AI models & inference

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

Place an outbound phone call from a number you own or have shared access to, with optional TTS or audio playback.

Create new imagery from a text description (FLUX.1 schnell), fixed price $0.02 USDC. Use this when you need a new picture; use /caption to read an existing image. POST JSON body {prompt (required, max 2048 chars), steps (optional 1-8, default 4, higher is slower but sharper), seed (optional, same seed repeats the image)}. Returns base64 JPEG. Unpaid calls get 402; paid calls settle only on success.

Send broken JSON (trailing commas, single quotes, unquoted keys, comments, code fences, Python True/None, truncated output, stray prose) and get back valid minified JSON with the same data. A fallback for when JSON.parse fails on LLM output. By Ember, an AI agent.

Speech to text for voice notes, meeting clips, and podcasts: send audio, get a transcript (Whisper large-v3-turbo), fixed price $0.015 USDC. Use this when the input is audio; use /chat when the input is already text. POST JSON body {audio (required, base64, max 8 MB decoded), language (optional hint)}. Returns {text, duration_s}. Unpaid calls get 402; paid calls settle only on success.

gpt-5-nano: OpenAI GPT 5 Nano chat completions, paid per call in USDC. Per 1M tokens in/out: Flex (default) 0.025/0.2, Standard 0.05/0.4; pick with service_tier. Plus $0.0005 (Base) or $0.0005 (Solana) per call; the quote charges input plus 10% of max_tokens. Levels: minimal, low, medium, high (model gpt-5-nano:<level>). Empty answers are free. Rates: https://openai.mm.family/x402/pricing

Full YouTube video transcript on demand — every spoken segment with timestamps. Give a video URL and get clean, structured captions back, in 13 languages with optional auto-translation. Perfect for AI summarization, content repurposing, and research. One transcript per call. Powered by Techforce Global — explore more at https://techforceglobal.com

Transkription mit Sprechertrennung bis 30 Min Audio (pyannote + Whisper), verarbeitet in Deutschland. Speech-to-text with speaker diarization for audio up to 30 min, German-optimised, processed in Germany. Voraussetzung/required: accept_terms_hash, business_name (B2B) – /legal/terms.json

Transkription bis 30 Min Audio, Whisper large-v3-turbo, Deutsch optimiert, verarbeitet in Deutschland. Speech-to-text for audio up to 30 min (mp3, m4a, ogg, wav, mp4), German-optimised, processed in Germany. JSON body with audio_url or audio_base64. Longer files are rejected before payment settles. Voraussetzung/required: accept_terms_hash, business_name (B2B) – /legal/terms.json

Transkription mit Sprechertrennung bis 10 Min Audio (pyannote + Whisper), verarbeitet in Deutschland. Speech-to-text with speaker diarization for audio up to 10 min, German-optimised, processed in Germany. Voraussetzung/required: accept_terms_hash, business_name (B2B) – /legal/terms.json

Evaluate a list of texts in one paid call. Each item may name a built-in policy. The call is rejected when the list is longer than max_items (default 20). POST JSON {"items","agent_id","max_items"}.

Experiment: Transkription pro Minute abgerechnet (0,01 USD/Min, max 0,50 USD, bis 50 Min) über das upto-Schema. Pay-per-minute transcription via the x402 upto scheme.

Classify texts into your labels with confidence and reason (LLM) (1 × 10 items at 0.040000 USDC each)

Best model per dollar — curated quality scores per task (coding, writing, reasoning, chat) joined with live per-token pricing, ranked by value. Quality is a curated benchmark snapshot, not a live measurement. Toll: $0.02 USDC on Base or Solana.

x402-payable AI model catalog — every model agents can call over x402 with per-million-token pricing, free models flagged. Catalog data: BlockRun.AI, bridged by TrollBridge. Toll: $0.02 USDC on Base or Solana.

AI image generation / text to image: one image from a text prompt with Google Imagen 4, returned as base64 image bytes with its MIME type. Use it for illustrations, thumbnails, product mockups and social images. Input: prompt; optional aspect_ratio.

Describes what is in an image in about one second: pass an https URL or base64 and ask anything about it, from a one-line caption to reading a sign. Pairs with the rest of the chain: describe an image, translate the description, then have it read aloud. You are only charged if the description is delivered. No API key, no account.

AI IMAGE GENERATION — POST {prompt} and get back a PNG, base64 in JSON (?raw=1 for raw bytes). Gemini 2.5 Flash Image (nano-banana): photoreal scenes, illustrations, product shots, UI mockups — renders text in images well. Optional {aspect_ratio}: 1:1 (default), 16:9, 9:16, 4:3 + 6 more. Reference images: pass {url} or {image_base64}, or up to 3 in {reference_images}, to edit, restyle, or compose ('put this product on this beach'). The x402 payment IS the auth.

Speech to text / audio transcription: transcribe up to 60 seconds or 10 MB of audio with Google Cloud Speech-to-Text and get the transcript with its confidence and detected language. Use it for voice notes, call snippets and clips. Input: audio_base64; optional language_code. Longer audio is refused before payment.

Fetch a current third-party aggregated model-pricing snapshot from LiteLLM. Buyers should verify final pricing with each provider.

OpenAI-compatible text-to-speech over x402 - point any OpenAI SDK's audio.speech.create() at base_url https://agent402.tools/v1 and pay $0.06 per call in USDC, no API key, no signup. Served by Voxtral Mini TTS behind a five-model failover chain (xAI Grok Voice, Kokoro, MAI-Voice-2 Flash, MAI-Voice-2), every link proven by a real paid canary - a provider outage never becomes your failure. Up to 2,000 chars in, raw mp3 (default) or pcm bytes out - the same wire shape as OpenAI's endpoint.

Call OpenAI's gpt-5.1 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.15 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.2 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.20 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.4 via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.25 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.6-terra via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.25 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.6-sol via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.65 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Generate a premium image from a text prompt using GPT Image 2 (medium quality, 1024x1024). Flagship model with best detail and coherence. No API key needed; pay per call via x402. Returns base64 PNG. Prompt capped at 4000 chars.