Kimi K3
by MoonshotAIReleased Jul 16, 2026
moonshotai/kimi-k3- Reads images
- Calls tools
- Answers in a JSON schema
- Reasons before it answers
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
- Input / 1M tokens
- $0.60
- Output / 1M tokens
- $18.00
- Context
- 1.05M
- Longest answer
- 944K
What it costs
What each call is charged to the token's AI credit.
| Billed for | You pay |
|---|---|
| Input tokens | $0.60 / 1M |
| Output tokens | $18.00 / 1M |
| Cached input, read | $0.52 / 1M |
A typical call
A short chat turn: 2,000 tokens in, 500 out.
- per call
- $0.01
- calls per $20
- 1,960
What it can do
From its listing. The router passes every field through.
- Reads imagesYes
- Reads files and PDFsNo
- Hears audioNo
- Calls toolsYes
- Answers in a JSON schemaYes
- Reasons before it answersYes
- Searches the webNo
- Caches long promptsYes
- Draws imagesNo
Call it
Any router key works, in the format your SDK already speaks.
import OpenAI from "openai";const ai = new OpenAI({ baseURL: "https://relayfor.si/api/v1", apiKey: process.env.RELAYFOR_ROUTER_KEY,});const reply = await ai.chat.completions.create({ model: "moonshotai/kimi-k3", messages: [{ role: "user", content: "Welcome the 1,000th holder in one line." }],});Specifications
What its maker and providers list for it.
- Reads
- Text, Images, and Video
- Writes
- Text
- Context
- 1,048,576 tokens
- Longest answer
- 943,718 tokens
- Reasoning effort
- low to max
- Intelligence index
- 43.6 (#16 of 219 rated)
- Released
- Jul 16, 2026
- Moderation
- None
Request fields
The fields its providers accept, passed through as you send them.
- frequency_penalty
- include_reasoning
- logit_bias
- logprobs
- max_tokens
- min_p
- presence_penalty
- reasoning
- reasoning_effort
- repetition_penalty
- response_format
- seed
- stop
- structured_outputs
- temperature
- tool_choice
- tools
- top_k
- top_logprobs
- top_p
Questions
How much does Kimi K3 cost?
$0.60 per million input tokens and $18.00 per million output tokens, paid from the token's AI credit. A call of 2,000 tokens in and 500 out costs about $0.01.
How do I call Kimi K3?
Make a router key for one of your tokens on the dashboard, point any OpenAI or Anthropic SDK at https://relayfor.si/api/v1 and send the model id moonshotai/kimi-k3. The token's AI credit pays for each call.
How long a prompt can Kimi K3 take?
Up to 1,048,576 tokens of context, and up to 943,718 tokens in one answer.
Are my prompts stored?
No. The RFS Router passes each call through and keeps only its token counts and cost, for the token's usage page.
More from MoonshotAI
Output price per 1M tokens
Similar in price
Output price per 1M tokens
