moonshotavailablesupports_function_callingsupports_tool_choicesupports_web_search

Back to Model Explorer

MoonshotAvailable on AvalAI

Kimi K3 API on AvalAI

kimi-k3

Kimi K3 is an AI model from Moonshot that is available through AvalAI's OpenAI-compatible API.

Open dashboardCompare

Price display scale

Input price$3.00 / 1M tokens

Output price$15.00 / 1M tokens

Context window262,144 tokens

Maximum output262,144 tokens

Release date2026-07-16

Use Kimi K3 with the AvalAI API

Keep the API key in an environment variable and send requests from server-side code.

Bash

curl https://api.avalai.ir/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $AVALAI_API_KEY" \
  -d '{"model": "kimi-k3", "messages": [{"role": "user", "content": "Give a concise, practical solution."}]}'

Python

import os
from openai import OpenAI

client = OpenAI(
    api_key=os.environ["AVALAI_API_KEY"],
    base_url="https://api.avalai.ir/v1",
)

response = client.chat.completions.create(
    model="kimi-k3",
    messages=[{"role": "user", "content": "Give a concise, practical solution."}],
)

print(response.choices[0].message.content)

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.AVALAI_API_KEY,
  baseURL: "https://api.avalai.ir/v1",
});

const response = await client.chat.completions.create({
  model: "kimi-k3",
  messages: [{ role: "user", content: "Give a concise, practical solution." }],
});

console.log(response.choices[0].message.content);

Create an API keyRead the quickstart

Capabilities and endpoints

• Function calling
• Tool choice
• Web search

Third-party model parameters

Third-party reference data does not change AvalAI endpoint support; use the capabilities and endpoints above.

• 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

Supplemental reasoning effort values

high, low, max

Kimi K3 rate limits

Tier	RPM	TPM
Basic	3	40,000
Tier 1	50	1,000,000
Tier 2	100	4,000,000
Tier 3	250	8,000,000
Tier 4	500	10,000,000
Tier 5	5,000	30,000,000

AvalAI and reference marketplace pricing

Token role	AvalAI final price0% platform fee	OpenRouter cost breakdown
		Model rate	Credit purchase fee	Effective OpenRouter cost after fee
Input price	$3.00 / 1M tokens	$3.00 / 1M tokens	5.5%	$3.17 / 1M tokens
Output price	$15.00 / 1M tokens	$15.00 / 1M tokens	5.5%	$15.82 / 1M tokens

AvalAI pricing is final with a 0% platform fee. The effective OpenRouter prices add its 5.5% credit purchase fee to the highest reported model rate, including long-context tiers. OpenRouter charges a 5.5% fee when credits are purchased ($0.80 minimum), so small credit purchases can have a higher effective cost. OpenRouter FAQ

Peer benchmark performance

Independent, sourced scores with no composite rating.

Artificial Analysis Agentic Index

50.9index

Score	Peer rank	Direction	Source and date
50.9 index	No comparable data	Higher is better	OpenRouter · 2026-09-05

Artificial Analysis Coding Index

76.2index

Score	Peer rank	Direction	Source and date
76.2 index	No comparable data	Higher is better	OpenRouter · 2026-09-05

Artificial Analysis Intelligence Index

50.2index

Score	Peer rank	Direction	Source and date
50.2 index	No comparable data	Higher is better	OpenRouter · 2026-09-05

Third-party model data

Source: OpenRouter

Independent sources supplement this context; AvalAI remains authoritative for pricing, availability, and endpoint support.

Reviewed snapshot 2026-09-05

Provider count

—

Context window range

1,048,576

Maximum output range

943,718

OpenRouter model input rate range

$3 / 1M

OpenRouter model output rate range

$15 / 1M

OpenRouter fee

5.5% credit purchase fee · OpenRouter fee details

Effective input price range after fee

$3.165 / 1M

Effective output price range after fee

$15.825 / 1M

Related models

• kimi-k2.7-code-highspeed
• Kimi K2.7 Code
• Kimi K2.6
• Kimi K2.5

Frequently asked questions

What is the Kimi K3 API on AvalAI?

Create an AvalAI API key and send the model ID kimi-k3 to one of the supported endpoints shown on this page.

How much does the Kimi K3 API cost on AvalAI?

The Kimi K3 API on AvalAI costs $3.00 per 1M input tokens and $15.00 per 1M output tokens.

What is the token cost for Kimi K3?

Current AvalAI pricing for Kimi K3 is $3.00 / 1M tokens for input and $15.00 / 1M tokens for output.

What is the Kimi K3 context window?

The recorded maximum input context for Kimi K3 is 262,144 tokens.

What are the rate limits for Kimi K3 on AvalAI?

On tier 5, Kimi K3 on AvalAI supports up to 5,000 requests per minute and 30,000,000 tokens per minute.

What features does Kimi K3 support on AvalAI?

Kimi K3 on AvalAI supports Function calling, Tool choice, Web search.

What account tier is required to use Kimi K3 on AvalAI?

Calling Kimi K3 on AvalAI requires the Basic tier (tier 0) or higher.

Third-party data and freshness

• Pricing, availability, endpoints, and rate limits: AvalAI structured data (authoritative)
• OpenRouter marketplace · Last checked: 2026-09-05