MODEL DIRECTORY
Moonshot AI Model Directory
Moonshot AI develops the Kimi model family for long context, reasoning, coding, vision, and tool use.
Website · CNPublic models
12
With relay prices
12
Relay sites
77
Reasoning
9
Tool call
12
Structured output
0
Multimodal input
7
Text models
12
Image models
0
Video models
0
Audio models
0
Release range
2025-07-11 ~ 2026-10-23
12 models foundPrices in USD per 1M tokens; relay prices and ≈ are converted from CNY at today's rate
| Model | Provider | Type | Relays | Context | Max output | Input | Output | Capabilities | Price (input / output) | Details | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
Kimi K3.1 Prokimi-k3.1-pro | Moonshot AI | Text | 29 sites | 1.05M | 131.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | 55.1 | Official$2 / $10Lowest$0.018 / $0.0898 | 2026-10-23 | |
Multimodal Kimi model with 1M context and always-on reasoning for coding, 3D creation, financial research, and agentic work Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Kimi K2.8 Previewkimi-k2.8-preview | Moonshot AI | Text | 6 sites | 1.05M | - | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supported | - | OfficialNo priceLowest$0.0293 / $0.1131 | 2026-09-11 | |
Kimi K2.8 Preview is a Kimi Code programming model. The API id is kimi-for-coding. It is available on Andante / Plus and above, with up to a 1M context window and thinking levels low, high, and max (verified 2026-10-20). Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Kimi K3kimi-k3 | Moonshot AI | Text | 72 sites | 1.05M | 131.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | 43.6 | Official≈$2.99 / $14.96Lowest$0.081 / $0.4049 | 2026-07-17 | |
Kimi K3 is Moonshot AI's most capable flagship, with 2.8 trillion parameters, Kimi Delta Attention, Attention Residuals, sparse MoE, native vision, and a 1M-token context window. It targets long-horizon coding, knowledge work, and reasoning, with tool calling, structured output, and automatic context caching. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Kimi K2.7 Codekimi-k2.7-code | Moonshot AI | Text | 33 sites | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | 25.8 | Official$0.95 / $4Lowest$0.0384 / $0.1746 | 2026-06-12 | |
Coding-focused Kimi model, stronger on long-horizon repo work with less overthinking Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Kimi K2.7 Code Highspeedkimi-k2.7-code-highspeed | Moonshot AI | Text | 5 sites | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | - | Official$1.9 / $8Lowest$0.3665 / $1.52 | 2026-06-12 | |
Kimi K2.7 Code HighSpeed is the low-latency Kimi Code variant. The API id is kimi-for-coding-highspeed. It is available on Allegretto / Pro and above, for interactive editing and coding-agent loops (verified 2026-10-20). Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
| ||||||||||||
Kimi 2.6kimi-k2.6 | Moonshot AI | Text | 36 sites | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 27.0 | Official≈$0.9723 / $4.04Lowest$0.003 / $0.003 | 2026-04 | |
Kimi 2.6 targets long-context work, code understanding, complex reasoning, and agent workflows. It is suitable for cross-file analysis, knowledge-intensive Q&A, tool use, and high-quality Chinese-language tasks. Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Kimi K2.5kimi-k2.5 | Moonshot AI | Text | 17 sites | 262.1K | 262.1K | Text: SupportedImage: SupportedVideo: SupportedFile: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: Not supportedOpen weights: Supported | 23.5 | OfficialNo priceLowest$0.0227/ 次 | 2026-01 | |
Earlier Kimi frontier model for long-context agents, coding, and multimodal work Basics
Limits
InputText: SupportedImage: SupportedAudio: Not supportedVideo: SupportedPDF: Not supportedFile: Supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported Pricing
/ 次 | ||||||||||||
Kimi K2 Thinkingkimi-k2-thinking | Moonshot AI | Text | 3 sites | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 22.0 | OfficialNo priceLowest$0.3411 / $1.36 | 2025-11-06 | |
Thinking Kimi model for slower research passes, planning, and hard technical questions Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Kimi K2 Thinking Turbokimi-k2-thinking-turbo | Moonshot AI | Text | 2 sites | 262.1K | 262.1K | Text: Supported | Text: Supported | Reason: SupportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowest$0.718 / $5.21 | 2025-11-06 | |
Kimi reasoning model for long-horizon research, planning, and tool use Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Kimi K2 Instruct 0905kimi-k2-0905 | Moonshot AI | Text | 2 sites | 262.1K | 98.3K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 15.3 | OfficialNo priceLowest$0.359 / $1.44 | 2025-09-05 | |
September 2025 Kimi K2 instruction update with a 256K context and improved agentic coding Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Kimi K2 0711kimi-k2 | Moonshot AI | Text | 5 sites | 131.1K | 98.3K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | 12.7 | OfficialNo priceLowest$0.3351 / $1.34 | 2025-07-11 | |
Kimi model for long-context chat, coding, and agentic reasoning Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Kimi K2 Instructkimi-k2-instruct | Moonshot AI | Text | 2 sites | 131.1K | 32.8K | Text: Supported | Text: Supported | Reason: Not supportedTools: SupportedJSON: UnknownTemperature: SupportedOpen weights: Supported | - | OfficialNo priceLowest$0.4368 / $1.74 | 2025-07-11 | |
Non-thinking Kimi K2 MoE instruction model for coding and tool-using agents Basics
Limits
InputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supportedPDF: Not supportedFile: Not supported OutputText: SupportedImage: Not supportedAudio: Not supportedVideo: Not supported API capabilitiesReasoning: Not supportedTool call: SupportedStructured output: UnknownTemperature: Supported Pricing
| ||||||||||||
Capabilities and limits come from public sources. “Unknown” means no reliable data yet, not “not supported”. Relay counts include only sites with a current public price, de-duplicated per site.
Data source: models.dev · OpenRouter
Intelligence scores come from the OpenRouter benchmark rankings (Intelligence Index); higher is smarter.