Moonshot AI

Kimi K2

Vérifié par l’équipe de recherche de GetInfoUsDernière révision : October 2026Politique éditoriale
Géant agentique open sourceOfficial Source Verified ↗
83
Intelligence Index

Moonshot d'AI landmark 1-billions paramètre ouvert MoE modèle de fondation développé pour autonome agents, profond codage, et outil exécution.

Technical Specifications

Provider
Moonshot AI
Category
open-source
Release Date
2025-07
Knowledge Cutoff
May 2025
Architecture
Trillion-Scale Sparse Mixture-of-Experts Transformer
Parameters
1T total (32B active MoE)
Context Window
131K tokens
Max Output
16K tokens
Cached Input Price
$0 / 1M tokens
Batch API Discount
Standard rate
Consumer Subscription
Free / Self-Hosted
Reasoning Mode
Yes (Chain-of-Thought)
Reasoning Effort Control
Configurable (Low / Med / High)
Tool Calling
Yes
Structured Outputs
Yes
Open Weights
Yes (Open Source / Self-Hostable)
Input Modalities
text
Output Modalities
text
Official Documentation
Visit Official Docs ↗

Data Privacy, Licensing & Deployment Governance

API Data Training Policy
100% Isolated when self-hosted on private GPUs or VPC
Model License & Commercial Rights
Open-Weights Research & Commercial License
Deployment & Cloud Availability
Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API
Output Ownership
Full commercial ownership of generated outputs

Official Provider Release Intelligence, API Quotas & Agentic Specs

Compare Multi-Models Side-by-Side →
Official API Model ID (SDK String)
kimi-k2
Supported SDK & API Protocol
OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI
Lifecycle & Deprecation Status
Active GA (Guaranteed support through 2027+)
Production Rate Limits (RPM & TPM)
Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud
Long-Context Pricing Tier (>128K / >200K)
Free across full context window (only KV-cache VRAM scales)
Prompt Cache Write & TTL Policy
Automatic prefix KV-caching in vLLM / SGLang (0 cost)
Computer Use & Browser GUI Agent
API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
MCP & Parallel Tool Calling
Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
Web Search Grounding & Code Sandbox
Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
Fine-Tuning & Distillation Support
Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory)
Multimodal Tokenization Billing
Text BPE (~4 chars/token)
Weights Precision & Quantization
BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0)
Minimum GPU VRAM Requirement
620 GB VRAM (4-bit Quantized) · 2150 GB VRAM (Native BF16)
Supported Inference Engines
vLLM, SGLang, Ollama, llama.cpp, TensorRT-LLM, HuggingFace TGI
System Card & Safety Framework
Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma)
Enterprise Compliance (SOC2 / HIPAA / ZDR)
100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control
Engineering & Pricing Workbench

Kimi K2 Cost, Context, Hardware & API Integration

500 / day
4,000 tok
1,000 tok
Conversation Depth (History Re-billing):1 Turn (Single-Shot)
50%
Estimated Monthly API Cost (30 Days)
Free ($0)
Subscription ($20/mo) vs API

Open-weights or free-tier model: $0 API license cost when self-hosted.

Same Monthly Workload Cost Across Popular Reference Models

Kimi K2 (Active)
$0.00
/ month
Gemini 2.5 Flash
$18.00
/ month
DeepSeek V3
$32.70
/ month
GPT-4o
$300.00
/ month
Claude 3.7 Sonnet
$405.00
/ month

Live Prompt Paste Tokenizer & Cost Counter

Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.

Chars / Words
175 / 24
OpenAI o200k
~46 tok
Claude BPE
~49 tok
Llama / DeepSeek
~51 tok

Hybrid Prompt Routing Cascade Simulator

Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Kimi K2:

Cascaded Monthly Bill:$13.50/mo
This model is already priced at or below the fast router baseline.

Benchmark Scores & 6-Axis Capability Radar

Benchmark Encyclopedia
Coding (53)Reasoning (76)Knowledge (81)Speed (41)Context (75)Cost Value (98)
Kimi K22026 Frontier Median
SWE-bench Verified
46%
GPQA Diamond
66.5%
MMLU-Pro
80.5%
HumanEval
91%
Chatbot Arena Elo
1360pts

Strengths

  • massif 1T paramètre knowledge base avec efficient 32B actif paramètre inférence
  • natif multi-étapes agent planning et complexe environment interaction
  • à poids ouverts permitting complet auto-hébergé d'entreprise déploiement

Limitations & Trade-offs

  • nécessite substantiel distributed VRAM infrastructure pour complet-précision hosting
  • texte-seulement interface sans natif visuel compréhension

Editorial Assessment

un monumental open source achievement qui established Moonshot AI sur le mondial agent stage.

Best for: d'entreprise autonome agents, privé ingénierie logicielle pipelines, et complexe appel d'outils

Frequently Asked Questions about Kimi K2

How much does the Kimi K2 API cost per 1M tokens?+

Kimi K2 by Moonshot AI is priced at $0 per 1M input tokens and $0 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.

Should I use a $20/month subscription or the Kimi K2 pay-as-you-go API?+

A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.

How many words and pages fit in Kimi K2's context window?+

Kimi K2 features a 131K tokens context window, which equals approximately 98,304 English words or ~262 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 16,384 tokens.

Can I run Kimi K2 locally on my own GPU (Open Weights)?+

Yes, Kimi K2 (1T total (32B active MoE)) releases open weights that can be self-hosted locally or on private cloud GPUs using vLLM, Ollama, SGLang, or llama.cpp.

Does Moonshot AI train on data sent to the Kimi K2 API, and is commercial use allowed?+

100% Isolated when self-hosted on private GPUs or VPC. License tier: Open-Weights Research & Commercial License. Full commercial ownership of generated outputs. Supported deployment channels include: Self-Hosted GPU (vLLM / Ollama), Private VPC, or Managed Serverless API.

How does Kimi K2 perform on coding and reasoning benchmarks?+

Kimi K2 achieves a composite Intelligence Index of 83/100, scoring 46% on SWE-bench Verified, 66.5% on GPQA Diamond, 80.5% on MMLU-Pro, and 1360 pts on Chatbot Arena Elo.

What is Kimi K2 best used for?+

Kimi K2 is best suited for: d'entreprise autonome agents, privé ingénierie logicielle pipelines, et complexe appel d'outils. Assessment: un monumental open source achievement qui established Moonshot AI sur le mondial agent stage.

Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.

Sources: Moonshot AI Kimi K2 Technical Report & Hugging Face↗