Hormouz AIHormouzSign in

MoonshotAI: Kimi K2 0711: AI model

Kimi K2 0711 is a trillion-parameter MoE model tuned for agentic coding and tool use from Moonshot AI. Reachable from inside Iran through Hormouz.

Context window:
131,072 tokens
Input:
$0.57/1M tokens
Output:
$2.3/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Kimi K2 (0711) is a Mixture-of-Experts model from Moonshot AI: one trillion parameters in total, with 32 billion firing on each forward pass. It is tuned for agentic work. Advanced tool use, reasoning and code synthesis. And scores well across coding, reasoning and tool-use benchmarks. It runs a 128K-token context and was trained with the MuonClip optimizer to keep large-scale MoE training stable.

Kimi K2 0711 is a good fit for agentic coding, tool-using agents and code-synthesis pipelines. It supports tool (function) calling. The model works with a context window of about 131K tokens, so it comfortably handles long inputs. It is served through Hormouz behind an OpenAI-compatible API. Just point your base URL at Hormouz and drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.57 per million input tokens and $2.3 per million output tokens, billed only for what you use. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for...

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",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorMoonshot AI
TypeText
Context window131,072 tokens
Pricing$0.57/M in · $2.30/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
59.8%
HLE
Humanity's Last Exam
4.4%
IFBench
Instruction-following
55.1%
AA-LCR
Long-context reasoning
28%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
17.9%
Non-Hallucination
Rate of avoiding fabricated answers
18.4%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
8.3%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
24.9%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
Code
Top 86%
1,039Elo
Win rate: 51.7%Avg time: 60.0s
Data Viz
Top 87%
1,025Elo
Win rate: 49.4%Avg time: 57.0s
Game Dev
Top 90%
987Elo
Win rate: 46.4%Avg time: 70.8s
UI Component
Top 83%
1,037Elo
Win rate: 55.1%Avg time: 52.6s
Website
Top 83%
1,057Elo
Win rate: 53.1%Avg time: 59.8s

Metrics sourced from Design Arena

Code example

cURL
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",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
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",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
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",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the MoonshotAI: Kimi K2 0711 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches MoonshotAI: Kimi K2 0711 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.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does Kimi K2 0711 cost?
Billing is usage-based: $0.57 per million input tokens and $2.3 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access Kimi K2 0711 from inside Iran?
Create a Hormouz account and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is Kimi K2 0711 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does Kimi K2 0711 have?
Kimi K2 0711 works with a context window of about 131K tokens. It also supports tool calling. That makes it suitable for agentic coding, tool-using agents and code-synthesis pipelines.
What is Kimi K2 0711 good for?
It is best suited to agentic coding, tool-using agents and code-synthesis pipelines.
Which provider serves Kimi K2 0711 on Hormouz?
Hormouz is the provider you connect to and bill through. It routes your request to the model and handles access, billing and stable connectivity from inside Iran on your behalf.

Updated 2026-10-13