Kimi K3
5.0 out of 5 starsAverage Ratings 0 Ratings
Average Ratings 1 Rating
Description
Inkling 2 Small is a general-purpose multimodal AI model developed by Thinking Machines Lab for software engineering, advanced reasoning, visual analysis, and autonomous agent applications. The model features a sparse mixture-of-experts architecture containing 594 billion total parameters, with approximately 17 billion parameters activated during inference. Its one-million-token context window supports processing large documents, software repositories, extended conversations, and complex collections of information. Inkling 2 Small accepts text and image inputs and generates text outputs, enabling visual reasoning, programming assistance, document analysis, and multimodal problem-solving. Its agentic coding capabilities support autonomous software development, code debugging, repository modifications, application creation, and verification of completed engineering tasks. The model can also perform extended research workflows involving machine learning experimentation, GPU kernel optimization, data analysis, and iterative scientific problem-solving. Configurable reasoning effort allows users to balance response speed and computational resources against the complexity of individual tasks. Thinking Machines Lab reports benchmark scores of 25.4% on FrontierCode 2.0, 72.1% on DeepSWE 1.1, and 86.3% on SWE-Bench Pro v2 Hard. Inkling 2 Small is available for inference and fine-tuning through Tinker, with model weights scheduled for release under the Apache 2.0 license after additional safety evaluations.
Description
Kimi K3 is a large-scale AI model from Moonshot AI designed for advanced reasoning, software engineering, visual understanding, agentic workflows, and knowledge work. The model is built with 2.8 trillion parameters and uses Kimi Delta Attention, a hybrid linear attention design created to support long-context intelligence. It also includes Attention Residuals and a native 1 million token context window, giving developers room to work with large files, repositories, documentation sets, transcripts, and enterprise knowledge bases. Kimi K3 always runs with thinking mode enabled and currently supports maximum reasoning effort by default. Developers can access the model through Moonshot’s OpenAI-compatible API using Python, cURL, and the OpenAI SDK. The API supports standard chat completions, streaming output, structured JSON Schema responses, partial continuation from a prefix, custom tool calling, required tool choice, and dynamic tool loading. Kimi K3 also supports vision inputs, including local images encoded as base64 and video files uploaded through the file API. Automatic context caching helps repeated long-prefix workflows become more efficient without requiring manual cache IDs or extra cache parameters. By combining long context, visual understanding, tool use, structured output, and advanced reasoning, Kimi K3 is built for developers creating sophisticated AI agents, coding systems, research tools, and enterprise applications.
API Access
Has API
Yes
API Access
Has API
Yes
Integrations
C
No
C++
No
Claude Code
No
Claw Code
No
ClinePass
No
Command Code
No
Cosmos
No
Hermes Agent
No
Kimi Code
No
Kimi Work
No
Integrations
C
Yes
C++
Yes
Claude Code
Yes
Claw Code
Yes
ClinePass
Yes
Command Code
Yes
Cosmos
Yes
Hermes Agent
Yes
Kimi Code
Yes
Kimi Work
Yes
Pricing Details
$0.30 per million input tokens
$0.30 per million input tokens, $0.03 per million cached input tokens, and $1.00 per million output tokens
Free Trial
No
Free Version
No
Pricing Details
$3 per 1M tokens (input)
Kimi K3 is priced per 1 million tokens:
Cached input: $0.30
Uncached input: $3.00
Output: $15.00
Context window: 1,048,576 tokens
Cached inputs cost 90% less than uncached inputs, while generated output is the most expensive token category. Prices exclude applicable taxes, which are calculated based on the customer’s jurisdiction.
Cached input: $0.30
Uncached input: $3.00
Output: $15.00
Context window: 1,048,576 tokens
Cached inputs cost 90% less than uncached inputs, while generated output is the most expensive token category. Prices exclude applicable taxes, which are calculated based on the customer’s jurisdiction.
Free Trial
No
Free Version
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Deployment
Web-Based
Yes
On-Premises
No
iPhone App
No
iPad App
No
Android App
No
Windows
No
Mac
No
Linux
No
Chromebook
No
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Customer Support
Business Hours
No
Live Rep (24/7)
No
Online Support
Yes
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Types of Training
Training Docs
Yes
Webinars
No
Live Training (Online)
No
In Person
No
Vendor Details
Company Name
Thinking Machines Lab
Founded
2025
Country
United States
Website
thinkingmachines.ai/
Vendor Details
Company Name
Moonshot AI
Founded
2023
Country
China
Website
kimi.ai