~kimi Latest

~kimi-latest by Moonshot AI Released July 17, 2026
Reasoning · Function calling · Structured output · Prompt caching · Image input · Video input · EU hosting · Up to 35% off
Input from
$1.95 / 1M
Output from
$9.75 / 1M
Cached input from
$0.195 / 1M
Context window
1.05M
Endpoints
14
from 12 providers
Regions
Global, Asia, Europe, United States

About ~kimi Latest

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.

~kimi Latest is a chat model by Moonshot AI, available on Eden AI through 14 endpoints from 12 providers, from $1.95 per million input tokens and $9.75 per million output tokens, with a context window of up to 1.05M tokens.

Providers and prices

14 endpoints from 12 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
Qwenqwen/kimi-k3
Global
1M
$3$1.95
$9.75
$0.195
−35% · Reasoning · Tools · JSON · Cache · Vision
DeepInfra (United States)deepinfra/moonshotai/Kimi-K3
United States
1.05M
$2.85
$14.25
$0.285
Reasoning · Tools · JSON · Cache · Vision
Arkane Cloudarkanecloud/moonshotai/Kimi-K3
Global
1M
$3
$15
$0.3
Reasoning · Tools · Cache · Vision
Tencent Cloud (Asia)tencent/kimi-k3
Asia
1M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache
Databricksdatabricks/databricks-kimi-k3
Global
1M
$3
$15
$0.3
Reasoning · Tools · Cache · Vision
TensorX (Europe)tensorx/moonshotai/kimi-k3
Europe
1.05M
$3
$15
$0.75
Reasoning · Tools · Cache · Vision
Amazon Web Servicesamazon/moonshotai.kimi-k3
Global
1.05M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache · Vision
Amazon Web Services (United States)amazon/moonshotai.kimi-k3@us
United States
1.05M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache · Vision
Fireworks AI (United States)fireworks_ai/accounts/fireworks/models/kimi-k3
United States
1.05M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache · Vision
Fireworks AI (United States)fireworks_ai/kimi-k3
United States
1.05M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache · Vision
Moonshot AI (Asia)moonshot/kimi-k3
Asia
1.05M
$3
$15
$0.3
Official · Reasoning · Tools · JSON · Cache · Vision
Nebiusnebius/moonshotai/Kimi-K3
Global
1.05M
$3
$15
$3
Reasoning · Tools · Cache · Vision
Together AItogether_ai/moonshotai/Kimi-K3
Global
1.05M
$3
$15
$0.3
Reasoning · Tools · JSON · Cache · Vision
GreenPT (Europe)greenpt/kimi-k3
Europe
1M
$3.6264
$18.1318
$0.9066
Reasoning · Tools · JSON · Cache · Vision

Performance

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

Fastest first token
0.82 s
Nebius
Lowest latency
2.19 s
Databricks
Highest throughput
104.75 tok/s
Amazon Web Services
Best availability
100%
Tencent Cloud (Asia)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
4.3 s
12.14 s
87.62 s
26.86 tok/s
99.91%
93.47%
3.61%
6.67%
DeepInfra (United States)
1.77 s
6.89 s
67.22 s
41.21 tok/s
55.8%
86.15%
60.09%
0%
Arkane Cloud
0.88 s
4.4 s
34.3 s
82 tok/s
99.71%
96.47%
0.36%
0%
Tencent Cloud (Asia)
2.84 s
5.22 s
126.82 s
25.63 tok/s
100%
93.25%
0.43%
0%
Databricks
2.19 s
2.19 s
8.43 s
35.31 tok/s
100%
83.55%
0%
0%
TensorX (Europe)
2.19 s
8.56 s
107 s
40.18 tok/s
96.66%
81.89%
8.05%
0%
Amazon Web Services
1.51 s
3.8 s
78.76 s
104.75 tok/s
96.03%
71.75%
7.41%
17.24%
Fireworks AI (United States)
2.46 s
6.94 s
47.28 s
36.7 tok/s
99.77%
93.14%
5.34%
0%
Fireworks AI (United States)
2.57 s
9.04 s
60.25 s
36.37 tok/s
99.77%
88.34%
7.03%
0%
Moonshot AI (Asia)
8.54 s
18.82 s
109.55 s
26.8 tok/s
99.7%
91.39%
2.78%
27.66%
Nebius
0.82 s
2.31 s
77.87 s
100.88 tok/s
98.51%
88.85%
7.77%
0%
Together AI
1.65 s
7.3 s
51.91 s
40.35 tok/s
99.82%
92.75%
6.94%
20%
GreenPT (Europe)
1.84 s
14.47 s
84.52 s
31.87 tok/s
95.99%
51.19%
1.34%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call ~kimi Latest 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": "~kimi-latest",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about ~kimi Latest

On Eden AI, prices for this model start at $1.95 per million input tokens and $9.75 per million output tokens. Prices differ by endpoint; the providers table lists each one.

Up to 1.05M tokens, depending on the endpoint.

14 endpoints from 12 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run ~kimi Latest in the EU? 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. ‖ How fast is ~kimi Latest? Over the last 30 days, the fastest first token was 0.82 s (Nebius) and the highest throughput was 104.75 tokens per second (Amazon Web Services).