x402engine

Quick image generation using FLUX Schnell (~2s, good for drafts)

High-quality image generation using FLUX.2 Pro (~5s, production-ready)

Image generation with accurate text rendering using Ideogram v3 (best for logos, signage)

Identity-preserving face swap using FLUX PuLID for portraits, product shots, and stylized edits

Google's fast, high-quality image generation with aspect ratio control and optional web search

Generate a 5-second video with Kling V3 Standard in landscape, portrait, or square format

Generate a production-quality 5-second video with Kling V3 Pro

Generate a cinematic 1080p video with MiniMax Hailuo 2.3 Pro

Animate a public image into a 5-second video with Kling V3 Pro

Voice-cloning text-to-speech — provide a reference audio clip and generate speech in that voice at 48kHz

Run code in isolated sandbox — Python, JavaScript, Bash, R (up to 5 min)

Convert audio to text with speaker identification — covers up to 10 minutes of audio

Real-time cryptocurrency prices for any coin in any fiat currency

Market rankings with price, volume, market cap — filterable by category

Historical price, market cap, and volume data for any coin

Currently trending coins on CoinGecko

Search for a coin by name or symbol to get its CoinGecko ID

Token balances for any wallet across 20+ chains — EVM, Solana, Bitcoin

Transaction history with asset transfers and labels for any wallet

Realized and unrealized profit & loss per token for any wallet

Real-time DEX-derived token prices with OHLC data — up to 200 tokens per request

Token/asset metadata — name, symbol, decimals, chain info

Pin JSON, files, or URLs to IPFS for decentralized storage

Fetch a file from IPFS by CID via gateway

OpenAI's flagship multimodal model — strong all-around for text, vision, and reasoning

Fast, affordable GPT-4o variant — great for simple tasks and high-volume use

OpenAI's reasoning model — excels at math, science, coding, and multi-step problem solving

Anthropic's most powerful model — best for complex analysis, coding, and extended thinking

Anthropic's balanced model — excellent coding, reasoning, and creative writing

Anthropic's fastest model — affordable and quick for simple tasks and high throughput

Google's most capable model — strong at reasoning, coding, and multimodal tasks

Google's fast model — great balance of speed, quality, and cost for everyday tasks

DeepSeek's flagship chat model — strong open-source reasoning and coding at low cost

DeepSeek's reasoning model — chain-of-thought reasoning competitive with o3 at fraction of cost

Meta's open-source model — great general-purpose performance at very low cost

xAI's current Grok 4 route — strong reasoning and real-time knowledge

Alibaba's flagship open model — excellent multilingual and coding capabilities

Mistral's flagship model — strong European AI with great multilingual support

Search-augmented LLM — answers grounded in real-time web search with citations

OpenAI's latest flagship model — top-tier reasoning, coding, and multimodal capabilities

OpenAI's code-specialized reasoning model — optimized for software engineering tasks

Moonshot AI's flagship model — strong reasoning and long-context capabilities

MiniMax's efficient model — fast and affordable for everyday tasks

Zhipu AI's flagship model — strong multilingual and reasoning performance

xAI's build-focused model — code generation, analysis, and agentic implementation work

ByteDance's flagship model — competitive reasoning and generation at low cost

Mistral's code-focused model — optimized for software development and technical tasks

DeepSeek's latest flagship model — improved reasoning and coding over V3 at same low cost

Google's Gemini 3.1 Pro Preview on the Gemini Pro compatibility route — advanced reasoning, coding, and multimodal understanding

Google's next-gen flash model — fast and efficient for everyday tasks with improved quality