AI models & inference

Text-to-speech with speed (0.7x-2.0x) and quality-step (1-100) control, 1 of 10 standard voices across 31 languages, for 501-2000 characters, returned as WAV audio. Use it to: pace a longer narration like a podcast intro, read a multi-paragraph script at a chosen speed, produce a slow deliberate reading of instructions, voice an extended alert or briefing. USDC on Base via x402.

Notarize AI output in bulk: one signed Ed25519 attestation of the model response per record for up to 20 AI inferences in a single call — same content hash, receipt token, and anchor status as single notarization, giving you a cryptographic receipt for inference across an entire audit-trail pipeline.

OpenAI-compatible chat completions backed by DeepSeek (GET probe variant). Answers open-ended questions and returns reasoned analysis.

Pay-per-joke vending machine: send USDC, get a fresh Claude-generated joke. Optional "theme" picks the topic.

GPU/Compute — run AI model inference via Replicate (image, video, LLM, audio, utility).

EU VAT validation via official VIES. $0.01 USDC.

Text-to-speech API: convert up to 2000 characters into natural speech (WAV, base64) using our locally-hosted neural speech engine — no API keys, pay per call with USDC. Choose voices F1-F5/M1-M5. Use for voice agents, notifications, audio content, and IVR. Text never stored. Full 20-voice / 31-language tiered product at voice.forgemesh.io.

Bounded low-cost inference with a signed delivery receipt

AI chat completions via 200+ models.

Locus public pay-per-use API

Locus public pay-per-use API

Bazaar Ping (discovery test) ($0.05 USDC on Base, Polygon, Arbitrum, or Avalanche via x402). Discovery test purchase. One cosmic wallpaper JPG (16:9), instant download. Music made with Suno — disclosed. Automatic fulfillment after settlement. Pay to 0xa98e8c6cbc64b7bb30fd0d2015ab24814c661839.

One paid call on kyp-model.ai for $0.01 USDC: the surface's own statement of record (a market node: its list_nodes line; a product: its record of record; allooloo.io: the estate scale block), public-record only, with an EdDSA-signed receipt that resolves forever at https://kyp-model.ai/x402/receipt/{nonce}. Doctrine: https://agentic-x402.ai/.

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

Private pay-per-call LLM inference for autonomous agents. Prompts run on our own GPU (house Qwen3 brain, resident model qwen3-14b); settled in USDC on Base L2.

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

One riddle by difficulty, in English or Spanish, with the answer AND the SHA-256 of the answer in lowercase. The hash is the point: an agent can check whether its guess is right without reading the solution first, which no other riddle endpoint lets you do.

Transcribes any video URL to text with Whisper v3 large. Auto-detects 90+ languages and offers a translate-to-English mode. 60-min / 500MB max. Same backend as video-to-text under a clearer slug. Use it for video transcription, video to audio transcription, or video-to-text. For speaker labels, use the speaker-diarize endpoint.

gpt-4.1: OpenAI GPT 4.1 chat completions, paid per call in USDC. Per 1M tokens in/out: Standard (default) 2.0/8.0, Fast 3.5/14.0; pick with service_tier. Plus $0.0005 (Base) or $0.0005 (Solana) per call; the quote charges input plus 10% of max_tokens. Empty answers are free. Rates: https://openai.mm.family/x402/pricing

Edits an image you provide instead of generating one from scratch: pass the image and a black-and-white mask, and Stable Diffusion inpainting repaints only the white area following your prompt. Image and mask go as https URLs or as base64, up to 10 MB each. Returns a hosted image URL valid for 24 hours. You are only charged if the edit is delivered. No API key, no account.

Check agent outputs for quality issues, inconsistency, and behavioral drift.

Send a supplier profile (what you do, keywords, regions, value band, certifications) and get the best-fitting live UK tenders, each scored 0-100 by deterministic published rules across five factors - relevance, value fit, geography, timeline, buyer history - each with its numerator AND denominator so you can re-weight client-side, plus a what-to-emphasise note on the top matches. Rules score; a model never does.

Validate a JSON value against a JSON Schema and coerce common LLM-output mistakes (numbers as strings, stringified booleans, scalars where arrays are expected, missing defaults, extra properties). Returns the coerced value plus a structured error report. Built for cleaning up LLM tool-call arguments and structured outputs. POST a JSON body like: {"schema":{"type":"object","required":["name","age"],"properties":{"name":{"type":"string"},"age":{"type":"integer"}}},"data":{"name":"Ada","age":"36"}}

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.

Turn a full recording into a structured document: POST JSON with an audio_url — up to 2 HOURS of meeting, interview, hearing, or podcast audio — and get a diarized who-said-what transcript JSON: timestamps, speaker tracking with per-segment confidence, language codes. Most transcription APIs cap at ~20 minutes; this one runs Gemini long-context, built for the long ones. mp3, wav, m4a, ogg, webm, flac. Flat price, USDC on Base, no account.

Transcribe short audio fast: POST JSON with an audio_url (voicemail, call recording, voice memo, podcast clip — up to 15 min) and get Gemini-powered transcript JSON back with speaker-labeled, timestamped segments — any spoken language, auto-detected and labeled per segment. Handles mp3, wav, m4a, ogg, webm, flac. $0.10 flat in USDC on Base — no account, no API key. For hour-long meetings use /routes/x402/transcribe-long.

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: 30 minutes connected time at $0.36 flat.

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: 15 minutes connected time at $0.18 flat.

Request-priced LLM inference · 0% service fee launch promotion