Generate
Create images, chat with LLMs, and generate media using The Grid’s distributed GPU network.
Account Credits
The Grid meters generation against a USD-denominated internal account balance.
Check /v1/account/credits for paid balance, any free allowance, and
total_spendable_usd; a displayed free allowance is spendable only when
free.active is true.
Workers separately accrue den work units for completed jobs. Worker den is not a customer’s usage balance and cannot be transferred or spent.
Generate Images
aipg.art
aipg.art is the AI art gallery powered by The Grid.
What you can do:
- Generate images with z-image-turbo, FLUX.2 Klein 4B, Krea 2 Turbo, and more
- Browse community creations
- Use pre-built workflows or customize parameters
- Download your generations
How to use:
- Go to aipg.art
- Sign up or log in
- Enter your prompt
- Choose a model and settings
- Generate
Available Models:
| Model | Best For |
|---|---|
| z-image-turbo | Fast, high-quality generations |
| FLUX.2 Klein 4B FP8 | Highest quality, photorealism |
| Krea 2 Turbo | Fast, stylized generations |
Available models track what workers are currently serving — check the art gallery or /v1/models for the live list.
Parameters you can adjust:
- Steps (quality vs speed)
- CFG scale (prompt adherence)
- Sampler and scheduler
- Dimensions
- Seed (for reproducibility)
NFT Provenance (Roadmap)
The proposed GridNFT flow is limited to approved deterministic media workflows. It is not deployed on Base mainnet and there is no live minting API today.
The design records the inputs needed to identify and re-execute a supported generation:
- Model hash
- Prompt and negative prompt
- Seed, steps, CFG, sampler
- Workflow recipe
Validators can compare a trusted re-execution with the committed artifact under the workflow’s evidence policy. Exact bytes are not promised across arbitrary models, software versions, quantizations, or hardware.
Chat with AI
aipg.chat
aipg.chat is the chat interface running on The Grid.
What you get:
- Chat with open-source LLMs (gpt-oss-120b, gpt-oss-20b, qwen3-27b, and more)
- No corporate API middleman
- Inference runs on Grid workers
- Conversation history
How to use:
- Go to aipg.chat
- Sign up or log in
- Select a model
- Start chatting
The responses come from real GPUs running real models—no API wrappers, no OpenAI under the hood.
Use the API
For programmatic access, use The Grid API directly.
Get Your API Key
- Sign in at console.aipowergrid.io with Google, GitHub, or a wallet
- Create an API key (shown once)
- Check your usage anytime in the console
Generation API (OpenAI Compatible)
The Grid supports OpenAI-compatible text, image, and video generation. Use any OpenAI SDK:
from openai import OpenAI
client = OpenAI(
base_url="https://api.aipowergrid.io/v1",
api_key="your-grid-api-key",
)
stream = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "Hello!"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)Or with curl:
curl -N https://api.aipowergrid.io/v1/chat/completions \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"gpt-oss-120b","messages":[{"role":"user","content":"Hello"}],"stream":true}'Python (OpenAI SDK)
The API is OpenAI-compatible — use the standard openai package, no custom
SDK needed. Check /v1/models for the
models currently online.
pip install openaifrom openai import OpenAI
client = OpenAI(
base_url="https://api.aipowergrid.io/v1",
api_key="your-grid-api-key",
)
stream = client.chat.completions.create(
model="gpt-oss-120b",
messages=[{"role": "user", "content": "What is AI Power Grid?"}],
stream=True,
)
for chunk in stream:
print(chunk.choices[0].delta.content or "", end="", flush=True)Discord Agents
The Grid powers Discord agents and automations:
News Bot
AI-powered news summaries and updates.
Repository: github.com/AIPowerGrid/grid-discord-news-bot
Aigarth
Natural chat, Grid tools, and image generation in Discord.
Repository: github.com/AIPowerGrid/grid-discord-agent
What Models Are Available?
Available models track what workers are currently serving. Check
/v1/models for the live list. Current
categories:
Image Generation
- z-image-turbo
- FLUX.2 Klein 4B FP8
- Krea 2 Turbo
Video Generation
- LTX-2.3 — available now via
POST /v1/videos/generations
Text Generation
- gpt-oss-120b
- gpt-oss-20b
- qwen3-27b
- deepseek-v4-flash-nvfp4
- Gemma4-26B_A4B-uncensored
Coming Soon
- Audio/music generation
Models are continuously being added.
Tips
For better images:
- Be specific in prompts
- Use negative prompts to exclude unwanted elements
- Higher steps = more detail (but slower)
- Same seed + same settings = same image
For faster generations:
- Use a turbo model (z-image-turbo, Krea 2 Turbo) for quick iterations
- Lower step counts for drafts
- Generate at smaller sizes, upscale after
For chat:
- Larger models give better responses but may be slower
- Be clear and specific in your questions
- The model only knows what it was trained on (no real-time info)
Questions?
- Discord: discord.gg/W9D8j6HCtC
- API issues: Check api.aipowergrid.io
- Feature requests: Open an issue on GitHub