⏱️ Lectura: 11 min
Moonshot AI completely redesigned kimi.com and now splits its assistant into three separate products: Kimi Work, Kimi Code, and Kimi Claw, all running on top of the Kimi K3 model. The interface change replaces the previous single chat with an offering segmented by task.
📑 En este artículo
The Chinese company, the same one behind the Kimi K2 and K2.6 models that already held a prominent place among open models in coding references, is now betting that users will pick a product rather than a model: writing a report, generating code, or letting an agent run scheduled tasks without constant supervision.
TL;DR
- Moonshot AI relaunched kimi.com organized into three products: Kimi Work, Kimi Code, and Kimi Claw, all on the Kimi K3 model.
- The platform adds Scheduled Tasks and a plugin system visible in the main menu.
- Kimi Code targets agentic coding: generating, running, and fixing code within a single agent flow.
- Kimi Claw focuses on autonomous web tasks that run without constant supervision thanks to scheduled tasks.
- Kimi Work offers the general knowledge assistant for writing, summarizing, and analyzing documents.
- As of this writing, Moonshot AI has not published a technical spec sheet with Kimi K3’s parameter count.
- Kimi’s API remains compatible with the OpenAI format, which lets you reuse existing SDKs.
- The direct predecessors, Kimi K2 and K2.6, already ranked among the standout open models in coding benchmarks.
What Happened
The kimi.com site now presents, as soon as it opens, three named shortcuts: Kimi Work, Kimi Code, and Kimi Claw. Alongside them, the main menu shows the Plugins and Scheduled Tasks sections, two features that previously had no visible place in the Kimi interface.
Kimi Work concentrates the assistant’s general use: writing text, summarizing documents, and answering knowledge questions, Kimi’s original function since its earliest versions. Kimi Code positions itself as the product built for agentic coding, in the same category as Anthropic’s Claude Code, GitHub’s Copilot Workspace, or Cursor. Kimi Claw completes the trio with a focus on web automation: tasks an agent runs on its own, on a recurring basis, thanks to the scheduled tasks system.
Moonshot AI did not pair the relaunch with an extensive technical announcement or a benchmark sheet for K3. The information available at the time of this article comes from the site’s own public interface, without a paper or technical report equivalent to the one the company published for K2.
Context and History
Moonshot AI is the Chinese startup behind the Kimi model family, known for releasing open weights under an MIT-derived license. Kimi K2, launched in 2025, uses a mixture-of-experts (MoE) architecture with a total parameter count far higher than what activates on each inference, a design that reduces compute cost per token without sacrificing the model’s overall capacity. Moonshot documented that architecture and the use of the Muon optimizer in the repositories it maintains on GitHub.
The K2.6 update deepened that agentic bet: even then the model stood out in open source coding references, something this channel covered at the time. Kimi K3 arrives as the next step in that line, but with a product strategy shift rather than a simple version bump: instead of offering a generic chat, Moonshot packages the model into three specialized surfaces.
That move follows a trend other labs already set: separating the conversational assistant from the code agent, and in turn separating the code agent from the agent that browses and acts on the web without direct supervision. Kimi Work, Kimi Code, and Kimi Claw mirror that split into three named products.
Technical Details and Performance
As of this writing, Moonshot AI has not published a technical spec sheet for Kimi K3 with a parameter count, context size, or benchmark results. What can be described with certainty is the technical lineage it builds on: Kimi K2 uses an MoE architecture with a small fraction of active parameters per token, trained with the Muon optimizer, and exposes its API under a format compatible with OpenAI’s.
That API compatibility is the most relevant piece for anyone who wants to integrate Kimi K3 today: any code written against the OpenAI SDK works against the Moonshot endpoint by changing just the base URL and the API key. It is the same pattern other providers already use to lower adoption friction.
⚠️ Heads up: Moonshot AI has not published a technical spec sheet with the parameter count or official benchmarks for Kimi K3 at the time of this article; the architecture data described above corresponds to K2 and K2.6, its confirmed predecessors.
The following table summarizes what each product in the new family solves:
| Product | What it does | Advantage | Limitation |
|---|---|---|---|
| Kimi Work | Write, summarize, and analyze general knowledge documents | Simple interface, built for non-programmers | Less fine-grained control over tools and code execution |
| Kimi Code | Agentic coding: generate, run, and debug code | Integrates tool calling built for development flows | Requires the user to define the available tools well |
| Kimi Claw | Automate web tasks and scheduled tasks | Can operate without constant supervision thanks to Scheduled Tasks | Higher risk of unwanted actions if the agent browses without clear limits |
Kimi Code is the one that comes closest to the agentic coding category the platform’s own slogan promises: an agent that not only suggests code but runs it, runs tests, and fixes the result within the same flow, using tool calling in OpenAI’s standard function calling format. Kimi Claw, by contrast, targets tasks that go beyond code: monitoring something, generating a periodic report, all scheduled with Scheduled Tasks to run without the user triggering each execution by hand.
How to Try Kimi K3
To experiment with Kimi K3 today you don’t need to wait for an official API announcement: Moonshot exposes its models under an OpenAI-compatible endpoint, which lets you reuse the official Python SDK or any HTTP client.
The first step is to set the API key as an environment variable. The syntax varies by operating system:
- macOS and Linux (bash/zsh):
export MOONSHOT_API_KEY="sk-tu-clave" - Windows (PowerShell):
$env:MOONSHOT_API_KEY = "sk-tu-clave" - Windows (cmd):
set MOONSHOT_API_KEY=sk-tu-clave
With the key configured, a minimal curl call is enough to confirm the endpoint responds:
curl https://api.moonshot.ai/v1/chat/completions \
-H "Authorization: Bearer $MOONSHOT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "kimi-k3",
"messages": [{"role": "user", "content": "Hola Kimi, presentate en una linea"}]
}'This example assumes Moonshot exposes K3 under an identifier like kimi-k3; confirm the exact model name in your account before integrating it into production. For a more realistic agentic coding case, the OpenAI Python SDK pointed at the Moonshot endpoint lets you define tools the model can invoke, such as running a test suite:
from openai import OpenAI
client = OpenAI(
api_key="TU_API_KEY_DE_MOONSHOT",
base_url="https://api.moonshot.ai/v1",
)
respuesta = client.chat.completions.create(
model="kimi-k3",
messages=[
{"role": "system", "content": "Sos un agente de Kimi Code que corrige bugs en Python."},
{"role": "user", "content": "Este script falla con ZeroDivisionError, arreglalo: def dividir(a, b): return a / b"},
],
tools=[{
"type": "function",
"function": {
"name": "ejecutar_tests",
"description": "Corre la suite de tests del repo y devuelve el resultado",
"parameters": {"type": "object", "properties": {}, "required": []},
},
}],
)
print(respuesta.choices[0].message)This pattern, a system message that defines the agent’s role plus a list of tools, is the same one Kimi Code and other coding agents use to decide when to run an action instead of just returning text. To confirm the account has access to the K3 model and not an earlier version, it’s a good idea to list the available models before integrating it into production:
curl https://api.moonshot.ai/v1/models -H "Authorization: Bearer $MOONSHOT_API_KEY"and check that the K3 identifier appears in the response.
💡 Tip: Before pointing your OpenAI SDK at the Moonshot endpoint, run the call to /v1/models to confirm the exact identifier of the K3 model available in your account; model names often change between announcements and actual API availability.
Impact and Analysis
Moonshot AI’s bet comes at a time when the code agent category already has established players: Anthropic’s Claude Code, GitHub’s Copilot Workspace, Cursor, and Windsurf compete for the same type of user, a developer who wants to delegate not just code suggestions but the full execution of a task.
Separating Kimi Work from Kimi Code and Kimi Claw simplifies the product message: each surface promises one concrete thing instead of a generic assistant that does everything. The trade-off is that a user who wants to combine the three functions in a single flow (writing a report that also runs code and schedules automatic follow-up) has to move between three different products instead of just one.
Another real limitation: without a public technical spec sheet for K3, a team evaluating the platform for production has no way to objectively compare cost per token, context size, or performance against K2.6 or against models from other providers. Migrating an agent flow to Kimi Claw, in particular, requires trusting a model that browses and acts on the web when the company has not yet published what safety limits apply to those actions.
The following diagram summarizes what a Kimi Claw scheduled task looks like in practice:
sequenceDiagram
participant U as Usuario
participant K as Kimi Claw
participant W as Sitio web objetivo
participant N as Notificacion
U->>K: programa tarea recurrente
K->>W: navega y ejecuta la accion
W-->>K: devuelve resultado
K-->>N: envia resumen al usuario
Note over U,K: la tarea se repite segun el horario definidoWhat’s Next
Open questions remain that only Moonshot AI can answer with a formal announcement: whether K3 keeps K2’s MoE architecture, whether the parameter count changed, and whether the model will remain available with open weights like its predecessors. There is also, for now, no public pricing table for Kimi Work, Kimi Code, or Kimi Claw as separate products.
What is predictable from the pattern K2 and K2.6 followed: if Moonshot keeps its open weights strategy, it’s reasonable to expect that at some point it will publish a repository and a technical report for Kimi K3 in its GitHub organization, as it did with the earlier versions.
📖 Summary on Telegram: View summary
Try it yourself: head to kimi.com, open Kimi Code, and ask it to fix a real bug in your repo to see the tool calling flow in action today.
Frequently Asked Questions
What is Kimi K3?
It’s the model behind Moonshot AI’s new generation of products, the common base for Kimi Work, Kimi Code, and Kimi Claw introduced in the kimi.com redesign.
What’s the difference between Kimi Work, Kimi Code, and Kimi Claw?
Kimi Work targets general knowledge tasks like writing and summarizing, Kimi Code targets agentic coding with code execution, and Kimi Claw targets web automation with scheduled tasks.
Is the Kimi K3 API compatible with the OpenAI SDK?
Yes. Moonshot exposes its models under an API format compatible with OpenAI’s, which lets you reuse the official SDK by changing the base URL and the API key.
How many parameters does Kimi K3 have?
Moonshot AI has not published that figure at the time of this article. Its predecessor, Kimi K2, uses a mixture-of-experts architecture with a fraction of active parameters per token, documented in the company’s repository on GitHub.
Is Kimi K3 an open weights model?
It’s not confirmed yet. K2 and K2.6 were released with open weights under an MIT-derived license; Moonshot did not clarify whether it will keep that policy with K3.
What are Kimi Claw’s Scheduled Tasks?
It’s the system that lets you schedule a task so the agent repeats it at a set time, without the user having to trigger each execution manually.
References
- Kimi AI: official page introducing the K3 platform with Kimi Work, Kimi Code, and Kimi Claw.
- Moonshot AI on GitHub: repositories where the company published the open weights of the Kimi K2 family.
- Moonshot AI Platform: documentation of the OpenAI-compatible API used to integrate the Kimi models.
- Wikipedia: Moonshot AI: general context about the company and its Kimi model line.
📱 Enjoy this content? Follow @programacion on Telegram for daily tech content in Spanish: quick summaries, fresh content every day.
Imagen destacada: Foto de Caspar Camille Rubin en Unsplash
0 Comments