# DGrid AI Docs

> Documentation for DGrid AI: The Decentralized Smart Network of AI

## Docs

- [Academic Research](https://docs.dgrid.ai/academic-research.md): Peer-reviewed academic papers and research that validate DGrid's Proof of Quality (PoQ) consensus mechanism for decentralized AI inference.
- [Arena for Agent](https://docs.dgrid.ai/ai-arena/arena-for-agent.md): Build AI Agents that auto-evaluate models in DGrid's AI Arena, complete benchmark tasks, and earn $DGAI airdrop points for the leaderboard.
- [AI Arena](https://docs.dgrid.ai/ai-arena/overview.md): Discover DGrid AI Arena, a gamified hub where users rate AI models, complete daily tasks, climb the leaderboard, and earn $DGAI airdrop points.
- [Integration Tutorials](https://docs.dgrid.ai/ai-gateway/integrations.md): Step-by-step integration tutorials showing how to connect DGrid AI Gateway to popular developer tools, SDKs, frameworks, and AI coding assistants.
- [Realtime](https://docs.dgrid.ai/ai-gateway/model-api/realtime.md): Build OpenAI-compatible Realtime API sessions on DGrid for low-latency text and audio conversations over WebSocket with streaming voice models.
- [AI Gateway](https://docs.dgrid.ai/ai-gateway/overview.md): DGrid AI Gateway provides one unified, OpenAI-compatible API to call 200+ leading AI models with crypto billing, routing, and global edge access.
- [Supported Countries and Regions](https://docs.dgrid.ai/ai-gateway/supported-regions.md): Regional availability, supported countries, and geographic restrictions for the DGrid AI Gateway, including IP and compliance limitations.
- [Terms of Service](https://docs.dgrid.ai/ai-gateway/terms-of-service.md): Legal terms, acceptable use policy, and service conditions governing access to and use of the DGrid AI Gateway and Model API endpoints.
- [Create speech](https://docs.dgrid.ai/api-reference/audio/create-speech.md): Convert text into natural speech with the OpenAI-compatible audio speech interface. Returns a binary audio stream — save the response body directly to a file.
- [Create transcription](https://docs.dgrid.ai/api-reference/audio/create-transcription.md): Transcribe uploaded audio into text with the OpenAI-compatible Whisper-style interface. Supported formats: FLAC, MP3, MP4, MPEG, MPGA, M4A, OGG, WAV, and WebM.
- [Create translation](https://docs.dgrid.ai/api-reference/audio/create-translation.md): Translate uploaded audio into English with the OpenAI-compatible translation endpoint.
- [Native Gemini Format](https://docs.dgrid.ai/api-reference/audio/native-gemini-format.md): Gemini-native generateContent interface for text chat, multimodal media recognition (images, audio, video), speech synthesis, and image generation with structured parts. Use `generationConfig` to request specific response modalities such as speech (`speechConfig`) or images (`imageConfig`).
- [Create chat completion](https://docs.dgrid.ai/api-reference/chat/create-chat-completion.md): OpenAI-compatible Chat Completions for standard multi-turn chat, structured output, and tool calling. Model names use the `provider/model-name` format, for example `openai/gpt-4o`. Image-capable models can also return generated images through this endpoint.
- [Create message (Claude)](https://docs.dgrid.ai/api-reference/chat/create-message.md): Claude Messages API for Anthropic-compatible payloads, tool use, and system prompts.
- [Create response](https://docs.dgrid.ai/api-reference/chat/create-response.md): OpenAI Responses API for stateful flows, reasoning-specific options, and newer OpenAI tooling patterns.
- [Gemini Media Recognition](https://docs.dgrid.ai/api-reference/chat/gemini-media-recognition.md): Gemini-native generateContent interface for text chat, multimodal media recognition (images, audio, video), speech synthesis, and image generation with structured parts. Use `generationConfig` to request specific response modalities such as speech (`speechConfig`) or images (`imageConfig`).
- [Generate content (Gemini)](https://docs.dgrid.ai/api-reference/chat/generate-content.md): Gemini-native generateContent interface for text chat, multimodal media recognition (images, audio, video), speech synthesis, and image generation with structured parts. Use `generationConfig` to request specific response modalities such as speech (`speechConfig`) or images (`imageConfig`).
- [Create completion](https://docs.dgrid.ai/api-reference/completions/create-completion.md): Classic OpenAI-compatible text completion for single-prompt generation workloads that do not require a multi-message chat schema.
- [Create embeddings](https://docs.dgrid.ai/api-reference/embeddings/create-embedding.md): OpenAI-compatible embeddings for retrieval, clustering, and semantic similarity workloads.
- [Create embeddings (legacy engines)](https://docs.dgrid.ai/api-reference/embeddings/create-engine-embedding.md): Legacy engine-based embeddings path format for older SDK integrations.
- [Create image](https://docs.dgrid.ai/api-reference/images/create-image.md): OpenAI-compatible image generation. Also accepts Qwen-compatible payloads (`wanx-v1` style models) using an `input.messages` wrapper instead of `prompt`.
- [Edit image](https://docs.dgrid.ai/api-reference/images/edit-image.md): Edit an uploaded image with an optional mask using the OpenAI-compatible image editing endpoint. Also accepts Qwen-compatible JSON payloads with an `input.messages` wrapper.
- [Gemini Native Format](https://docs.dgrid.ai/api-reference/images/gemini-native-format.md): Gemini-native generateContent interface for text chat, multimodal media recognition (images, audio, video), speech synthesis, and image generation with structured parts. Use `generationConfig` to request specific response modalities such as speech (`speechConfig`) or images (`imageConfig`).
- [OpenAI Chat Format](https://docs.dgrid.ai/api-reference/images/openai-chat-format.md): OpenAI-compatible Chat Completions for standard multi-turn chat, structured output, and tool calling. Model names use the `provider/model-name` format, for example `openai/gpt-4o`. Image-capable models can also return generated images through this endpoint.
- [Qwen Image Edits](https://docs.dgrid.ai/api-reference/images/qwen-image-edits.md): Edit an uploaded image with an optional mask using the OpenAI-compatible image editing endpoint. Also accepts Qwen-compatible JSON payloads with an `input.messages` wrapper.
- [Qwen Image Generations](https://docs.dgrid.ai/api-reference/images/qwen-image-generations.md): OpenAI-compatible image generation. Also accepts Qwen-compatible payloads (`wanx-v1` style models) using an `input.messages` wrapper instead of `prompt`.
- [Introduction](https://docs.dgrid.ai/api-reference/introduction.md): Overview of DGrid's three API surfaces — the Model API, Management API Keys, and x402 pay-per-inference API — with authentication and base URLs.
- [List models](https://docs.dgrid.ai/api-reference/models/list-models.md): Retrieve all models visible to the current API key. The result is permission-aware and scoped to the key's assigned access group.
- [Create moderation](https://docs.dgrid.ai/api-reference/moderations/create-moderation.md): OpenAI-compatible content safety checks for user-generated or model-generated text. Evaluates input against categories such as hate, harassment, self-harm, sexual content, and violence.
- [Background](https://docs.dgrid.ai/background.md): Market pain points, industry gaps, and the centralized AI infrastructure problems that motivated DGrid's decentralized inference network.
- [Circulation Mechanism](https://docs.dgrid.ai/circulation-mechanism.md): How the $DGAI token flows through the DGrid economy via staking, inference payments, rewards, and buyback to form a closed-loop value cycle.
- [Core Functions](https://docs.dgrid.ai/core-functions.md): The four core functions of $DGAI — staking, payment, incentives, and governance — that power the DGrid decentralized AI inference network.
- [DClaw](https://docs.dgrid.ai/dclaw.md): DClaw is DGrid's one-click deployment layer for spinning up personal AI agents on decentralized nodes without managing infrastructure or servers.
- [DGrid's Solution](https://docs.dgrid.ai/dgrid-solution.md): Core architecture, key modules, and technical design of DGrid AI's decentralized inference network for routing, verification, and incentives.
- [Dori Find Models](https://docs.dgrid.ai/dori.md): Dori is DGrid's natural-language assistant for discovering, comparing, and evaluating large language models across providers, prices, and benchmarks.
- [DGrid AI Documentation](https://docs.dgrid.ai/index.md): Access 200+ leading AI models through DGrid's Web3-native gateway. Explore guides, the API reference, tokenomics, and the $DGAI economy.
- [Management API Keys](https://docs.dgrid.ai/management-api-keys.md): Programmatically create, rotate, list, and revoke DGrid Model API keys to manage the full lifecycle of credentials, scopes, and team access.
- [Node Operators](https://docs.dgrid.ai/node-operators.md): Why node operators are the backbone of DGrid's decentralized AI network and how they earn rewards by contributing GPU compute to model inference.
- [Compliance and Regulatory](https://docs.dgrid.ai/premium/compliance-and-regulatory.md): Regulation S compliance, disclosures, and regulatory principles that apply to purchases of the DGrid Genesis Premium License worldwide.
- [Exclusive Benefits](https://docs.dgrid.ai/premium/exclusive-benefits.md): Exclusive economic, resource, governance, and ecosystem benefits available only to DGrid Genesis Members through the Premium License program.
- [Incentive Mechanism & Rewards](https://docs.dgrid.ai/premium/incentive-mechanism-and-rewards.md): How DGrid Genesis Members earn and redeem tDGAI, IOTX, and referral rewards through the Premium License incentive and rebate program.
- [Legal Disclaimer](https://docs.dgrid.ai/premium/legal-disclaimer.md): Important legal disclaimer, risk warnings, and liability terms that govern participation in the DGrid Genesis Premium License program.
- [Program Overview](https://docs.dgrid.ai/premium/program-overview.md): What the DGrid Genesis Premium License is, why early participants should join, and the benefits unlocked by becoming a Genesis Member.
- [Purchase & Activation](https://docs.dgrid.ai/premium/purchase-and-activation.md): Step-by-step instructions for buying the DGrid Genesis Pass and activating the Premium License to unlock Genesis Member benefits and rewards.
- [Quickstart](https://docs.dgrid.ai/quickstart.md): Get started with DGrid in under five minutes — create an account, generate an API key, and make your first call to a model through the AI Gateway.
- [Roadmap](https://docs.dgrid.ai/roadmap.md): DGrid AI development roadmap covering mainnet launch, decentralized inference milestones, $DGAI token unlocks, and ecosystem product releases.
- [Token Distribution](https://docs.dgrid.ai/token-distribution.md): How the 1 billion $DGAI total supply is allocated across community rewards, team, investors, treasury, ecosystem grants, and liquidity reserves.
- [What is $DGAI?](https://docs.dgrid.ai/what-is-dgai.md): $DGAI is the native utility token of DGrid AI, used for staking, paying for inference, governance voting, and distributing network rewards.
- [What We Do](https://docs.dgrid.ai/what-we-do.md): DGrid's mission to build a trusted, decentralized AI network that efficiently connects model providers with users and developers worldwide.
- [API Reference](https://docs.dgrid.ai/x402/api-reference.md): Endpoint reference for DGrid's x402 API, including request format, payment headers, response codes, and pay-per-inference billing details.
- [x402 API](https://docs.dgrid.ai/x402/overview.md): DGrid's x402 API lets developers pay per inference call using the x402 micropayment protocol — no API keys, accounts, or subscriptions required.

## OpenAPI Specs

- [openapi](https://docs.dgrid.ai/api-reference/openapi.json)