Kimi K2.7 Code – Chat and Inference API hosted in Europe
MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native multimodal mixture-of-experts...
Input Price
$1.50/1M tokens
Output Price
$6.30/1M tokens
Intelligence
N/A
Coding
N/A
Specifications
Technical details and pricing.
EU-hosted inference API
Power your AI projects with open-source models.
Drop-in OpenAI-compatible API. No data leaves Europe.
MiniMax
MiniMax M3
$0.50 / $1.90
per M tokens
Z.ai
GLM 5.3 Flash
$0.20 / $0.60
per M tokens
MoonshotAI
Kimi K3
$4.00 / $18.00
per M tokens
DeepSeek
DeepSeek V4.1 Flash
$0.40 / $1.42
per M tokens
Frequently Asked Questions
What is Kimi K2.7 Code good for?
Use Kimi K2.7 Code for everyday tasks like writing, summarizing, brainstorming, and getting clear explanations.
How much does Kimi K2.7 Code cost?
Pricing is based on usage. Current rates are $1.50/1M tokens for input and $6.30/1M tokens for output.
Can I use Kimi K2.7 Code in LLMBase Chat?
Yes. Use the chat action on this page to open Kimi K2.7 Code in LLMBase Chat. Access still follows the current plan and model tier.
Does Kimi K2.7 Code support images or audio?
Kimi K2.7 Code focuses on text-based tasks.
Where does Kimi K2.7 Code run?
Kimi K2.7 Code is hosted by LLMBase in EU data centers. LLMBase is operated by a German company, and a DPA is available for business customers.
Similar Models
Other models you might want to explore.
Kimi K3.1 Pro
Moonshotai
Kimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is built for long-horizon coding, 3D...
DetailsKimi K3
Moonshotai
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
DetailsSpaceXAI: Grok 4.7
X Ai
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
DetailsBenchmarks and pricing use Artificial Analysis where available. Catalog specs are used as a fallback.