GreenPT Code

GreenPT Code is our suite of specialized AI models for software development, optimized for efficiency and sustainability. These models are designed for agentic coding tasks, multi-file editing, and integration with modern AI coding assistants.

Recommended coding models

Three open-weight models cover almost every coding workload, hosted on sustainable EU infrastructure. glm-5.2 is our flagship coding model.

Sizes, for a sense of what each one costs to run:

kimi-k2.7-code is also tuned for software engineering, with a 256K context. For every model in the catalogue, including chat, vision, embedding, reranking and speech, see Model Cards.

API usage

Call these models via the GreenPT API using OpenAI-compatible endpoints.

curl -X POST https://api.greenpt.ai/v1/chat/completions \
  -H "Authorization: Bearer $GREENPT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5.2",
    "messages": [
      {
        "role": "user",
        "content": "Write a Python function to parse JSON files"
      }
    ]
  }'

import OpenAI from 'openai';

const client = new OpenAI({
  apiKey: process.env.GREENPT_API_KEY,
  baseURL: 'https://api.greenpt.ai/v1',
});

const completion = await client.chat.completions.create({
  model: 'glm-5.2',
  messages: [
    {
      role: 'user',
      content: 'Write a Python function to parse JSON files',
    },
  ],
});

console.log(completion.choices[0].message.content);

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_GREENPT_API_KEY",
    base_url="https://api.greenpt.ai/v1",
)

completion = client.chat.completions.create(
    model="glm-5.2",
    messages=[
        {
            "role": "user",
            "content": "Write a Python function to parse JSON files",
        }
    ],
)

print(completion.choices[0].message.content)

Connect your coding agent

GreenPT Code is OpenAI-compatible, so any tool that supports a custom OpenAI-style endpoint works. Most setups need the same three values:

• Base URL: https://api.greenpt.ai/v1
• API key: your GREENPT_API_KEY
• Model: a coding model ID, e.g. glm-5.2

Step-by-step guides for popular agents:

Any other OpenAI-compatible IDE or extension (Cursor, GitHub Copilot BYOK, Continue, …) connects with the three values above.

Token compression

Cut what your coding agent emits — less code, less prose — to lower API cost, speed up responses, and reduce energy per request. GreenPT Code pairs well with these open-source agent skills:

• Honey — less code and less prose, plus dense agent-to-agent handoffs (~49% fewer code tokens at 98% of baseline quality).
• Ponytail — minimal code, YAGNI first (~54% less code).
• Caveman — terse prose (~75% fewer output tokens).

See the Token compression section for details.

Use cases

Ideal applications for GreenPT Code models.

• AI code assistants: power IDE extensions and coding copilots with agentic capabilities.
• Automated code review: analyze pull requests and suggest improvements automatically.
• Repository analysis: understand large codebases with 256K+ context windows.
• Multi-file refactoring: perform complex migrations across multiple files simultaneously.
• Test generation: generate comprehensive unit and integration tests.
• Documentation: auto-generate documentation from code and comments.

Sustainability

• Sustainable infrastructure: hosted on Scaleway's green EU data centers with low PUE (1.25) and WUE (0.25).
• Efficient architecture: all three are Mixture-of-Experts models, so only a fraction of their parameters activates per request, reducing compute and energy consumption.
• Data sovereignty: full GDPR compliance with EU-based processing.
• Transparency: CO2 and energy usage tracking per request. See Sustainability Impact.