Kimi K2 0905
VerifiedMoonshot AI's Kimi K2 processes up to 262k tokens of text.
About Kimi K2 0905
Kimi K2 0905 is built as a proprietary LLM by Moonshot AI. Its architecture supports a context length of 262144 tokens while remaining limited to text input and output. The model is not released as open weights.
Its primary strength lies in managing extended documents and multi-turn conversations without losing coherence. This capability suits tasks where retaining information across tens of thousands of tokens matters.
Users typically apply Kimi K2 0905 to long-form text analysis, summarization of large corpora, and complex instruction following that benefits from the full context window.
Capabilities
How Kimi K2 0905 compares
Kimi K2 0905 (striped bar) vs other language models on intelligence, speed and price.
Price
USD per 1M output tokens · Lower is better · Kimi K2 0905 ranks #52 of 63
Sources: Artificial Analysis (intelligence, speed) · OpenRouter (price).
Best for
Long Document Analysis
The model processes and reasons over entire books, research papers, or legal contracts within its 262144-token window without losing earlier sections.
Extended Codebase Review
It handles large repositories or multi-file projects in a single prompt, enabling coherent refactoring suggestions and bug tracing across thousands of lines.
Multi-Turn Research Sessions
Users can maintain ongoing conversations that reference hundreds of prior messages or uploaded sources while preserving factual consistency.
Strengths & limitations
Strengths
- +Handles 256k token contexts
- +Strong extended-text comprehension
- +Efficient long-input processing
Limitations
- –Text-only modality
- –No vision capabilities
- –Higher resource use at max context
Cost calculator
Estimate what Kimi K2 0905 would cost for your usage.
Based on Kimi K2 0905's $0.60/1M input · $2.50/1M output. Estimate only — actual cost varies by provider and caching.
Quick start
OpenRouter's API is OpenAI-compatible — most SDKs work by just swapping the base URL. Only the model slug changes between models.
import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://openrouter.ai/api/v1",
apiKey: process.env.OPENROUTER_API_KEY,
});
const completion = await client.chat.completions.create({
model: "moonshotai/kimi-k2-0905",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(completion.choices[0].message.content);Model slug: moonshotai/kimi-k2-0905
Editor's verdict
Kimi K2 0905 is Moonshot AI's proprietary language models with a 262K-token context window.
At $2.50 per 1M output tokens, it is mid-priced for its class.
It is available through Moonshot AI's API and aggregators like OpenRouter.
Best suited to handles 256k token contexts and strong extended-text comprehension.
Frequently asked questions
The model supports a context window of 262144 tokens.
User reviews
Real, verified reviews from the community shape this model's rating.
Loading reviews…
Other Kimi models
Sibling versions in the Kimi family from Moonshot AI.
Similar models
Other language models worth comparing.