Specs & substance
- Developed by
- Moonshot
- Model family
- Kimi
- Use case
- Coding
- Modality
- Text
- Context window
- 256K tokens
- Architecture
- MoE
- Version
- K2.7 Code
- License
- Modified MIT
- Pricing
- $0.75 in · $3.50 out · $0.16 cache read
- Released
- May 2026
- Endpoint
- parasail-kimi-k27-code
Specialized coding model optimized for software engineering and agentic coding workflows.
Kimi K2.7 Code is part of the Kimi family by Moonshot, and sits in the coding category. It supports a 256K tokens context window and is built on a MoE architecture.
Key strengths: coding, agentic. Parasail serves Kimi K2.7 Code on a global fleet of current-gen GPUs behind a single OpenAI-compatible endpoint — with per-token pricing, no minimums, and dedicated capacity options when you need guaranteed throughput.
Drop-in via the OpenAI SDK
Point any OpenAI-compatible client at Parasail and change the model name. That's it.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://api.parasail.io/v1"
)
response = client.chat.completions.create(
model="parasail-kimi-k27-code",
messages=[
{"role": "user", "content": "Hello, what can you do?"}
],
stream=True,
max_tokens=1000
)
for chunk in response:
if chunk.choices and chunk.choices[0].delta.content is not None:
print(chunk.choices[0].delta.content, end="", flush=True) curl https://api.parasail.io/v1/chat/completions \
-H "Authorization: Bearer $PARASAIL_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "parasail-kimi-k27-code",
"messages": [{"role": "user", "content": "Hello, what can you do?"}],
"stream": true,
"max_tokens": 1000
}' Explore the library
Kimi K3
Moonshot's 2.8T-parameter open-weight multimodal agentic model — frontier reasoning, native vision, and a 1M-token context window.
Kimi K2.6
Strong reasoning model with excellent long-context understanding.
GLM-5.3 Flash
Z.AI’s first natively multimodal GLM-5 model — 320B total / 18B active parameters at a tenth of GLM-5.2’s price.
Qwen3-Coder-Next
Code-specialized model with strong fill-in-the-middle and agentic coding support.
Start building today
Instantly run any open model — popular or specialized.