AI models & inference

Use when you need a new image of a licensed character or brand: give a text prompt and a Story Protocol IP asset, and get a PNG generated with that asset as the reference image. Paid per image in USDC.

Transcribe the audio track of a video into timestamped segments (priced per minute)

+1 more from ParseAPI

IFC models: duct networks, circuits, pressure drop. EN 12828 vessels, EN 378, Swiss refrigerants.

AI Text Summary: Summarize up to 1500 characters in a short paragraph. Local Qwen3 small-model inference; output requires review. Local processing. Limits and retention: /ai-services.

Generate sentence embeddings (all-MiniLM-L6-v2, 384-dim, mean-pooled + L2-normalized) for up to 96 texts per call. Drop-in compatible with any all-MiniLM-L6-v2 index. Pairs with /chunk for a complete RAG pipeline.

OpenAI-compatible chat completion on NVIDIA Nemotron-3-Nano-4B (nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16, base weights), a small open model served from Taifoon's own GPU: short chat, text and arithmetic, not facts about recent technology. 0.001 USDC per request of up to 5,000 tokens (prompt chars/4 + max_tokens, max_tokens ≤ 700). Send { messages, max_tokens }. The answer is checked before you are charged: a failed answer is not charged.

AI Text Embeddings: Generate normalized 384-dimensional MiniLM embeddings for up to 32 texts, each up to 1000 characters. Token truncation is reported. Local processing. Limits and retention: /ai-services.

AI chat and text generation API — general-purpose LLM completion for any prompt; chatbots, drafting and Q&A. Deterministic on-chain execution by the AmanChain node — live consensus state, real blocks, pools and balances. Pay per call via x402 (USDC on Base), no account, no API key. POST JSON {"serviceId":"aman-llm-chat","request":"<input>"}.

Deploy sims to any screen. Control your displays with Claude.

Create, inspect, and manage Wubble music, speech, voice, and sound-effect requests through MCP.

Provides capabilities that let LLM agents perform a range of infrastructure management tasks.

Live rankings and pricing for 10,000+ AI products and LLMs. Free tier; paid data via x402.

French-first SEO: semantic content guides, scoring, E-E-A-T audits for Google, ChatGPT & Claude.

GPT Image 2 Low - GPT Image 2, low quality: text to picture. Sharp detail, faces and readable text. The all-rounder. Any shape up to 3:1, transparent PNG or JPEG. $0.008, about 20 s.

Media Studio image or video: generates an image (FLUX, Imagen 4, GPT Image, Nano Banana Pro) or a video (Seedance, Kling, Veo 3.1) from a prompt. $0.04 this call, in USDC on Base; you pay only if it succeeds. HivemindOS SuperAgent API.

Grok Image Generation 1024x1024: Generate one 1024x1024 image with xAI Grok Imagine through BlockRun. Returns a provider-hosted image URL or inline image file plus generation metadata. Prompt is sent to those providers. Different model from FLUX; generation may require a retry of the same payment to finish. 0.04 USDC includes one 1024x1024 image.

Convert text to speech using OpenAI TTS-1-HD (higher fidelity). Returns base64-encoded audio. Same interface as /api/tts but with better audio quality. No API key needed; pay per call via x402. Text capped at 2000 chars.

Transcribe and summarize one public X post or YouTube video. The exact x402 price is resolved from the source and duration before payment.

Build a real 3D website by chatting: pages, models and text in space, published to a live URL.

One MCP endpoint for 17 top Chinese LLMs. OpenAI-compatible. Up to 60% cheaper than OpenRouter.

Validate Claude Code Settings: Validate a JSON document for Claude Code Settings. Uses a pinned SchemaStore definition on this PC. Reports JSON pointers and rule violations. Up to 100 KB per document; no YAML/TOML parsing or deployment/security guarantee. 0.01 USDC includes one JSON document validation.

Transcript+: audio/video URL or upload to a speaker-labelled (diarized) transcript, summary, chapters and SRT/VTT captions. Priced per audio minute.

Remote MCP gateway for GPT-5.6 Luna, Soul, Terra, and x402-paid agent tools with no API key.

Tables and ledgers checked by arithmetic, not by a model. 24 tools. MCP 2026-07-28 ready.

Conversational what-if simulation: build, diagnose and compare Petri-net models; CC0 catalog.

Decode a vehicle identification number into make, model, year and build details.

Inspect 1NFER models, crypto funding terms and task cost without keys or paid calls.

Mid-tier OpenAI-compatible chat completion. Qwen3 235B (instruct/thinking/VL/next), DeepSeek V3.2, GLM 5.2, venice-uncensored 1.2, GLM 4.6/4.7, Kimi K2.5, MiniMax M3 Preview, Nemotron 3 Ultra 550B, DeepSeek V4.1 Flash, Gemma 4 26B. Supports tools/tool_choice and stream:true SSE.

GPU compute API: LLM inference (ornith-1.5) on RTX 4080, pay-per-credit in Bitcoin.

Shared cross-LLM long-term memory over MCP: semantic recall, sessions, and media (pgvector).