MoonshotAI: Kimi K2.7 Code: AI model
Kimi K2.7 Code is a coding-focused Moonshot AI model that always reasons, with a 256K context and text+image input. Built for end-to-end programming, reachable from inside Iran through Hormouz.
- Context window:
- 262,144 tokens
- Input:
- $0.67/1M tokens
- Output:
- $3.35/1M tokens
- Type:
- text, image
- Vision
- Tools
- Streaming
- Long context
Thinking levels: Always thinks
Kimi K2.7 Code is a coding-focused member of 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 architecture that accepts text and image input and always operates in a thinking mode, preserving full reasoning content across multi-turn conversations.
With a 256K-token context window it targets long-horizon coding, agentic task decomposition and multi-turn dialogue. It activates about 32B parameters out of roughly 1T total, which keeps it efficient for its capability level.
Pricing is usage-based: $0.74 per million input tokens and $3.5 per million output tokens. Hormouz provides stable access to Kimi K2.7 Code from inside Iran, with no foreign credit card or circumvention tooling required.
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...
Quickstart
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2.7-code",
"messages": [{"role": "user", "content": "Hello!"}]
}'Specs
| Vendor | Moonshot AI |
|---|---|
| Type | Text, Image |
| Context window | 262,144 tokens |
| Pricing | $0.67/M in · $3.35/M out |
| API | Chat Completions |
| Capabilities | Streaming · Vision · Tools |
Benchmarks
Reasoning
Coding
Agentic
Source: Artificial Analysis
Design Arena
How Design Arena works ↗Metrics sourced from Design Arena
Code example
curl https://api.hormouz.net/v1/chat/completions \
-H "Authorization: Bearer ng-YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "moonshotai/kimi-k2.7-code",
"messages": [{"role": "user", "content": "Hello!"}]
}'from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
model="moonshotai/kimi-k2.7-code",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
model: "moonshotai/kimi-k2.7-code",
messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);Buy the MoonshotAI: Kimi K2.7 Code API, paid in rial
- Buy credit with an Iranian bank card; no foreign card or account needed.
- One Hormouz key reaches MoonshotAI: Kimi K2.7 Code and 600+ other models, and you pay only for what you use.
- No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Use via Hormouz
Connect to this model and 600+ others with one API key, then see usage down to each request.
Request company accessFAQ
- How much does Kimi K2.7 Code cost?
- Billing is usage-based: $0.74 per million input tokens and $3.5 per million output tokens. There is no fixed monthly fee. You pay only for what you use, at the rates shown in the Hormouz dashboard.
- How do I access Kimi K2.7 Code from inside Iran?
- Create an account on Hormouz and generate an API key. Hormouz provides a stable path to Kimi K2.7 Code from inside Iran, with no foreign credit card or circumvention tooling required.
- Is Kimi K2.7 Code compatible with OpenAI code?
- Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing OpenAI SDKs and code run without a rewrite.
- Does Kimi K2.7 Code always reason?
- Yes. It always operates in a thinking mode and preserves full reasoning content across multi-turn conversations. It accepts text and image input and has a 256K-token context, built for end-to-end coding and agentic task decomposition.
Updated 2026-10-13