Bài học chính

• Hiện có 2 đường tích hợp đã được xác nhận trong bộ bằng chứng này: gọi Kimi K2.6 qua Kimi Open Platform bằng API tương thích OpenAI, hoặc dùng model `@cf/moonshotai/kimi-k2.6` trên Cloudflare AI. [1][3][8] Với app/production workflow, hướng rõ ràng nhất là API chính thức vì Kimi
• ## Cách tích hợp phù hợp nhất cho app / production

Câu trả lời nghiên cứu

from openai import OpenAI

client = OpenAI(
    api_key="$MOONSHOT_API_KEY",
    base_url="https://api.moonshot.ai/v1",
)

completion = client.chat.completions.create(
    model="PUT_K2_6_MODEL_ID_HERE",
    # ... payload theo quickstart K2.6
)

Hỗ trợ hình ảnh

Trao đổi nghiên cứu

from openai import OpenAI

client = OpenAI(
    api_key="$MOONSHOT_API_KEY",
    base_url="https://api.moonshot.ai/v1",
)

completion = client.chat.completions.create(
    model="PUT_K2_6_MODEL_ID_HERE",
    # ... payload theo quickstart K2.6
)

Người ta cũng hỏi

Tiếp tục nghiên cứu của bạn

Nguồn

• [1] kimi-k2.6 (Moonshot AI) - Cloudflare Docsdevelopers.cloudflare.com

  "description": "The input text prompt for the model to generate a response.". "description": "An upper bound for the number of tokens that can be generated for a completion.". "description": "Output types requested from the model (e.g. "description": "An upper bound for the number of tokens that can be generated for a completion.". "description": "Output types requested from the model (e.g. "description": "The model used for the chat completion.". "description": "The input text prompt for the model to generate a response.". "description": "An upper bound for the number of tokens that can be g…

• [2] Moonshot AI (Kimi K2.6) - TypingMind Docsdocs.typingmind.com

  Moonshot AI (Kimi K2.6). ## Step 1: Create a Moonshot API account. Go to and create a new Moonshot API account. ## Step 2: Set up Moonshot API account. To use the model via API, you’ll need to add balance to your account. ## Step 3: Get your Moonshot API key. Be sure to copy and save it securely — you’ll need it to set up Kimi K2 on TypingMind. ## Step 4: Set up Kimi as custom model on TypingMind. On TypingMind, go to Models —> Add Custom Models and enter the following details:. * Enter the endpoint: https://api.moonshot.ai/v1/chat/completions. * Enter the Model ID and context length: `ki…

• [3] docs/deploy_guidance.md · moonshotai/Kimi-K2.6 at mainhuggingface.co

  docs/deploy_guidance.md · moonshotai/Kimi-K2.6 at main. * Models. * Docs. # . moonshotai. Kimi-K2.6. Moonshot AI 8.99k. [Image-Text-to-Text](https://huggingface.co/models?p…

• [4] Kimi K2.6 - Kimi API Platformplatform.kimi.ai

  Skip to main content. * Kimi K2.6 Multi-modal Model. * Kimi K2. * Using Thinking Models. * Overview of Kimi K2.6 Model. * Long-Thinking Capabilities. * [Example Usage]…

• [5] Kimi-K2/docs/deploy_guidance.md at main - GitHubgithub.com

  Skip to content. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert. * Code. * [Issues 61](https…

• [6] MoonshotAI: Kimi K2.6 – API Quickstart | OpenRouteropenrouter.ai

  MoonshotAI: Kimi K2.6. ### moonshotai/kimi-k2.6. Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end-to-end coding tasks across Python, Rust, and Go, and can convert prompts and visual inputs into production-ready interfaces. ## Sample code and API for Kimi K2.6. ### OpenRouter normalizes requests and responses across providers for you. OpenRouter supports reasoning-enabled models that can show their step-by-step thinking process. Use the reasoning parameter in…

• [7] Kimi K2 is the large language model series developed by Moonshot ...github.com

  Skip to content. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert. * Code. * Issues 61. * Pull requests 3. * [Actions](https://github.c…

• [8] Kimi K2.6 Now on SiliconFlow: SOTA Long-horizon Codingsiliconflow.com

  Kimi K2.6 Now on SiliconFlow: SOTA Long-horizon Coding. This open-source multimodal model delivers state-of-the-art long-horizon coding, autonomous agent orchestration, and coding-driven design capabilities. With 58.6 on SWE-Bench Pro and 86.3 on BrowseComp (Agent Swarm), K2.6 outperforms leading closed-source models in agentic workflows. Start building with SiliconFlow's API today to explore long-horizon coding tasks. Kimi K2.6, Moonshot AI's latest open-source multimodal agentic model. This release brings exceptional long-horizon coding capabilities, proactive autonomous execution, and sw…

• [9] Moonshot AI Open-Sources Kimi K2.6 — A Coding Model ...chatlyai.app

  Moonshot AI Open-Sources Kimi K2.6 — The Coding Model That Runs for Days. Moonshot AI Open-Sources Kimi K2.6 — The Coding Model That Works for Days Without You. Written by Muhammad Bin Habib. Explore what Kimi K2.6's release means for developers, and open-source AI. # Moonshot AI Open-Sources Kimi K2.6 — A Coding Model That Runs Autonomously for Days. Beijing / April 21, 2026 — Moonshot AI has released Kimi K2.6 to the open-source community — a model that executes complex engineering tasks for hours, sometimes days, without a human in the loop. Available immediately via Kimi.com, the…

• [10] Kimi API Platformplatform.moonshot.ai
  • . * . * . * . * . * ![Image 14: CodeBuddy](https://platform.moonshot.ai/_next/image?url=%2Fpa…
• [11] Moonshot AImoonshot.ai

  . KimiAPIResearchDownloadCareers. . KimiAPIResearchDownloadCareers. ![Image 3](bl…

• [12] Moonshot AI Open-Sources Kimi K2.6, Advancing Multi ...pandaily.com

  Moonshot AI Open-Sources Kimi K2.6, Advancing Multi-Agent Collaboration. # Moonshot AI Open-Sources Kimi K2.6, Advancing Multi-Agent Collaboration. Moonshot AI has open-sourced its Kimi K2.6 model, introducing stronger multi-agent collaboration and matching top closed-source models in key benchmarks. Moonshot AI has officially released and open-sourced its flagship Kimi K2.6 model, less than three months after launching K2.5. Kimi K2.6 focuses on overcoming limitations in multi-agent collaboration. Building on K2.5’s Agent Swarm capability, the new version introduces enhanced support for the…

• [13] Best Practices for Benchmarking - Kimi API Platformplatform.kimi.ai

  | ZeroBench w/ tools | 1.0 | max tokens = 64k | 3 | top_p=0.95 | Recommended max steps = 30 thinking={"type": "enabled"} |. | AIME2025 w/ tools | 1.0 | per turn tokens = 96k; total max tokens = 96k | 32 | top_p=0.95 | thinking={"type": "enabled"} Recommended max steps = 120 |. | HMMT2025 w/tools | 1.0 | per step tokens = 96k; total tokens = 96k | 32 | top_p=0.95 | thinking={"type": "enabled"} Recommended max steps = 120 |. | Agentic Search Task | BrowseComp / BrowseComp-ZH / Seal-0 / Frames | 1.0 | per step tokens = 24k; total max tokens = 256k | 4 | top_p=0.95 | thinking={"type": "enable…

• [14] API Overview - Kimi API Platformplatform.kimi.ai

  Using the API. ##### API Reference. ##### Batch API. # API Overview. https://api.moonshot.aihttps://api.moonshot.ai. Kimi Open Platform provides OpenAI-compatible HTTP APIs. You can use the OpenAI SDK directly. When using SDKs, set base_url to https://api.moonshot.ai/v1. When calling HTTP endpoints directly, use the full path such as https://api.moonshot.ai/v1/chat/completions. ## ​ OpenAI Compatibility. Our API is compatible with the OpenAI Chat Completions API in request/response format. * Simply point base_url to https://api.moonshot.ai/v1 to switch. All API requests requir…

• [15] Generation Model Kimi K2 Pricing - Kimi API Platformplatform.kimi.ai

  🎉 New kimi k2.5 Multi-modal Model released! ##### Model Pricing. # Generation Model Kimi K2 Pricing. The prices in the table represent the cost per 1M tokens consumed. * Kimi K2 is a Mixture-of-Experts (MoE) foundation model with exceptional coding and agent capabilities, featuring 1 trillion total parameters and 32 billion activated parameters. In benchmark evaluations covering general knowledge reasoning, programming, mathematics, and agent-related tasks, the K2 model outperforms other leading open-source models. * kimi-k2-0905-preview: Context length 256k. Based on kimi-k2-0711-preview, w…

• [16] Kimi K2 Quickstart - Kimi API Platformplatform.kimi.ai

  from openai import OpenAI from openai import OpenAI client = OpenAI(client = OpenAI( api_key = "$MOONSHOT_API_KEY", api_key = "$MOONSHOT_API_KEY", base_url = "https://api.moonshot.ai/v1", base_url = "https://api.moonshot.ai/v1",)) completion = client.chat.completions.create(completion = client.chat.completions.create( model = "kimi-k2-turbo-preview", model = "kimi-k2-turbo-preview", messages = [ messages = [ {"role": "system", "content": "You are Kimi, an AI assistant provided by Moonshot AI. curl https://api.moonshot.ai/v1/chat/completions \ curl https://api.moonshot.ai/v1/chat/completions \…

• [17] Main Concepts - Kimi API Platformplatform.kimi.ai

  ​ Text and Multimodal Models. Text generation models process text in units called Tokens. ## ​ Rate Limits. Rate limits are measured in four ways: concurrency, RPM (requests per minute), TPM (Tokens per minute), and TPD (Tokens per day). For the gateway, for convenience, we calculate rate limits based on the max_completion_tokens parameter in the request. This means that if your request includes the max_completion_tokens parameter, we will use this parameter to calculate the rate limit. If your request does not include the max_completion_tokens parameter, we will use the default max\…

• [18] Migrating from OpenAI to Kimi APIplatform.kimi.ai

  Moonshot AI is a proper noun and should not be translated into other languages."}, {"role": "user", "content": "Please search the internet for Context Caching and tell me what it is."} # The user asks Kimi to search online {"role": "user", "content": "Please search the internet for Context Caching and tell me what it is."} # The user asks Kimi to search online]] finish_reason = None finish_reason = None # ==========================================================================================================================================================# ==================================…

• [19] Model Inference Pricing Explanation - Kimi API Platformplatform.kimi.ai

  Model Pricing. # Model Inference Pricing Explanation. ### ​ Billing Unit. Token: A token represents a common sequence of characters. The number of tokens used for each English character may vary. Generally speaking, for a typical English text, 1 token is roughly equivalent to 3-4 English characters. The exact number of tokens generated by each call can be obtained through the Token Calculation API. #### ​ Billing Logic. Chat Completion API charges: We bill both the Input and Output based on usage. If you upload and extract content from a document and then pass the extracted content as I…

• [20] Multi-modal Model Kimi K2.5 Pricing - Kimi API Platformplatform.kimi.ai

  🎉 New kimi k2.5 Multi-modal Model released! Now supports multimodal understanding and processing. Kimi API Platform home pagelight logodark logo. ##### Model Pricing. ##### Support. # Multi-modal Model Kimi K2.5 Pricing. ## ​ Product Pricing. Explanation: Prices exclude applicable taxes. Specific tax obligations are subject to local tax regulations and will be calculated at checkout based on your jurisdiction. Here, 1M = 1,000,000. The prices in the table represent the cost per 1M tokens consumed. ## ​ Model Description. * Kimi K2.5 is Kimi’s most intelligent model to date. It is also Ki…

• [21] Multi-modal Model Kimi K2.6 Pricingplatform.kimi.ai

  🎉 Kimi K2.6 has been released with improved long-context coding stability. Top-up bonus event in progress 🔗. Kimi API Platform home pagelight logodark logo. ##### Model Pricing. ##### Promotions. ##### Support. # Multi-modal Model Kimi K2.6 Pricing. ## ​ Product Pricing. Explanation: Prices exclude applicable taxes. Specific tax obligations are subject to local tax regulations and will be calculated at checkout based on your jurisdiction. Here, 1M = 1,000,000. The prices in the table represent the cost per 1M tokens consumed. ## ​ Model Description. * Kimi K2.6 is Kimi’s latest and most…

• [22] Using Playground to Debug Model - Kimi API Platformplatform.kimi.ai
  2. Experience the model's tool calling capabilities using Kimi Open Platform's built-in tools. * Kimi Open Platform provides officially supported tools that execute for free. You can select tools in the playground, and the model will automatically determine whether tool calls are needed to complete your instructions. If tool calls are required, the model will generate parameters according to the tool's requirements and integrate them into the final answer. * Currently supported tools: Date/Time tools, Excel file analysis tools, Web search tools, Random number generation tools, etc. * Currentl…
• [23] Frequently Asked Questions and Solutions - Kimi API Platformplatform.kimi.ai

  In this case, the Kimi API will only return content within the max_completion_tokens limit, and any excess content will be discarded, resulting in the aforementioned “incomplete content” or “truncated content.” When encountering finish_reason=length, if you want the Kimi large language model to continue generating content from where it left off, you can use the Partial Mode provided by the Kimi API.

• [24] WebSearch Pricing - Kimi API Platformplatform.kimi.ai

  Kimi K2.6 Open Platform, providing trillion-parameter K2.5 large language model API, supporting 256K long context and Tool Calling.