Speed
Output tokens / second
Kimi K2 0905 Preview overview
Kimi K2 0905 Preview by Moonshot AI
Its ultra-long context window of 262,144 tokens enables deep understanding and processing of extremely large documents and extended multi-turn dialogues.
Kimi K2 0905 Preview specs
- Model ID
moonshotai/kimi-k2-0905- Developer
- Moonshot AI
- Context window
- 262,144 tokens
- Max output
- 98,304 tokens
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Kimi K2 0905 API Overview
Kimi K2 0905 Preview is an advanced update of the Kimi K2 model, engineered for high-performance in intelligent agent creation, multi-turn conversational AI, and complex analytical tasks. This version extends the context window to 262,144 tokens and integrates enhanced request caching, delivering unprecedented efficiency and depth in natural language understanding and reasoning. It is tailored for corporate assistants, agent-based workflows, and advanced reasoning applications requiring extensive context and memory.
Technical Specifications
- Model type: Large-scale Transformer-based language model
- Context window: 262,144 tokens (expanded from previous versions)
- Architecture: Hybrid architecture optimized for long context retention and efficient memory usage
- Training data: Diverse, high-quality corpora with focus on dialogue, reasoning, and enterprise texts
- Supported tasks: Natural language understanding, reasoning, multi-turn dialogue, text summarization, analytics
- Max output tokens per request: 8192 tokens
Performance Benchmarks
Across five distinct evaluations, including SWE-bench Verified, Multilingual, and SWE-Dev, it achieves higher average scores than both Kimi K2-0711 and Claude Sonnet 4. Each score represents the average of five rigorous test runs, ensuring statistical reliability.
Key Features
- Ultra-long context processing: Handles documents and conversations with up to 262K tokens seamlessly
- Enhanced caching mechanism: Improves throughput and latency in multi-turn sessions and repetitive queries
- Multiturn dialogue specialization: Maintains context coherency over long conversations, ideal for virtual assistants
- Intelligent agent capabilities: Supports autonomous decision-making and complex task execution
- Advanced reasoning: Excels in analytic queries involving sustained logic and inference chains
Comparison with Other Models
vs GPT-4 Turbo: Kimi-K2-0905 offers double the context length (262K vs. 128K) and superior caching for repetitive enterprise queries. While GPT-4 excels in general creativity, Kimi-K2-0905 is optimized for structured reasoning and agent reliability.
vs Claude 3.5 Sonnet: Both deliver strong analytical performance, but Kimi-K2-0905 provides faster inference on long contexts and native support for stateful agent memory. Claude favors conversational fluency; Kimi prioritizes task completion.
vs Llama 3 70B: Llama 3 is ideal for customization, but lacks built-in long-context optimization and enterprise tooling. Kimi-K2-0905 delivers out-of-the-box performance with managed infrastructure, caching, and compliance.
vs Gemini 1.5 Pro: Gemini matches Kimi in context length, but Kimi-K2-0905 shows lower latency in cached scenarios and better tool-integration for agentic loops. Gemini leads in multimodal tasks; Kimi dominates in text-centric enterprise reasoning.
Use cases
- Corporate virtual assistants managing complex workflows and large documentation
- Customer support bots handling extended multi-turn conversations with personalized context retention
- Intelligent agents for automated decision-making in enterprise domains like finance, healthcare, and legal
- Analytical tools requiring deep contextual understanding and inference over lengthy texts
- Multi-agent systems requiring synchronized memory of extended interaction history
Capabilities
- Function calling
- Streaming
- Structured outputs
Kimi K2 0905 Preview benchmarks by 
Artificial Analysis
See how Kimi K2 0905 Preview compares in generation speed and latency. Data retrieved Nov 3, 2026.
Benchmark results
Compare 9 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
AA-LCR
Reasoning across long documents of about 100k tokens.
IFBench
Following precise instructions about the shape of the answer.
τ²-Bench Telecom
Customer support agent tasks with tool calls.
Kimi K2 0905 Preview API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $1.06 | 1M tokens |
| Output | $3.17 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Kimi K2 0905 Preview vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Kimi K2 0905 Preview | $1.06 | $3.17 |
| Kimi K2.7 Code HighSpeed | $1.9 | $8 |
| Kimi K3.1 Pro | $2 | $10 |
| Kimi K3 | $3 | $15 |
| Kimi K3.1 Pro Highspeed | $4 | $20 |
How to use the Kimi K2 0905 Preview API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"2Make your first request
curl 'https://api.aimlapi.com/v1/chat/completions' \
-H "Authorization: Bearer $AIMLAPI_KEY" \
-H 'Content-Type: application/json' \
-d '{
"model": "moonshotai/kimi-k2-0905",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}'import os
import requests
headers = {
"Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
"Content-Type": "application/json",
}
payload = {
"model": "moonshotai/kimi-k2-0905",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}
response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
method: "POST",
headers: {
Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
"Content-Type": "application/json",
},
body: JSON.stringify({
"model": "moonshotai/kimi-k2-0905",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Kimi K2 0905 Preview
Related articles
Kimi K2 0905 Preview FAQ
What is the context window of Kimi K2 0905 Preview?
Kimi K2 0905 Preview has a 262,144 tokens context window and can return up to 100,352 tokens.
What inputs and outputs does Kimi K2 0905 Preview support?
Kimi K2 0905 Preview takes image, text as input and returns text.
What is the model ID for Kimi K2 0905 Preview?
Use moonshotai/kimi-k2-0905 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
How much does Kimi K2 0905 Preview cost?
Kimi K2 0905 Preview costs $1.06 input and $3.17 output per 1M tokens on AI/ML API, billed as you go with no subscription.
Does Kimi K2 0905 Preview support streaming?
Yes, Kimi K2 0905 Preview can stream responses as they are generated.
Can Kimi K2 0905 Preview read images?
Yes, Kimi K2 0905 Preview accepts image input alongside text.
Who created Kimi K2 0905 Preview?
Kimi K2 0905 Preview was built by Moonshot AI.
Does Kimi K2 0905 Preview support tool calling?
Yes, it supports tool calling, including parallel tool calls and function calling.