How to Use Renewable-Powered AI on magicdoor.ai
Turn on renewable-powered inference for GLM-5.3, GLM-5.3 Flash, or DeepSeek V4.1 Flash 1017 and understand the response impact receipt.
Kimi update — October 28, 2026: K3 and Renewable K3 are retired. Kimi K3.1 Pro uses Moonshot AI via Gateway and has no Renewable option. Choose a supported GLM or DeepSeek model below for GreenPT inference.
Magicdoor lets you choose renewable-powered inference for three supported open-weight models. The Renewable control changes the inference route for supported-model requests while it is selected in chat; it does not claim that the models were trained using renewable energy.
Choose the model. Choose renewable.
Supported models
| Model in Magicdoor | GreenPT model route | Attachments on renewable route |
|---|---|---|
| GLM-5.3 | glm-5.3 | No |
| GLM-5.3 Flash | glm-5.3-flash | Images only |
| DeepSeek V4.1 Flash 1017 | deepseek-v4.1-flash-1017 | Images only |
For DeepSeek 1017, GreenPT lists EUR 0.36 input / EUR 0.04 cached input / EUR 1.45 output per million tokens, separate from USD Fireworks pricing. This is the existing EU route, not the US endpoint. See the official checkpoint guide and pricing. Check the picker for current availability.
DeepSeek energy coefficients are inherited estimates from the 0731 model, not checkpoint-specific measurements.
PDFs and other documents are not supported on this route. GreenPT lists these model IDs in its current model API documentation.
Turn it on in chat
- Open Magicdoor chat.
- Select GLM-5.3, GLM-5.3 Flash, or DeepSeek V4.1 Flash 1017.
- Press the Renewable toggle beside the model selector.
- Send your prompt as usual.
- After the reply, expand Renewable inference beneath the response to inspect the receipt.
The Renewable toggle appears only when the selected model supports this route. If you switch to an unsupported model, that model continues on its existing inference route.
Prefer renewable inference by default
Only active subscribers can save Prefer renewable inference in chat preferences. Saving it applies the choice to the current chat and loads it when new chats start. Magicdoor will use GreenPT whenever the active model supports it.
Without an active subscription, select a supported model and turn on Renewable beside the model selector. While the control is on, supported-model requests use GreenPT; starting a new chat reloads the saved preference.
“Prefer” is deliberate: it does not reroute every model. Unsupported models keep their normal behavior, and Magicdoor tools remain available. The GreenPT route itself keeps Magicdoor tools available for supported requests.
What stays unchanged
- Your prompt-first chat workflow
- The ability to switch models during a conversation
- Magicdoor tools
- The existing routes for unsupported models
- The explicit choice of model—you still choose what answers
The route is attributed to GreenPT, which says the inference runs on 100% renewable-powered infrastructure in the EU. This is an inference claim, not a training claim, data-residency promise for Magicdoor as a whole, or full-platform certification claim.
Read the response receipt
After a renewable response, expand Renewable inference. Magicdoor displays provider-reported values for:
- Inference time: how long the model computation took, in the provider's reported unit
- Energy: an estimate normalized for display in mWh or Wh when possible
- Emissions: estimated CO2e for the inference operation
The receipt also offers familiar context, such as time for a 10 W LED bulb. Its method is marked alpha. Comparisons provide scale; they are not direct comparisons with Magicdoor's other inference route. The impact object is transient and session-only, so it will not remain as part of the stored chat after the browser session.
For the units and calculation boundaries, read AI energy use and carbon footprint: what one answer can measure. For the broader terminology, read what green AI means.
Attachments and troubleshooting
The Renewable toggle is missing. Check that you selected one of the three supported models. It is intentionally hidden for other models.
An attachment is rejected. On the renewable route, GLM-5.3 Flash and DeepSeek V4.1 Flash 1017 accept image attachments. Remove unsupported files, choose one of those models for an image, or turn off Renewable and use a compatible existing route. PDFs and documents are not supported.
There is no receipt. Confirm Renewable was active when you sent the prompt. A provider impact object must be returned for Magicdoor to show the receipt.
A tool is needed. Magicdoor tools remain available on the GreenPT route. Enabling the preference does not disable them.
FAQ
Which magicdoor.ai models support renewable inference?
The current GreenPT route supports GLM-5.3, GLM-5.3 Flash, and DeepSeek V4.1 Flash 1017. The Renewable toggle appears only for supported models.
What does Prefer renewable inference change?
Only active subscribers can save this chat preference. Saving it selects the GreenPT route when a supported model is active; other users can turn on Renewable beside the model selector after selecting a supported model. Other models and Magicdoor tools remain unchanged.
Can I attach images or documents on the renewable route?
GLM-5.3 Flash and DeepSeek V4.1 Flash 1017 support image attachments on the GreenPT route. GLM-5.3 is text-only on this route. PDFs and documents are not supported on this route.
What appears in the Renewable inference receipt?
After a renewable response, Magicdoor shows GreenPT's provider-reported inference time, energy, and emissions estimates, plus context comparisons and methodology caveats.
Does the receipt persist with my chat?
The impact object is transient and available for the current browser session only; it is not stored as part of the persisted message history.
Related Resources
GPT Image 2.6 Flare and Sunburst Guide on magicdoor.ai
GPT Image 2.6 Flare and Sunburst on magicdoor.ai, covering quality-based pricing, complexity, editing limits and when to choose each model.
Flux vs GPT Image 2.6 Flare on magicdoor.ai (2026): Fixed Price or Quality Tiers?
Practical Flux vs GPT Image 2.6 Flare comparison using the image models, pricing, and editing support currently available on magicdoor.ai. Covers Flux 2 Pro and GPT Image 2.6 Flare.
AI Model Costs on magicdoor.ai: Current Chat Rates
Compare current chat-model input, cached-input and output prices, including Claude Haiku 5.5 long-context tiers and Mistral Large 4 guarded Gateway rates.
Mistral Large 4 (Le Chonk) on magicdoor.ai: Gateway Limits and Pricing
Compare Mistral Large 4 (Le Chonk)'s image and reasoning capabilities, Vercel Gateway context window, conditional privacy routing, and current token rates.