Moonshot AI's flagship multimodal model - 'Visual Agentic Intelligence'. 1T MoE / 32B activated, vision and language understanding, instant and thinking modes, conversational and agentic paradigms. January 2026.
Context window
256K
tokens
Parameters
1T total / 32B activated (MoE)
parameters
Max output
32,768
tokens
Release date
27 January 2026
Access:APIDownloadHostedDeployment:☁ Cloud💻 Local
Overview
Access & deployment
APIDownloadHosted
CloudLocal
Weights: Open weights
Key parameters
📏 Context: 256K
🧩 Parameters: 1T total / 32B activated (MoE)
✓ Tools · ✓ Fine-tuning
📥 Input: text, image, documents, structured data
Technical specification
Context window
256K
tokens
Parameters
1T total / 32B activated (MoE)
parameters
Max output tokens
32,768
tokens per response
Knowledge cutoff
1 Nov 2025
Knowledge boundary
License
Modified MIT License (open-source z ograniczeniami komercyjnymi dla dużych deploymentów - patrz repo Moonshot)
Hardware requirements
Open-weights model (moonshotai/Kimi-K2.5 on Hugging Face) - self-hosting on multi-GPU infrastructure (recommended 8+ H100/H200 with INT8 quantisation for 32B activated, ~100GB+ VRAM). Moonshot serves the model commercially via the platform.moonshot.ai API with a K2 Turbo option on faster hardware.
Features:✓ Tool use✓ Fine-tuning
Modalities
⬇ Input
textimagedocumentsstructured_data
⬆ Output
textcodestructured_data
Capabilities and applications
Native model capabilities
Advanced reasoning
The ability to perform multi-step, structured reasoning: analysing problems, planning steps, and drawing conclusions from hypotheses. Reasoning-first models (e.g. GPT-5.1 Thinking) dedicate a portion of inference to chains of thought before responding.
Category: reasoning
Extended thinking mode
A reasoning-model variant with a larger inference budget: more thinking cycles, higher answer precision at the cost of response time. Choice between 'standard' and 'extended' thinking is left to the user (e.g. the selector in GPT-5.2 Pro).
Category: reasoning
Adaptive reasoning effort
The model decides how much 'thinking' to allocate to a given query: simple questions are answered quickly, complex problems receive more inference cycles. A GPT-5.1 feature (both Instant and Thinking) that shortens time on easy tasks and extends it for hard ones.
Category: reasoning
Multi-step reasoning
Carrying out multi-step chains of reasoning across long, complex tasks.
Category: reasoning
Mathematical reasoning
The model's ability to solve mathematical tasks requiring multi-step reasoning — equations, proofs, combinatorics, geometry, calculus and competition-level problems.
Category: reasoning
Coding
Generating, analysing and modifying code in many programming languages. Covers writing functions, debugging, refactoring, code review, and creating tests. Measured by benchmarks such as HumanEval and SWE-bench.
Category: coding
Agentic coding
Multi-hour, multi-step programming tasks performed autonomously by the model: cloning a repository, running tests, iterating on fixes, integrating with CLI tools. Characteristic of Codex variants (GPT-5.1-Codex-Mini, Codex-Max).
Category: coding
Agentic capability
The model's ability to autonomously plan and execute multi-step tasks by sequentially using tools, maintaining context, and adapting to intermediate results.
Category: planning
Tool use
The model's ability to call external functions, APIs and tools during a conversation: calculator, search engine, code editor, database. The model decides when and how to use a tool and interprets its result.
Category: planning
Long context
Support for large context windows — tens to hundreds of thousands (or millions) of input tokens. Enables analysis of entire codebases, long documents, and many parallel conversations without losing earlier information. GPT-5.1 supports 400,000 tokens.
Category: language
Prompt caching
Cost-performance optimisation: repeated prompt fragments (e.g. system prompt, long documentation) are cached server-side and cheaper in subsequent calls. Significantly reduces cost for applications with long contexts.
Category: other
Multilingual
Competence in many natural languages (from a few to over a hundred): understanding, generation, translation, and code-switching within a single conversation. Frontier models support a wide range of languages with comparable quality.
Category: language
Pricing
Technical architecture
Core Architecture
Deployment and security
🔒 Security / Enterprise
✓ Verified enterprise information
The model is hosted on Moonshot AI's infrastructure in China - subject to Chinese AI regulations (Cyberspace Administration of China, politically sensitive content filters). Weights are publicly available (Modified MIT), so self-hosting in a private cloud or on-premise is possible for customers requiring data residency outside China. API is accessed via platform.moonshot.ai with API key authentication.