About Kimi K3

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

Kimi K3 is a chat model by Moonshot AI, available on Eden AI through 12 endpoints from 10 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

12 endpoints from 10 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

QwenOfficial−35%qwen/kimi-k3

Global

1M

$3$1.95

$9.75

$0.195

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/moonshotai/Kimi-K3

Global

1.05M

$2.7$2.7

$13.5

$0.27

ReasoningToolsJSONCacheVisionWeb

DeepInfra (United States)Official−%deepinfra/moonshotai/Kimi-K3

United States

1.05M

$2.85$2.85

$14.25

$0.285

ReasoningToolsJSONCacheVisionWeb

Tencent Cloud (Asia)Official−%tencent/kimi-k3

Asia

1M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-kimi-k3

Global

1M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

TensorX (Europe)Official−%tensorx/moonshotai/kimi-k3

Europe

1.05M

$3$3

$15

$0.75

ReasoningToolsJSONCacheVisionWeb

Amazon Web ServicesOfficial−%amazon/moonshotai.kimi-k3

Global

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Amazon Web Services (United States)Official−%amazon/moonshotai.kimi-k3@us

United States

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (United States)Official−%fireworks_ai/accounts/fireworks/models/kimi-k3

United States

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (United States)Official−%fireworks_ai/kimi-k3

United States

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Moonshot AI (Asia)Official−%moonshot/kimi-k3

Asia

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/moonshotai/Kimi-K3

Global

1.02M

$3$3

$15

$3

ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token

1.15 s

Amazon Web Services

Lowest latency

2.95 s

Databricks

Highest throughput

74.92 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

4.24 s

11.39 s

95.92 s

26.7 tok/s

99.87%

94.38%

3.64%

0%

Together AI

1.61 s

5.7 s

55.51 s

45.51 tok/s

99.37%

92.87%

12.86%

36%

DeepInfra (United States)

2.02 s

15.8 s

250.78 s

17.02 tok/s

98.34%

61.59%

26.23%

0%

Tencent Cloud (Asia)

5.2 s

65.69 s

235.2 s

40.04 tok/s

100%

65.31%

0%

Databricks

1.98 s

2.95 s

19.27 s

50.44 tok/s

100%

89.08%

34.06%

0%

TensorX (Europe)

1.45 s

10.5 s

105.76 s

41.18 tok/s

98.88%

83.13%

9.35%

1.3%

Amazon Web Services

1.15 s

3.62 s

63.84 s

74.92 tok/s

100%

71.52%

6.45%

0%

Amazon Web Services (United States)

s

tok/s

%

Fireworks AI (United States)

2.64 s

8.74 s

81.11 s

29.99 tok/s

99.77%

91.34%

60.14%

5.88%

Fireworks AI (United States)

3.31 s

10.51 s

74.01 s

30.67 tok/s

99.88%

93.67%

60.43%

2.78%

Moonshot AI (Asia)

9.47 s

19.87 s

111.53 s

16.38 tok/s

99.96%

91.52%

3.24%

0%

Nebius

2.31 s

5.96 s

153.02 s

54.34 tok/s

99.91%

93.97%

21.01%

0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Kimi K3 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())

curl https://api.edenai.run/v3/chat/completions \
  -H "Authorization: Bearer YOUR_EDENAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "", "messages": [{"role": "user", "content": "Hello!"}]}'

const response = await fetch("https://api.edenai.run/v3/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer YOUR_EDENAI_API_KEY",
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "",
    messages: [{ role: "user", content: "Hello!" }],
  }),
});
console.log(await response.json());

Questions about Kimi K3

How much does Kimi K3 cost?

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. .

What is the context window of Kimi K3?

Up to 1.05M tokens, depending on the endpoint.

Which providers serve Kimi K3?

12 endpoints from 10 providers, available in: Global, Asia, Europe, United States. All of them are called with the same Eden AI API key.

Can I run Kimi K3 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 K3?

Over the last 30 days, the fastest first token was 1.15 s (Amazon Web Services) and the highest throughput was 74.92 tokens per second (Amazon Web Services).

More from Moonshot AI

Other Moonshot AI models you can call with the same key.

See all Moonshot AI models

About Kimi K3

Providers and prices

Performance

Estimate your monthly cost

Call Kimi K3 with Eden AI

Questions about Kimi K3

More from Moonshot AI

Kimi K2 Thinking

Kimi K2 Instruct 0905

Kimi K2 Instruct

Kimi K2.6

Kimi K2.5

Kimi K3 Fast

Kimi K3

Kimi K2.8 Preview

Kimi K2.7 Code Highspeed

Kimi K2.7 Code