About Kimi K3

Kimi K3 est un modèle de raisonnement multimodal à poids ouvert de 2,8 T développé par Moonshot AI.

Kimi K3 est un modèle conversationnel développé par Moonshot AI, disponible sur Eden AI via 13 endpoints chez 11 fournisseurs, à partir de 1,95 $ par million de tokens en entrée et 9,75 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 1,05M tokens.

Providers and prices

13 endpoints from 11 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

Monde

1M

$3$1.95

$9.75

$0.195

ReasoningToolsJSONCacheVisionWeb

DeepInfra (États-Unis)Official−%deepinfra/moonshotai/Kimi-K3

États-Unis

1.05M

$2.85$2.85

$14.25

$0.285

ReasoningToolsJSONCacheVisionWeb

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

Asie

1M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

DatabricksOfficial−%databricks/databricks-kimi-k3

Monde

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

Monde

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

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

États-Unis

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (États-Unis)Official−%fireworks_ai/accounts/fireworks/models/kimi-k3

États-Unis

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

Fireworks AI (États-Unis)Official−%fireworks_ai/kimi-k3

États-Unis

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

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

Asie

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

NebiusOfficial−%nebius/moonshotai/Kimi-K3

Monde

1.02M

$3$3

$15

$3

ReasoningToolsJSONCacheVisionWeb

Together AIOfficial−%together_ai/moonshotai/Kimi-K3

Monde

1.05M

$3$3

$15

$0.3

ReasoningToolsJSONCacheVisionWeb

GreenPT (Europe)Official−%greenpt/kimi-k3

Europe

1M

$3.7135$3.7135

$18.5674

$0.9284

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

3.6 s

Amazon Web Services

Highest throughput

74.92 tok/s

Amazon Web Services

Best availability

100%

Tencent Cloud (Asie)

Endpoint

First token

Latency p50

Latency p95

Throughput

Availability

Cache hits

Tool errors

JSON errors

Qwen

3.73 s

11.29 s

93.76 s

33.47 tok/s

99.93%

92.91%

2.08%

0.12%

DeepInfra (États-Unis)

2.01 s

15.02 s

196.62 s

18.14 tok/s

96.17%

66.12%

20.6%

0%

Tencent Cloud (Asie)

5.2 s

48.68 s

235.2 s

37.68 tok/s

100%

64.97%

0%

Databricks

2.46 s

4.54 s

26.85 s

46.1 tok/s

100%

85.88%

0%

TensorX (Europe)

1.5 s

11.25 s

122.59 s

41.59 tok/s

98.94%

85.07%

3.47%

1.3%

Amazon Web Services

1.15 s

3.6 s

63.84 s

74.92 tok/s

100%

70.56%

6.25%

0%

Amazon Web Services (États-Unis)

s

tok/s

%

Fireworks AI (États-Unis)

2.88 s

10.59 s

78.9 s

29.21 tok/s

100%

95.92%

30.74%

0%

Fireworks AI (États-Unis)

3.4 s

12.87 s

71.27 s

28.35 tok/s

99.96%

94.45%

28.78%

5.26%

Moonshot AI (Asie)

7.48 s

17.43 s

114.67 s

21.51 tok/s

99.98%

92%

1.95%

0%

Nebius

1.23 s

5.29 s

237.54 s

68.54 tok/s

99.9%

89.26%

10.75%

0%

Together AI

1.56 s

5.88 s

56.59 s

43.52 tok/s

99.52%

90.83%

5.99%

21.43%

GreenPT (Europe)

s

tok/s

%

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?

13 endpoints from 11 providers, available in: Monde, Asie, Europe, États-Unis. 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

Aucun élément.