Kimi-K2-Instruct-0905
About Kimi-K2-Instruct-0905
Kimi K2-Instruct-0905, a state-of-the-art mixture-of-experts (MoE) language model, is the latest, most capable version of Kimi K2. Key Features include enhanced coding capabilities, esp. front-end & tool-calling, context length extended to 256k tokens, and improved integration with various agent scaffolds.
Leverage Kimi-K2-Instruct-0905's advanced agentic coding, extensive 256k context, and robust tool-calling to tackle complex software development, system analysis, and automated workflow challenges.
Full-Stack Dev Agent
Design, implement, and debug complex software across front-end, back-end, and database layers, leveraging extensive context for large projects.
Use Case Example:
"Developed a complete e-commerce platform, from React UI to Node.js API and PostgreSQL schema, handling multi-file dependencies and integrating payment APIs."
Codebase Modernization
Analyze vast legacy codebases to identify refactoring opportunities, migrate to newer frameworks, and ensure architectural consistency.
Use Case Example:
"Migrated a monolithic Java application to a microservices architecture using Spring Boot, automatically rewriting thousands of lines of code and updating build scripts."
Automated Test Generation
Generate comprehensive test suites (unit, integration, E2E) for complex applications, identifying edge cases and ensuring robust code quality.
Use Case Example:
"Created a full suite of Playwright end-to-end tests for a complex web application, covering user flows and data validation, significantly reducing manual testing effort."
Agent Workflow Orchestration
Coordinate multiple AI agents or tools to execute complex, multi-step tasks, from data ingestion to analysis and report generation.
Use Case Example:
"Orchestrated a data pipeline agent to extract data from various APIs, a processing agent to clean and transform it, and a reporting agent to generate interactive dashboards."
Interactive UI Prototyping
Rapidly generate interactive front-end prototypes and components based on natural language descriptions, integrating with design systems.
Use Case Example:
"Built a dynamic dashboard component in Vue.js with real-time data visualization, responding to user input and adhering to a given design system, all from a text prompt."
Metadata
Specification
State
Deprecated
Architecture
Mixture of Experts
Calibrated
No
Mixture of Experts
Yes
Total Parameters
1000B
Activated Parameters
32B
Reasoning
No
Precision
FP8
Context length
262K
Max Tokens
262K
Compare with Other Models
See how this model stacks up against others.
Moonshot AI
chat
Kimi-K2.6
Release on: Apr 21, 2026
Total Context:
262K
Max output:
262K
Input:
$
0.77
/ M Tokens
Output:
$
4.0
/ M Tokens
Moonshot AI
chat
Kimi-K2.5
Release on: Jan 30, 2026
Total Context:
262K
Max output:
262K
Input:
$
0.45
/ M Tokens
Output:
$
2.25
/ M Tokens
Moonshot AI
chat
Kimi-K2-Thinking
Release on: Nov 7, 2025
Total Context:
262K
Max output:
262K
Input:
$
0.55
/ M Tokens
Output:
$
2.5
/ M Tokens
Moonshot AI
chat
Kimi-K2-Instruct-0905
Release on: Sep 8, 2025
Total Context:
262K
Max output:
262K
Input:
$
0.4
/ M Tokens
Output:
$
2.0
/ M Tokens
Moonshot AI
chat
Kimi-K2-Instruct
Release on: Jul 13, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.58
/ M Tokens
Output:
$
2.29
/ M Tokens
Moonshot AI
chat
Kimi-Dev-72B
Release on: Jun 19, 2025
Total Context:
131K
Max output:
131K
Input:
$
0.29
/ M Tokens
Output:
$
1.15
/ M Tokens
