language 66.7
Instruction following 20.4
Every benchmark (7)
Lech Mazur Writing 85.6
Fiction.LiveBench 61.1
Aider polyglot 59.1
WeirdML 39.4
Terminal Bench 27.8
SimpleBench 11.6
GSO-Bench 4.9
LiveBench · All tasks
Reasoning
theory of mind 51.9
zebra puzzle 21.0
spatial 62.0
logic with navigation 34.0
Coding
code generation 74.7
code completion 73.9
Agentic coding
javascript 35.0
typescript 15.0
python 45.0
Mathematics
AMPS Hard 82.0
integrals with game 7.0
math comp 72.6
olympiad 71.1
Data analysis
consecutive events 3.2
tablejoin 32.7
tablereformat 94.1
Language
connections 78.2
plot unscrambling 45.9
typos 76.0
Instruction following
paraphrase 13.0
simplify 20.3
story generation 24.3
summarize 23.9

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/Kimi-K2-Instruct",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run Kimi K2 Instruct in the EU?

Yes. HostYourAI runs Kimi K2 Instruct on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting Kimi K2 Instruct GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does Kimi K2 Instruct cost?

Kimi K2 Instruct is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from Moonshotai

Kimi K3

Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date. It is a 2.8T-parameter model built on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with native vision capabilities and a 1-million-token context window. It is the world's first open 3T-class model, designed for frontier intelligence across long-horizon coding, knowledge work, and reasoning.

1M context View model →
Kimi K2.7 Code

Kimi K2.7 Code is a coding-focused agentic model built upon Kimi K2.6. With substantial improvements on real-world long-horizon coding tasks, it strengthens end-to-end task completion across complex software engineering workflows while improving token efficiency, reducing thinking-token usage by approximately 30% compared with Kimi K2.6.

1027B 262K context View model →
Kimi K2.6

Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

1027B 262K context View model →
Kimi K2.5

Kimi K2.5 is an open-source, native multimodal agentic model built through continual pretraining on approximately 15 trillion mixed visual and text tokens atop Kimi-K2-Base. It seamlessly integrates vision and language understanding with advanced agentic capabilities, instant and thinking modes, as well as conversational and agentic paradigms.

1027B 262K context View model →
Kimi K2 Thinking

Kimi K2 Thinking is the latest, most capable version of open-source thinking model. Starting with Kimi K2, we built it as a thinking agent that reasons step-by-step while dynamically invoking tools. It sets a new state-of-the-art on Humanity's Last Exam (HLE), BrowseComp, and other benchmarks by dramatically scaling multi-step reasoning depth and maintaining stable tool-use across 200–300 sequential calls. At the same time, K2 Thinking is a native INT4 quantization model with 256k context window, achieving lossless reductions in inference latency and GPU memory usage.

1026B 262K context View model →
Kimi Linear 48B A3B Base

Kimi Linear is a hybrid linear attention architecture that outperforms traditional full attention methods across various contexts, including short, long, and reinforcement learning (RL) scaling regimes. At its core is Kimi Delta Attention (KDA)—a refined version of Gated DeltaNet that introduces a more efficient gating mechanism to optimize the use of finite-state RNN memory.

49B View model →

Try Kimi K2 Instruct for free

Creating an account takes a minute. Test Kimi K2 Instruct straight away in the playground.

Start for free