Moonshot AI has released a new Kimi model every few months, from Kimi K2 in July 2025 to the flagship Kimi K3.1 Pro in October 2026. This guide lists every current version, explains how they differ in size, context, speed and price, and helps you choose the right one.
Six Kimi models are in use today. Two are flagships built on the same 2.8T K3.1 Pro model, one is the previous flagship, one powers Kimi Code, and two are low-cost open models from the K2 line.
The main specifications of every current Kimi model. API prices are in US dollars per million tokens. Scroll sideways on a phone.
| Feature | K3.1 Pro | K3.1 Pro HighSpeed | Kimi K3 | K2.8 Preview | K2.7 Code | Kimi K2.6 |
|---|---|---|---|---|---|---|
| Released | Oct 2026 | Oct 2026 | 16 Jul 2026 | 11 Sep 2026 | 12 Jun 2026 | 20 Apr 2026 |
| Best for | Hardest work | Speed | Legacy K3 apps | Kimi Code | Cheap coding | Cheap all-round |
| Total parameters | 2.8T | 2.8T | 2.8T | Not published | 1T | 1T |
| Active per token | 104B | 104B | 16 of 896 experts | Not published | 32B | 32B |
| Context window | 1M | 1M | 1M | 1M | 256K | 256K |
| Inputs | Text, image, video | Text, image, video | Text, image, video | Text, image | Text, code, image | Text, image |
| Thinking | Low / High / Max | Low / High / Max | Low / High / Max | Low / High / Max | Always on | Thinking or instant |
| API input / output | $2 / $10 | $4 / $20 | $3 / $15 | — | $0.95 / $4 | $0.95 / $4 |
| Cached input | $0.20 | — | $0.30 | — | $0.19 | $0.16 |
| Open weights | Yes | Same weights | Yes | No | Yes | Yes |
Sources: Moonshot AI launch posts, the Kimi API pricing pages and Kimi Code release notes. Moonshot has not published K2.8 Preview's size or a public API price for it.
The models differ in six ways that matter when you choose one.
The K3 models have 2.8 trillion parameters, almost three times the 1 trillion of the K2 line. Bigger models usually reason better but cost more to run and host.
K3.1 Pro, K3 and K2.8 Preview read about 1 million tokens at once. K2.6 and K2.7 Code read 256K, which is still enough for long documents and mid-size codebases.
The K3 models and K2.8 Preview let you choose Low, High or Max thinking. K2.7 Code always thinks, and K2.6 can answer instantly or think first.
All current models read images. The K3 models also understand video, which helps with screen recordings and visual bugs.
API prices range from $0.95 / $4 for K2.6 and K2.7 Code to $3 / $15 for K3. K3.1 Pro sits in between at $2 / $10, and cached input costs about a tenth.
Almost every Kimi model ships open weights you can download and self-host. K2.8 Preview is the exception, available only in Kimi Code and Kimi Work.
The newest models can read about four times more text at once, but the older K2 models cost much less per token. Pick based on what your task actually needs.
Context window and API output price for the five current models with published figures.
Tap the job that sounds most like yours to see the model we'd start with.
The 1M-token context holds whole stacks of reports, and it made the fewest false statements in Moonshot's finance tests. Set thinking to Max for the hardest questions.
Read the guide →Using the Kimi app? You don't pick a version there. Choose a mode, and Kimi uses its newest models.
A quick map from common jobs to the best Kimi model for each.
From the original Kimi K2 in July 2025 to the flagship Kimi K3.1 Pro in October 2026.
| Product | Model | How to choose |
|---|---|---|
| Kimi app and kimi.com | Newest models, with K3.1 Pro for the hardest work | Pick a mode (chat, thinking, agent, Agent Swarm). Kimi picks the model. |
| Kimi Code | K2.8 Preview by default (kimi-for-coding) | Switch to a K3 model for harder jobs. HighSpeed uses more quota. |
| Kimi Work | K2.8 Preview and the K3 models | Set in the app for each task. |
| Kimi API | K3.1 Pro, K3, K2.7 Code, K2.6 | Set the model field in your request. |
| Open weights | K3.1 Pro, K3, K2.7 Code, K2.6, K2.5, K2 | Download from Hugging Face and run with vLLM or SGLang. |
In Kimi Code, turning thinking off sends K3-series and K2.8 Preview requests to a non-thinking K2.8 Preview variant. See Kimi Code and plans and credits.
Use these IDs in the model field. The API is OpenAI-compatible at https://api.moonshot.ai/v1, and GET /v1/models lists what your account can use.
| Model | Model ID | Where | Copy |
|---|---|---|---|
| Kimi K3.1 Pro | kimi-k3.1-pro | Kimi API | |
| Kimi K3 | kimi-k3 | Kimi API | |
| K2.7 Code | kimi-k2.7-code | Kimi API | |
| K2.7 Code HighSpeed | kimi-k2.7-code-highspeed | Kimi API | |
| Kimi K2.6 | kimi-k2.6 | Kimi API | |
| K2.8 Preview | kimi-for-coding | Kimi Code only |
Moonshot has not published a separate API ID for K3.1 Pro HighSpeed. Check the model list on platform.kimi.ai. Full setup: Kimi API guide.
K3.1 Pro is free for commercial use, with extra terms for resellers earning over $20M a year and for very large products.
The Modified MIT License allows commercial use. Very large products must show the Kimi name.
Besides the main chat models, Moonshot has released models and agents for specific jobs.
An autonomous agent that searches, reads and writes cited research reports.
Read more →An open coding model trained to fix real software bugs.
Read more →An open audio model for speech recognition, audio understanding and voice.
Read more →The latest release of Kimi Work, Moonshot's desktop agent for knowledge work.
Read more →| Model | Status | Move to |
|---|---|---|
| Kimi K2.5 | Closed to new API users after K3, platform sunset 31 Aug 2026. Weights still on Hugging Face. | K2.6 or K3.1 Pro |
| Kimi K2 Thinking / Turbo | Deprecated on the API. | K2.6 or K2.7 Code |
| Kimi K2 (0711, 0905) | Superseded. Weights still on Hugging Face. | K2.6 |
| Kimi k1.5 | Replaced by the K2 line. | Any current model |
model value to a current ID from the table above, and check whether the new model always thinks, since that changes token use.