Kimi API
Moonshot AI's API for its Kimi models, open-weight coding and agent models with long context, compatible with the OpenAI and Anthropic API formats.
2 open-source projects declare Kimi API in their code; no maker's live product we track uses it yet.
Profile checked
- Oct 2026 Now covered: Kimi API, for llm api.
How makers use Kimi API
What Kimi API is used for
Kimi API vs the alternatives makers chose
| Option | Makers' products | 2026 launches | Free for | At 10,000 users | Open source | |
|---|---|---|---|---|---|---|
| 736 80% | 77% | ~1,000 users | $10/mo · GPT-6 Luna | No | ||
| 252 27% | 21% | ~1,000 users | $10/mo · Claude Haiku 5.5 | No | ||
| 99 11% | 12% | ~360 users | $28/mo · Gemini 3.1 Flash-Lite | No | ||
| 39 4% | 3% | ~1,500 users | $6.75/mo · GPT OSS 20B | No | ||
| 22 2% | 0% | — | — | No | ||
| 15 2% | 1% | ~1,700 users | $6.00/mo · Ministral 3 (3B) | No | ||
| Kimi API | 0 0% | 0% | ~110 users | — | No |
For LLM API: how many of the 923 makers' products we know the LLM API of chose each option, and the share among the 256 launched in 2026, since a tool that came first has products from every year, and what each costs at 10,000 users.
Costs are the cheapest plan that fits, from each vendor's pricing page, at the usage our stack planner assumes for a product with that many users. Free for: the users its cheapest plan a business can use stays free for.
When to use Kimi API, and when not
Something else fits better if
- You want the strongest general models and the widest ecosystem of examples and integrations: OpenAI API or Claude or Gemini API.
- Token cost dominates your budget, for example high-volume batch or agent workloads: DeepSeek or Groq or Mistral AI.
- You want to try or mix many models with one key and one bill, and fall back when a provider is down: OpenRouter.
- You want that routing and spend control but self-hosted, with keys and logs on your servers: LiteLLM.
The Kimi API is Moonshot AI's developer platform for its Kimi models: the flagship Kimi K3, with a 1M-token context window and image input, and the K2.6 and K2.7 Code models with 256K tokens. All of them support thinking mode and tool calls. The international platform is at platform.kimi.ai (platform.moonshot.ai redirects there); a separate mainland China platform bills in yuan.
More about Kimi API
There's no Kimi-specific SDK to learn. The API speaks the OpenAI Chat Completions format at https://api.moonshot.ai/v1, the Anthropic Messages format at https://api.moonshot.ai/anthropic, and a Responses API, so you use the official OpenAI or Anthropic SDKs, or agent tools such as Claude Code, by swapping the base URL and key. Usage is deducted from a prepaid balance.
Useful for a small team: context caching is automatic, and on K3 you can pick a 5-minute or 1-hour cache lifetime, with cache writes billed separately and hits at a tenth of the input price; Kimi K3's full weights are released, so the same model can be hosted elsewhere; and enterprise customers can ask for zero data retention.
Limits: you need to top up at least $1 to start, and rate limits rise with how much you've topped up in total, starting at 3 requests per minute. Moonshot AI Pte. Ltd. runs the international platform from Singapore under Singapore law, and its terms let it use your content to improve its services unless you agree otherwise in writing.
What Hacker News says about Kimi API
On Hacker News, 5% of comments about Kimi API recommend it and 5% criticize it: net praise 0%.
By year
| Year | Comments choosing it, per month | Net praise |
|---|---|---|
| 2023 | 0.0 | 0% |
| 2024 | 0.1 | 0% |
| 2025 | 0.3 | 0% |
| 2026 (8 mo) | 0.3 | 0% |
In their words
- “they seem to have gotten slower and worse at their jobs” HN, Jul 2026
Hacker News comments January 2023 to August 2026 that name Kimi API in a sentence like "I use" or "we moved to", Claude read a sample of 79 and the counts scale it to all of them; net praise is comments recommending it minus comments criticizing it, as a share of all comments about it. How it's counted, and how HN compares with makers.
Who uses it
No maker's live product on record yet, and 2 open-source projects that declare it in their code.
We haven't found a maker's live product that uses Kimi API yet — only the open-source projects below, which declare it in their code.
None of these in makers' own words.
Open source: a project that declares Kimi API as a dependency in its public code — verifiable, but not necessarily a live product.
Alternatives to Kimi API
All alternatives by situation →Further reading
Questions makers ask about Kimi API
What are the alternatives to Kimi API?
For LLM API, the other options makers' products we track chose most are OpenAI API (736), Claude (252), Gemini API (99), Groq (39), Azure OpenAI (22), Mistral AI (15). Each alternative, with the situation it fits, is on the Kimi API alternatives page.
Where is my data processed?
The international platform is run by Moonshot AI Pte. Ltd., and its privacy policy says the information it collects is stored on servers in Singapore. source ↗
Does Moonshot use my API inputs and outputs for training?
It may. The platform terms let Moonshot use customer content to develop and improve its services unless a separate written agreement says otherwise; customers who need that restriction are told to contact Moonshot about enterprise terms. source ↗
Is zero data retention available?
Yes, for enterprise customers on request. With it on, prompts and responses are deleted once the response is returned, though files uploaded directly, such as images and video, aren't guaranteed to be covered. source ↗
Can I use the OpenAI or Anthropic SDK?
Yes. Use https://api.moonshot.ai/v1 as the base URL for the OpenAI SDK, or https://api.moonshot.ai/anthropic for the Anthropic SDK and Claude Code, with a Kimi API key. source ↗
Is there a free tier, and what are the rate limits?
No free tier. You top up at least $1 to start and get a $5 voucher once your top-ups reach $5. Limits rise with total top-ups, from 1 concurrent request and 3 RPM at $1 to 15 concurrent and 100 RPM at $10, and so on. source ↗
Can I run the models myself?
Moonshot says the full Kimi K3 weights have been released, so you can serve it yourself or through another host, though it's a very large model at 2.8 trillion parameters. source ↗
Is Kimi API free?
No permanent free tier; paid use starts at Pay per token. source ↗
Is Kimi API open source or self-hostable?
Not open source, and hosted only.
Can AI coding agents work with Kimi API?
No llms.txt, official MCP server or CLI found yet.
Who uses Kimi API?
No maker's live product we track yet; 2 open-source projects declare it in their code. source ↗