Kimi K2.7 Code

kimi-k2.7-code by Moonshot AI Released June 13, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off
Input from
$0.6175 / 1M
Output from
$2.6 / 1M
Cached input from
$0.1235 / 1M
Context window
262K
Endpoints
8
from 8 providers
Regions
Monde, Asie, Europe, États-Unis

About Kimi K2.7 Code

MoonshotAI : Kimi K2.7 Code est un modèle axé sur la programmation issu de la famille Kimi K2 de Moonshot AI, conçu pour mener à bien de manière fiable des tâches de programmation de bout en bout dans des contextes étendus.

Kimi K2.7 Code est un modèle conversationnel développé par Moonshot AI, disponible sur Eden AI via 8 endpoints chez 8 fournisseurs, à partir de 0,618 $ par million de tokens en entrée et 2,6 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 262K tokens.

Providers and prices

8 endpoints from 8 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-k2.7-code
Monde
262K
$0.95$0.6175
$2.6
$0.1235
ReasoningToolsJSONCacheVisionWeb
DeepInfra (États-Unis)Official−%deepinfra/moonshotai/Kimi-K2.7-Code
États-Unis
262K
$0.68$0.68
$3.4
$0.136
ReasoningToolsJSONCacheVisionWeb
GreenPT (Europe)Official−%greenpt/kimi-k2.7-code
Europe
256K
$0.8665$0.8665
$4.3324
$0.2228
ReasoningToolsJSONCacheVisionWeb
Tencent Cloud (Asie)Official−%tencent/kimi-k2.7-code
Asie
256K
$0.95$0.95
$4
$0.19
ReasoningToolsJSONCacheVisionWeb
Cloudflare (CF/MOONSHOTAI/KIMI-K2.7-CODE)Official−%cloudflare/@cf/moonshotai/kimi-k2.7-code
CF/MOONSHOTAI/KIMI-K2.7-CODE
262K
$0.95$0.95
$4
$0.19
ReasoningToolsJSONCacheVisionWeb
Moonshot AI (Asie)Official−%moonshot/kimi-k2.7-code
Asie
262K
$0.95$0.95
$4
$0.19
ReasoningToolsJSONCacheVisionWeb
NebiusOfficial−%nebius/moonshotai/Kimi-K2.7-Code
Monde
262K
$0.95$0.95
$4
$0.95
ReasoningToolsJSONCacheVisionWeb
TensorX (Europe)Official−%tensorx/moonshotai/kimi-k2.7-code
Europe
262K
$1.25$1.25
$4.5
$0.3125
ReasoningToolsJSONCacheVisionWeb

Performance

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

Fastest first token
1.16 s
TensorX (Europe)
Lowest latency
2.57 s
TensorX (Europe)
Highest throughput
85.25 tok/s
TensorX (Europe)
Best availability
100%
TensorX (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
5.56 s
9.72 s
34.15 s
27.6 tok/s
100%
85.35%
1.03%
0%
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%
GreenPT (Europe)
s
s
s
tok/s
%
%
%
%
Tencent Cloud (Asie)
s
s
s
tok/s
%
%
%
%
Cloudflare (CF/MOONSHOTAI/KIMI-K2.7-CODE)
s
s
s
tok/s
%
%
%
%
Moonshot AI (Asie)
2.96 s
6.25 s
27.96 s
36.04 tok/s
100%
95.03%
0%
0%
Nebius
s
s
s
tok/s
%
%
%
%
TensorX (Europe)
1.16 s
2.57 s
13.04 s
85.25 tok/s
100%
97.53%
0%
0%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Kimi K2.7 Code 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 K2.7 Code

On Eden AI, prices for this model start at $0.6175 per million input tokens and $2.6 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

8 endpoints from 8 providers, available in: Monde, Asie, Europe, États-Unis. 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 1.16 s (TensorX (Europe)) and the highest throughput was 85.25 tokens per second (TensorX (Europe)).