x402 Resources

Max-quality image generation and editing with support for reference images.

The highest fidelity image model from Black Forest Labs.

High-quality image generation and editing with support for reference images.

OpenAI state-of-the-art image generation via Replicate. High-quality photorealism, sharp text rendering, and strong instruction following. Quality: medium.

AI image generation using Grok Imagine model. Takes your prompt and generates a high-quality image using xAI's Grok Imagine API.

AI image generation using Krea 2 Large model. Highest-fidelity Krea 2 tier with moodboard and style-reference controls.

AI image generation using Krea 2 Medium model. High-quality images with moodboard and style-reference controls.

AI image generation using Krea 2 Medium Turbo model. Fast, high-quality images with moodboard and style-reference controls.

AI image generation using nano-banana model. Takes your prompt and generates a high-quality image directly without style blending.

AI image generation using nano-banana-2 model with resolution-based pricing. Dynamic pricing: 1K=$0.06, 2K=$0.10, 4K=$0.15.

AI image generation using nano-banana-pro model. Takes your prompt and generates a high-quality image directly without style blending.

AI image generation using qwen/qwen-image model. Generate high-quality images with advanced AI capabilities using Dexter x402 v2 middleware.

AI image generation using ByteDance Seedream-4.5 model. Generate high-quality images with advanced AI capabilities using Dexter x402 v2 middleware.

AI video generation using grok-imagine-video-1.5. Requires an input image (.jpeg/.jpg/.png/.webp) and a prompt — generates a 10-second high-quality video clip.

AI short video generation using Grok Imagine Video model. Takes your prompt and generates a 10-second high-quality video using xAI's Grok Video API.

AI video generation using ByteDance Seedance 2.0 via Replicate. Generates a video with audio — defaults to a 10-second 480p clip; duration up to 10s, resolution up to 1080p.

AI video generation using ByteDance Seedance 2.5 via Replicate. Native audio and single-pass clips from 4 to 30 seconds; defaults to a 5-second 720p clip. Dynamic pricing: $0.26 per second at 720p, $0.12 per second at 480p.

AI music generation using ElevenLabs Music (via Replicate). Dynamic pricing: $1 per 120 seconds, max 3 minutes.

Transcribe audio from an HTTPS URL using OpenAI GPT-4o Transcribe (via Replicate).

X.AI text-to-speech: convert text to speech (MP3).

Claude Fable 5 text generation (Anthropic). Dynamic pricing: estimated input tokens at $0.01/1K + output tier ceiling at $0.05/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt and image input.

Claude Opus 4.6 text generation (Anthropic). Dynamic pricing: estimated input tokens at $0.005/1K + output tier ceiling at $0.025/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt and image input.

Claude Opus 5 text generation (Anthropic) via OpenRouter. OpenAI-compatible chat completions with a 1M-token context window. Usage-based pricing: input + output tokens at provider cost + 10% (~$5.50 in / $27.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound, so set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

AI-powered creative research and prompt refinement using X and Google. Analyzes trends, and transforms your idea into an optimized generation plan.

AI image generation with intelligent style blending. Takes your prompt and style keywords, refines them together, and generates a high-quality image.

Gemini 3.5 Flash text generation (Google). Dynamic pricing: estimated input tokens at $0.0015/1K + output tier ceiling at $0.009/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports system prompt.

GPT-5.2 text generation (OpenAI). Dynamic pricing: estimated input tokens at $0.00175/1K + output tier ceiling at $0.014/1K. Tiers: small (1K output tokens), medium (4K), large (8K). Supports image input and reasoning effort control.

GPT-5.6 Luna text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$1.10 in / $6.60 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound — set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

GPT-5.6 Sol text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$5.50 in / $33 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound — set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

GPT-5.6 Terra text generation (OpenAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$2.75 in / $16.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound — set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

Grok 4.5 text generation (xAI) via OpenRouter. OpenAI-compatible chat completions. Usage-based pricing: input + output tokens at provider cost + 10% (~$2.20 in / $6.60 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound — set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

Kimi K3 text generation (Moonshot) via OpenRouter. OpenAI-compatible chat completions with a 1M-token context window. Usage-based pricing: input + output tokens at provider cost + 10% (~$3.30 in / $16.50 out per 1M). On the x402 door the per-call charge is quoted up front as an upper bound — set max_tokens to lower it. Also available at POST /v1/chat/completions (API key + credits) and via the multi-model door POST /llm/nim.

OpenAI-compatible chat completions on frontier models (Claude Fable 5, Gemini 3.5 Flash, GPT-5.2 via Replicate; Nemotron 3 Ultra, Kimi K2.6, DeepSeek V4 Pro, GLM-5.1 via NVIDIA NIM with OpenRouter fallback). Pricing is usage-based: input + output tokens at the provider rate + 10%. On the x402 door the per-call charge is quoted up front as an upper bound (set max_tokens to lower it). Also available drop-in at POST /v1/chat/completions with an API key + prepaid credits (billed exactly per token).

Extract latest news from X (Twitter) username, generate draft tweet and banner with Xona.

Extract structured persona from X (Twitter) username. Analyzes posts, profile, and communication style to generate persona, style profile, content patterns, and avatar prompt.

Complete asset details — metadata, variants, market stats. Optionally include profile, risk, OHLCV, or DEX markets.

Get the asset profile — aggregated statistics, metadata, and external provider data.

Comprehensive risk analysis with detailed scoring inputs for a specific asset variant.

Risk score summary for a specific asset variant — score, grade, and trust flags.

List all token variants (native, wrapped, bridged, etc.) for a canonical asset with per-variant market data.

Bulk lookup cached market snapshots for up to 250 Solana mints in one call.

Retrieve curated/pre-assembled asset collections with market data.

List DEX market pools for a specific mint of an asset — liquidity, volume, and protocol tokens.

Get exchange ticker listings for an asset — shows where it trades and at what volume.

Get OHLCV (candlestick) price data for a specific mint — configurable interval and time range.

AI analysis of a single Limitless prediction market. Combines market data with X/news sentiment to return YES/NO/PASS recommendation, confidence, thesis, and key signals.

Scan top active Limitless prediction markets, run AI intel on each, return ranked opportunities sorted by edge.

List active prediction markets on Limitless Exchange (Base) with optional category filter and pagination.

Get canonical price history chart for an asset — uses external provider data when available, otherwise falls back to on-chain OHLCV.

Product discovery across Google Shopping, Amazon, and eBay from a single free-text query. The query is parsed for price range, condition, sort, and target marketplaces, then results are normalized into one schema, deduped across marketplaces, and ranked. Price scales with the number of marketplaces searched, from $0.0067 for one to $0.02 for all three.

Product discovery from a photo instead of a query. Google Lens identifies what is in the image and which retailers sell it, normalized into the same schema as Product Search. Identify mode returns the visual matches and a derived product name for $0.02; Shop mode also runs that product through Google Shopping, Amazon, and eBay for a full price comparison.

Full detail for one TikTok Shop listing from its URL. Returns everything Search does plus the seller's description, category, every product image, specifications, purchasable variants with per-SKU price and stock, seller rating and location, stock status, and a sample of buyer reviews with their text. US storefront only — the upstream serves no other region for detail, while Search covers all 16.

Keyword search across the TikTok Shop marketplace, covering 16 country storefronts. Results come back in the same normalized schema as Product Search, so TikTok Shop sits alongside Google Shopping, Amazon, and eBay in one comparison. Each product carries price, list price, discount, rating, units sold, seller, and TikTok's own badges. Prices are returned in the storefront's own currency, never assumed to be USD.

Get a cached description summary for a specific mint of an asset.

Resolve a Solana mint address or asset reference to its canonical asset ID and variant details.

Quick risk/quality assessment for a Solana mint — score, grade, label, and trust flags.

Search assets by text query — returns canonical assets plus singleton Solana tokens with market stats via Tokens API.

Get the cached market snapshot for a single variant (specific mint) of an asset.

Batch lookup per-mint variant market snapshots for up to 50 mints.

Get movers PumpFun tokens with AI-powered analysis including dominant meta summary, fresh token suggestions, and detailed token information with price changes and icon descriptions.

Get trending PumpFun tokens with AI-powered analysis including dominant meta summary, fresh token suggestions, and detailed token information with price changes and icon descriptions.

Discover trending tokens on Solana via OKX Onchain OS — hot tokens, top movers, smart money signals, and top traders. Multi-chain market intelligence powered by 500+ DEXs.

Deep token analysis on Solana via OKX Onchain OS — price overview, holder analysis, candlesticks, and whale trades.

Fetch token information from Jupiter via Corbits, get curated news from Syra, and generate banner and social content with Xona.

AI-powered market sentiment analysis for any crypto ticker. Returns sentiment score, 7-day price target, top 3 market signals, risk level, and a one-sentence agent-ready summary.

Generate token logo and banner automatically from a prompt. Extracts token information, generates logo, then creates a matching banner. Optionally uses a reference token CA to extract logo style.

Discover trending tokens on X Layer via OKX Onchain OS — hot tokens, top movers, and token search. Powered by Onchain OS with zero gas fees.

Deep token analysis on X Layer via OKX Onchain OS — price overview, holder analysis, candlesticks, and whale trades.