Kimi K2 Thinking

kimi-k2-thinking by Moonshot AI Released November 7, 2025
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to % off
Input from
$0.6 / 1M
Output from
$2.5 / 1M
Cached input from
$ / 1M
Context window
262K
Endpoints
2
from 2 providers
Regions
Global, United States

About Kimi K2 Thinking

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.

Kimi K2 Thinking is a chat model by Moonshot AI, available on Eden AI through 2 endpoints from 2 providers, from $0.6 per million input tokens and $2.5 per million output tokens, with a context window of up to 262K tokens.

Providers and prices

2 endpoints from 2 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
Amazon Web Services (United States)Official−%amazon/moonshot.kimi-k2-thinking
United States
256K
$0.6$0.6
$2.5
$
ReasoningToolsJSONCacheVisionWeb
Google CloudOfficial−%vertex/moonshotai/kimi-k2-thinking-maas
Global
262K
$0.6$0.6
$2.5
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.72 s
Amazon Web Services (United States)
Lowest latency
3.95 s
Amazon Web Services (United States)
Highest throughput
71.84 tok/s
Amazon Web Services (United States)
Best availability
100%
Amazon Web Services (United States)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Amazon Web Services (United States)
0.72 s
3.95 s
39.66 s
71.84 tok/s
100%
3.09%
0%
0%
Google Cloud
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Kimi K2 Thinking with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Kimi K2 Thinking

On Eden AI, prices for this model start at $0.6 per million input tokens and $2.5 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

2 endpoints from 2 providers, available in: Global, United States. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.72 s (Amazon Web Services (United States)) and the highest throughput was 71.84 tokens per second (Amazon Web Services (United States)).