AI models & inference

AI-callable calculators and engineering models with real formulas. No hallucinated math.

ElevenLabs in natural language: generate speech in any language, create and manage voices, compose m

Your Plaud recordings in natural language: list recordings, read speaker-attributed transcripts and

Search your AI chat history (ChatGPT, Claude, Codex) from any MCP client. Remote, private, read-only

130+ AI models for image, video, music, and audio — 18 model families, one RunAPI account.

Exact Claude API cost calc with real cache economics, plus a tiktoken-misuse scanner.

Publish AI-generated HTML to a live page on your own domain — from Claude, ChatGPT, or Cursor.

MCP server providing access to the Scorecard API to evaluate and optimize LLM systems.

List all AI models on Bittensor. OpenAI /v1/models compatible. Drop-in: just change base_url to gateway.spraay.app/bittensor/v1

Tenjin's tool router. Send a turn's bounded conversation packet, or a one-line query, and get which pay-per-call x402 service fits the step, if any, with its spec to fill and pay yourself. $0.003 per answer from a completed routing gate; an answer made without one settles at $0. batch-settlement only. Agent guide: https://tenjin.sh/llms.txt

LLM inference as a pay-per-call commodity — ask anything (?q=...) and get the first live answer from a multi-provider failover chain (Groq, Gemini, paid tiers when configured). One flat price, any subject, no API keys...

OpenAI-compatible chat on 100+ Venice models via x402 USDC (Base). Model from GET /api/v1/models?type=text; personas via /characters. Thinking models: empty content + reasoning_content is success; use venice_parameters.disable_thinking for plain text.

Signed spend receipts for agent x402 payments — who paid which call, verifiable by a third party. Treasury desk and possession book for agent spend — export, policy, evidence. POST /v1/chat/completions is the x402 USDC door on Base and Solana. Returns signed receipt + public verify_url. Paying this host is real mainnet USDC.

Full transcript of any YouTube video by video id or URL: captions/subtitles as clean plain text plus timestamped segments, the video's chapter markers, and every caption track it offers so an agent can pick a language and re-fetch. YouTube transcript, video to text, captions extraction, subtitle download, closed captions, speech to text, multilingual, asr and authored tracks. No API key.

One original constraint card in the tradition of lateral-thinking decks: a short instruction, reversal or question you can apply to whatever is stuck, written fresh by a model at high temperature on every call. The cards are ours, never a card from any published deck. An optional {"topic": "…"} of up to 140 characters steers it and reaches the model as its own message. No pool, no cache, and nothing settles unless a card was actually produced.

Instant text statistics — characters (with/without spaces), words, unique words, sentences, paragraphs, average word/sentence length, longest word, reading and speaking time. Deterministic, no LLM, no API key. For agents sizing content before summarizing, chunking, embedding, or posting. Pass text as ?text= (GET) or a JSON body (POST).

Text-to-speech synthesis in 1 of 10 standard voices (5 male M1-M5, 5 female F1-F5) across 31 languages, up to 500 characters, returned as inline WAV audio. Use it to: give an agent a spoken reply, read an alert aloud, narrate a short UI prompt, add voice to a chatbot response, speak a confirmation message. Cheapest tier. USDC on Base via x402, no API key, no signup.

ElevenLabs text-to-speech: convert text to speech (MP3) (Base Mainnet).

Generate cryptographic random bytes

Generate text embeddings and semantic embedding vectors using OpenAI text-embedding-3-small for vector search, semantic similarity, clustering, retrieval, and RAG workflows.

Generates a 1024x1024 JPEG from a text prompt with FLUX.1 [schnell] in about 2 seconds. Returns a hosted image URL valid for 24 hours that you can hand straight to the next tool; add inline=true to also get the base64. Choose 1-8 diffusion steps (default 4). You are only charged if the image is delivered. No API key, no account.

AI outline generated from text

LLM chat completion (qwen2.5:7b on the operator's RTX 5090 Laptop GPU) — Genesis402 / UnyKorn Operator Network

ElevenLabs TTS: 29 characters, voice 21m00Tcm4TlvDq8ikWAM

Generate one image from a text prompt: app icon, brand logo, character mascot or illustration. POST JSON {description, type?, style?, aspect_ratio?}. type is icon, logo, mascot or illustration (default icon; only icon gets app-icon framing and mask safe margins). style is flat, metallic, 2d-game, clay, 3d, gradient or glassmorphism. aspect_ratio is 1:1, 4:3 or 16:9. Returns image_key and preview_url. No account required.

Current U.S. nuclear power outage levels, updated daily: nationwide total generating capacity, megawatts offline, and percent outage. Aggregate figure for the whole U.S. reactor fleet, not broken out by individual plant or reactor. Sourced from the U.S. Nuclear Regulatory Commission via EIA.

UGC product video: 5s 9:16 for TikTok, casual, rendered by seedance-1.5-pro

Complete parcel intelligence: owner, situs, assessed value, classification, property tax and tax-sale (delinquency) status, full sale history and deeds, census tract, CDBG low/mod status, and every qualifying funding program with its cited rule.

The full record for one of the 1,326 specific Texas Hold'em starting hands: equity against modelled ranges, position-by-position opening guidance, exact head-to-head figures, and the exact card-removal effect of holding these specific two cards.

Live streaming speech-to-text for voice agents: buy a prepaid session, stream mic or call audio over WebSocket, get partial transcripts as the speaker talks. No account, no API key, no per-minute minimum — flat USDC on Base. Multilingual with mid-sentence code-switching. This SKU: 5 minutes connected time at $0.06 flat.