I Tried Kimi Agent and Here’s What I Found

Moonshot AI's Kimi Agent is a family of products built on the Kimi K3 model, a 2.8-trillion-parameter mixture-of-experts model with a 1-million-token context window, and includes Agent Swarm, which can coordinate up to 300 simultaneous sub-agents and more than 4,000 tool calls per task, claiming a 4.5x speed advantage over sequential processing. The free tier limits users to one concurrent agent task, with full agentic features starting at $39 per month, and Moonshot has documented two failure modes for the architecture: serial collapse and fake parallelism.

I Tried Kimi Agent and Here’s What I Found Kimi Agent is a name that's come to cover a sprawling family, and untangling it matters before judging any piece of it. " Kimi Agent " isn't one product; it's a name that's come to cover a sprawling family, and untangling it matters before judging any piece of it. Kimi K3 is the underlying model: a 2.8-trillion-parameter mixture-of-experts MoE model 16 of 896 experts active per token with a 1-million-token context window, developed by Moonshot AI, a Beijing-based lab backed by Alibaba https://amplifilabs.com/post/kimi-k3-the-complete-guide-to-moonshot-ais-2-8t-model . Agent Swarm is the architecture built on top of it — a system that can spin up dozens or hundreds of coordinated sub-agents on a single task rather than working through it sequentially. Goal https://x.com/Kimi Moonshot/status/2067574786965061677?lang=en is the feature for autonomous multi-step objectives: set a plain-language target and the agent plans and executes toward it. OK Computer is the agent mode built directly into Kimi's chat interface, generating multi-page sites and slide decks from a single prompt. , launched June 10, 2026, is a separate desktop app for macOS Apple Silicon and Windows that acts directly on your computer through a browser-control extension called WebBridge, searching, scrolling, and filling out forms the way a person would. Kimi Work https://www.kimi.com/products/kimi-work is the cloud counterpart that keeps tasks running when your machine goes to sleep, since Kimi Work's local tasks otherwise stop the moment the laptop lid closes. Kimi Claw https://www.kimi.com/bot is the dedicated coding command-line interface CLI . Kimi Code https://www.kimi.com/code The Architecture Claim: Agent Swarm Agent Swarm is the headline feature, and Moonshot's own description of it is genuinely more specific than most vendor marketing. It first shipped January 27, 2026 alongside Kimi K2.5, described as a scale-out architecture that coordinates sub-agent collaboration without predefined roles or manually designed workflows. The April 20, 2026 release of K2.6 gave it a real capacity jump: up to 300 simultaneous sub-agent instances and more than 4,000 tool calls in a single task https://www.digitalapplied.com/blog/kimi-k3-swarm-which-work-parallelizes-decision-framework-2026 , with Moonshot claiming a 4.5x speed advantage over a single agent working the same task sequentially. Agent Swarm now runs on K3 as well, with Moonshot describing further improvements to large-scale parallel search without publishing new capacity numbers beyond the K2.6 figures. What's unusually candid here — and worth crediting directly — is that Moonshot documents its own two failure modes for this architecture rather than only the wins: serial collapse, where the orchestrator fans work out but the sub-agents end up blocking on each other anyway, and fake parallelism, where work looks distributed but isn't actually independent enough to benefit from it. That's a genuinely useful decision framework for anyone deciding whether to fan a task out at all, not just a Kimi-specific caveat, and it's rare for a vendor to publish its own failure taxonomy alongside the capability numbers. Getting Started and Trying It Here's what I could verify directly, without a paid plan. Signing up at kimi.com takes a Google account and about ten seconds, no credit card required to start. The free tier gets you real functionality, but it's genuinely limited: according to a hands-on review from TechRadar Pro https://www.techradar.com/pro/kimi-ai-review , the free tier caps you to one concurrent agent task at a time, and the full agentic feature set — meaning real use of Agent Swarm at scale — only unlocks at $39 a month and above. That's a meaningful gate if the swarm architecture is specifically what drew you in, since a single concurrent task rather defeats the point of parallel sub-agents. Hands-On With the API Moonshot's Kimi API is OpenAI-compatible, which means the standard openai Python SDK works against it with only the base URL and model name changed. Prerequisites : - Python 3.9+ - Moonshot API key from platform.moonshot.ai https://platform.moonshot.ai/ , and pip install openai python export MOONSHOT API KEY=your-key-here run task.py import os import json from openai import OpenAI client = OpenAI api key=os.environ "MOONSHOT API KEY" , base url="https://api.moonshot.ai/v1", MODEL = "kimi-k3" TOOLS = { "type": "function", "function": { "name": "count words", "description": "Counts the number of words in a block of text.", "parameters": { "type": "object", "properties": {"text": {"type": "string"}}, "required": "text" , }, }, } def count words text: str - int: return len text.split def run task task: str, max turns: int = 6 - dict: """Runs a task through Kimi K3, executing any tool calls it makes, and returns a small report of what happened.""" messages = {"role": "user", "content": task} total prompt tokens = 0 total completion tokens = 0 turns used = 0 for turn in range max turns : turns used = turn + 1 response = client.chat.completions.create model=MODEL, max tokens=1024, tools=TOOLS, messages=messages, reasoning effort="max", K3 replaced the old thinking param with this usage = response.usage total prompt tokens += usage.prompt tokens total completion tokens += usage.completion tokens message = response.choices 0 .message if response.choices 0 .finish reason = "tool calls": return { "answer": message.content, "turns used": turns used, "prompt tokens": total prompt tokens, "completion tokens": total completion tokens, } messages.append message.model dump exclude none=True for tool call in message.tool calls: if tool call.function.name == "count words": args = json.loads tool call.function.arguments result = count words args "text" messages.append { "role": "tool", "tool call id": tool call.id, "content": str result , } return {"answer": None, "turns used": turns used, "error": "Hit max turns without finishing"} if name == " main ": task = "Write a two-sentence description of what a mixture-of-experts " "model is, then use the count words tool to tell me exactly how " "many words your description contains." report = run task task print json.dumps report, indent=2 What this does: because Moonshot's API follows the standard OpenAI chat-completions contract, tool calls arrive in the familiar message.tool calls shape rather than a custom format, and finish reason == "tool calls" is the signal to execute a tool and loop back rather than return. One K3-specific detail worth flagging directly: the older thinking parameter from the K2 line is gone in K3, replaced by reasoning effort , and as of this writing "max" is the only supported value https://therouter.ai/blog/kimi-k3-api-integration-guide/ , with more levels promised later. How to run it : with your key exported, run python run task.py On pricing, since it's central to Kimi's whole pitch: K3 runs $3 per million input tokens and $15 per million output tokens https://agentsapis.com/kimi-api/ , flat across the entire 1-million-token context with no tiered pricing by length. That's roughly a 5x jump over K2.6's pricing, notable because it's Moonshot moving away from the ultra-cheap positioning on which the Kimi line built its reputation. Automatic prefix caching, however, drops the cached-input rate to $0.30 per million tokens, which meaningfully changes the economics for long-context, multi-turn conversations specifically. What Independent Testers Actually Found On the positive side, TechRadar's https://www.techradar.com/pro/kimi-ai-review hands-on testing described genuinely strong results on document-heavy work: dropping two long PDFs into one conversation and asking Kimi to cross-reference specific sections came back accurate and well-organized, holding up through follow-up questions — describing long-context handling as one of Kimi's strongest suits, available even on the free tier. The same review tested Kimi Code on a Python refactoring task and found the output clean, with architectural reasoning that held up under questioning, if not quite matching Claude Code's structured explanations — a trade-off the reviewer judged worth it given the price difference. A Hacker News user's blunt assessment in the same discussion thread rated K2.6 as below Sonnet and Opus 4.0 on raw capability. And in a detail worth taking seriously precisely because it comes from the vendor itself rather than a critic, Moonshot's own K3 launch materials are candid that K3 trails Claude Fable 5 and GPT-5.6 Sol on their internal comparisons https://apidog.com/blog/kimi-k3-api/ , positioning it as strong and dramatically cheaper rather than a clean frontier win. Held together, that's a coherent picture rather than a contradiction: Kimi is genuinely capable on long-context document work and competent, cost-effective coding, and it falls short of Claude and GPT specifically on the hardest, most agent-coordination-heavy tasks — which happens to be exactly the category Agent Swarm is built to sell. The Rough Edges Worth Knowing About A few things worth knowing before adopting this for real work — none of them disqualifying on their own, all worth factoring in. On July 20, 2026, Moonshot paused new K3 subscriptions entirely after GPU capacity hit its limit https://explainx.ai/blog/kimi-k3-moonshot-beta-leaks-july-2026 following a demand surge — a real signal about scaling growing pains rather than a rumor. Moonshot's own documentation flags " excessive proactiveness " as an observed K3 behavior, where the model makes unprompted decisions when it hits ambiguity mid-task rather than pausing to ask — a direct consequence of training it heavily on long, difficult tasks. There's also a genuine harness-compatibility issue: Moonshot states K3 was trained to preserve reasoning history across a session, and output quality can degrade if an agent harness doesn't pass that history back correctly, or if a session started on a different model gets switched to K3 mid-conversation — which is why Moonshot recommends its own verified-compatible tooling and advises against a mid-session model swap. Finally, for regulated industries specifically, Kimi's hosted API routes through China-based servers — a real, practical consideration entirely separate from the model's capability. On licensing : the full K3 weights landed July 27, 2026 under a bespoke Kimi K3 License, open-weight in the sense that you can download and run them, but not an OSI-recognized open source license — worth knowing if "open" was doing specific legal work in your evaluation rather than just meaning "downloadable." Comparison Table | Kimi K3 / Agent Swarm | Claude Opus/Sonnet class | GPT-class agents | |---|---|---|---| Context window | 1,000,000 tokens | Varies by model, generally smaller than K3's 1M | Varies by model | Pricing per million tokens | $3 input / $15 output, cached input $0.30 | Higher list price than K3 | Higher list price than K3 | Parallel agent architecture | Native, up to 300 sub-agents, 4,000+ tool calls per task | Sub-agent orchestration available via Claude Code Teams, not the same fan-out scale by design | Handoff-based orchestration via Agents SDK | Independent hard-task benchmark result | 68/100 on an independent FlowGraph test, concentrated gap in multi-agent coordination | 91/100 on the same independent test | Not directly tested in that comparison | Vendor's own positioning | Moonshot states K3 trails Claude Fable 5 and GPT-5.6 Sol on their internal comparisons | N/A | N/A | Weight availability | Open-weight under a bespoke license not OSI open source | Closed | Closed | Data hosting | China-based servers | US-based | US-based | Wrapping Up The honest answer sits between the two extremes a launch post and a skeptical tweet would each give you. Kimi's pricing is genuinely disruptive, its long-context document handling is genuinely strong even on the free tier, and Agent Swarm is a real, more thoughtfully documented architecture than most competitors' equivalent features — including an unusually honest account of its own failure modes. Set against that: independent testing on the hardest agentic coordination tasks, the exact category Agent Swarm exists to win, shows a real, measured gap against Claude and GPT — one Moonshot's own launch materials don't fully dispute either. If your work is long-document analysis, cost-sensitive high-volume coding, or you specifically want an open-weight model with genuine agentic ambition, Kimi is worth a real trial. If your work depends on the hardest multi-agent coordination holding up flawlessly, the independent evidence so far says wait — or at minimum, run your own evaluation on your own workload before trusting the swarm at scale, rather than trusting either Moonshot's numbers or mine. is a software engineer and technical writer passionate about leveraging cutting-edge technologies to craft compelling narratives, with a keen eye for detail and a knack for simplifying complex concepts. You can also find Shittu on Shittu Olumide https://www.linkedin.com/in/olumide-shittu/