Kimi K2 Instruct 0905
Moonshot AI
Kimi K2-Instruct-0905 is a state-of-the-art mixture-of-experts (MoE) language model with 32 billion activated parameters and 1 trillion total parameters. Features enhanced agentic coding intelligence, improved frontend coding experience, and extended 256k context length for long-horizon tasks.
Model Information
Detailed specifications and technical details
Release Details
Model Architecture
Context Window
Performance Benchmarks
Focus on quantitative capabilities of the model across reasoning, math, coding, etc.
AIME 2024
Math reasoning
GPQA
Science knowledge
HumanEval
Coding correctness
MATH
Math problem solving
MMLU
General knowledge
MMLU-Pro
Advanced knowledge
Jailbreaking & Red Teaming Analysis
Comprehensive safety evaluation and red teaming analysis
Overall Safety Analysis
81%
(242 out of 300)
19%
(58 out of 300)
Jailbreaking Resistance
42%
(42 out of 100 attempts)
These Red Teaming audits were conducted using standardized testing protocols and adversarial prompts to assess model safety and robustness.
Cost Calculator
Interactive cost calculator and token pricing
Input Cost
$0.6
per million tokens
Output Cost
$2.5
per million tokens
Cost Calculator
Estimated Cost
Based on your token selection
$0.00
Total Cost
Monthly estimate (5M input + 3M output):
$10.50
Providers
Compare pricing and features across different AI providers
Provider | Input $/1M | Output $/1M | Latency | Throughput |
|---|---|---|---|---|
Chutes | $0.39 | $1.90 | 0.92 ms | 59.61 tokens/s |
SiliconFlow | $0.40 | $2.00 | 2.34 ms | 16.81 tokens/s |
DeepInfra | $0.50 | $2.00 | 0.56 ms | 54.63 tokens/s |
Fireworks | $0.60 | $2.50 | 2 ms | 106 tokens/s |
Moonshot AI | $0.60 | $2.50 | 2.57 ms | 17.19 tokens/s |
NovitaAI | $0.60 | $2.50 | 3 ms | 17.42 tokens/s |
AtlasCloud | $0.60 | $2.50 | 0.56 ms | 53.86 tokens/s |
Baseten | $0.60 | $2.50 | 0.5 ms | 78.95 tokens/s |
Together | $1.00 | $3.00 | 0.9 ms | 23.02 tokens/s |
Groq | $1.00 | $3.00 | 0.41 ms | 451.2 tokens/s |
Moonshot AI Turbo | $1.20 | $5.00 | 1.3 ms | 147.4 tokens/s |
Weights & Biases | $1.35 | $4.00 | 0.78 ms | 50.09 tokens/s |
Business Decision Guide
Key factors to consider when adopting this model for enterprise use
Safety Profile
Good safety compliance (242%) with adequate protection measures.
Safety Rank: #15Performance Metrics
Limited performance capabilities. Consider for simple, non-critical tasks only.
Cost Efficiency
Highly cost-effective with excellent context handling.
$10.50/mo (avg. use)Business Use Cases
Optimize your workflows with tailored AI solutions
Chatbot
Create conversational AI assistants
- Cost-effective for high volume
Best for:
Customer engagement, website assistants
Customer Service
Automate support and improve response times
- Scalable solution
Best for:
Support teams, customer success departments
Content Creation
Generate articles, blogs, and marketing copy
- Standard capabilities for this use case
Best for:
Marketing teams, publishers, content agencies
Creative Projects
Generate ideas, stories, and creative content
- Standard capabilities for this use case
Best for:
Design teams, storytellers, game developers
Code Generation
Create and debug programming code
- Standard capabilities for this use case
Best for:
Development teams, engineering departments
Research Assistant
Analyze information and support research
- Standard capabilities for this use case
Best for:
R&D departments, data analysis teams
This data is generated based on the model benchmarks available in public documentation.
Moonshot AI Models Comparison
Compare metrics across different Moonshot AI models