AI models & inference

Returns model health status and per-chain training stats (sequence count, last retrain time) — check before relying on sequence-anomaly scores for a given chain.

Currency rate conversion

Audio transcription API: transcribe any public audio URL (mp3, wav, m4a, ogg — up to 25MB / ~20 min) to text with a neural speech-recognition engine running locally on our hardware. Multilingual (~99 languages), auto language detection. Use as a speech-to-text step for voicemail, podcasts, meetings, and voice agents. Audio is processed in a sandbox and deleted immediately; we keep nothing.

Speech audio generator: reads any block of text aloud and returns the result as a downloadable WAV file, selectable across ten built-in voice presets. Pay-per-call with no subscription or stored text. Useful for narrating short-form content, generating spoken alerts, or producing sample audio for voice-agent testing.

OpenAI-compatible chat completions across the Venice AI model catalog. Pay per request in USDC on Base via x402, with no account and no API key. Overpayment is never lost: it banks as reusable wallet credit for your next call. Model ids and live prices: GET https://api.gondola-ai.com/v1/models.

Attested LLM inference: gpt-4o-mini chat completion plus a post-quantum signed, Hedera-anchored attestation binding the prompt hash, response hash, exact model version, and timestamp. Evidence of which model said what, when — for agents whose decisions may be questioned later.

Text embeddings for semantic search and RAG: one vector per call, 1024 dimensions.

Full transcript of a YouTube video from its URL — captions/subtitles as clean plain text in your language. YouTube transcript, video to text, captions extraction, subtitle download, speech to text, multilingual. 105 languages supported, including English, Spanish, Portuguese, French, German, Hindi, Arabic, Chinese, Japanese, Korean, Russian, Indonesian and Vietnamese. Pay per call, no account or API key.

Verifiable Random pick — string selection with or without replacement bound to a future drand round the server waits for (typically 3-6s) and verifies locally, with a reproducible proof transcript.

Detect AI-generated writing with a calibrated probability score. Returns a 0-1 likelihood, a verdict, suspicious phrases, and per-axis style signals (em-dash overuse, hedge phrases, formulaic transitions). Works as an AI content detector, GPT detector, or ChatGPT-text checker.

Privacy-first chat API: prompts run on a local open-weight model on dedicated hardware - your data is never forwarded to OpenAI/Anthropic or any third-party LLM cloud. OpenAI-compatible chat completions: summarize, draft, extract, translate, code, answer questions. Send a messages array, get chat.completion JSON. Pay per call in USDC on Base (x402), no API key or account. Tiers by output cap: quick 4,096 / long 8,192 / extended 32,768 tokens. Free trial: POST /v1/trial.

Privacy-first long-form inference: 8,192-token output cap on a local open-weight model on dedicated hardware - prompts never reach OpenAI/Anthropic or any third-party cloud. OpenAI-compatible chat completions (messages array in, chat.completion JSON out) for summarization, drafting, extraction, translation, code, multi-paragraph answers. Pay per call in USDC on Base (x402), no API key or account. Shorter work? Use the cheaper quick tier (4,096 tokens).

Structured evaluation with TypeSafe's Jev (System One) model. Send any state plus typed questions — noul (true/false), choice (pick one), or score (ordinal scale) — and get back calibrated probabilities and confidence for each. Built for routing, classification, triage and policy checks where a fast, predictable, machine-readable answer beats prose.

Text-to-speech with speed (0.7x-2.0x) and quality-step (1-100) control, 1 of 10 standard voices across 31 languages, up to 500 characters, returned as WAV audio. Use it to: speak an urgent alert faster, slow a reading for clarity, tune synthesis quality against latency, produce a paced voice cue for a UI, generate a rushed or calm-toned notification. USDC on Base via x402, no API key.

Translates text between about 100 languages with Meta M2M100 1.2B: pass the text and the target language (ISO code like es, fr, de, zh, ja, or its English name); the source language is detected if omitted. Long texts are split by sentence, so paragraphs keep their order and line breaks. Up to 2000 characters per call. Pairs with speech-to-text: translate a transcript, then read it aloud. You are only charged if the translation is delivered. No API key, no account.

List AI models.

Locus public pay-per-use API

run any ai model. compose agents, stack knowledge, connect tools. one api, pay per run.

Latest versions, LTS windows, and EOL dates for 300+ products. Fresh ground truth for stale models.

44 MCP tools to search, value, register, trade, and manage ENS names. AI-powered intelligence layer.

Give Claude only the Google Drive files you choose. Every action logged.

Find & cut horizontal and vertical video clips (Shorts/Reels), transcribe & summarize. Pay per job.

Public Cannon Studio MCP for product, pricing, workflow, model, and API answers.

MCP-native notes and memory for ChatGPT, Claude, and other AI tools.

Send a one-off fax from inside ChatGPT or Claude. Pay-per-use, $2-$4.50 per delivered fax.

Robert Blust: One model, true everywhere

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.

B2Bware MCP server — access products, orders and customers from Cursor, Claude, Windsurf and more.

Build, test, monitor & improve AI with Future AGI via Claude, Cursor, Windsurf & more.

AI-powered hiring for recruiters & candidates - video interviews, transcripts, scores, profiles.