AI models & inference

Divides each available substrate mass by its required mass per product mass, selects the limiting substrate, and applies a caller-supplied process efficiency. It does not model yeast metabolism, kinetics, oxygen transfer, toxicity, regulation or actual fermentation performance.

Goal and task planning MCP for Codex and AI agents, with evidence-backed completion.

AI image + video generation for agents: --flag prompt DSL, async generate/poll, x402 pay-per-use.

Search the SiteGPT documentation: setup, features, API reference, troubleshooting.

Plan AI video shots: model picks, sourced prompts, prompting guides and real $/s costs.

Multi-model chat completions. POST messages[] and set model to any LLM id from GET /v1/models; dynamic USDC pricing scales with model and token usage. Hero: GET /heroes/chat-completions.

Generate or edit images, video, music, and speech via fal.ai. Pass `model` (one of the registered keys) plus the model-specific params (prompt, image_url, aspect_ratio, duration, text, etc.).

Get OpenAI-compatible inference from many models at market prices via Surplus Intelligence.

Premium text-to-speech with ElevenLabs — ultra-realistic voices, multilingual support, custom voice IDs

Text-to-image generation on Venice models (Flux, SD3.5, GPT-Image, HunyuanImage, and more), paid per request in USDC on Base via x402, no API key. Resolve a model id from GET /api/v1/models?type=image and an optional style from GET /api/v1/image/styles.

Notarize AI output: a signed Ed25519 attestation of the model response plus sha256 content hash, receipt token, and Merkle anchor status for one AI inference — a cryptographic receipt for inference that lets you prove an AI said X and verify model output authenticity, checkable free by anyone, anytime.

Official $0.01 proof-of-life resource for SpendTheBits x402: returns a JSON heartbeat. Pay it to verify your agent's x402 client end to end.

OpenAPI Changelog Generator: Diff two OpenAPI specs and generate a structured breaking-change changelog (no LLM — deterministic diff). Provide base_spec_url and new_spec. Pay per call in USDC on Base via x402 — POST https://x402.freeq.one/tools/changelog_openapi.

Repariert die typischen Fehler aus Sprachmodell-Ausgaben und Fremdsystemen: Markdown-Zaun, haengende Kommas, einfache Anfuehrungszeichen, unquotierte Schluessel, Kommentare, typografische Anfuehrungszeichen, unsichtbare Zeichen, fehlende Klammern, NaN und Infinity. Liefert das geparste Objekt und ein Protokoll jeder einzelnen Reparatur.

One curious but true fact, in English or Spanish, filtered by topic: science, computing, history or nature. Takes parameters, returns an id so you can avoid repeats across a session, and accepts a seed for a reproducible answer.

Shuffle a list into a uniformly random order with Fisher-Yates over the platform CSPRNG. Every permutation is equally likely, which sorting by a random key does not give you.

The current time in any IANA time zone, in every form an agent needs at once: ISO with offset, 24-hour, 12-hour, weekday, unix timestamp and UTC. It also says whether daylight saving is active right now and what the zone's standard offset is, so a shifted clock can be told apart from a permanent one.

Use when an agent needs chat completion. Returns One bounded chat completion (standard messages request shape) per paid call, with no account to open and no provider key to hold; max 24,000 input characters and 600 output tokens. $0.01.

LLM inference proxy (Pro tier) - GPT-4o or GPT-4.1. Supports vision (up to 2 image URLs) and structured output (response_format: json_object or json_schema). No API key needed; pay per call via x402. Input capped at 16k chars, output at 2048 tokens.

Moderate text content using Claude Haiku — flags categories like harassment, hate, sexual content, violence, self-harm, and spam with per-category severity and an overall allow/flag/block recommendation, so agents can screen user-generated content before publishing or storing it.

OpenAI-compatible text embeddings API (alias of /v1/embeddings for api/v1-style base URLs) — input as a string or batch of up to 128 strings, model text-embedding-3-small (default) or text-embedding-3-large. Flat $0.005 per call in USDC via x402, no OpenAI account or API key.

Call OpenAI's gpt-4.1-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5.4-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Call OpenAI's gpt-5-nano via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

OpenAI-compatible text embeddings API — standard /v1/embeddings request shape: input as a string or a batch of up to 128 strings (64000 chars total on text-embedding-3-small, the default; 24000 on text-embedding-3-large). Flat $0.005 per call in USDC via x402, no OpenAI account or API key. Returns float vectors for RAG, semantic search, clustering, and dedup.

Call OpenAI's gpt-4o-mini via a single pay-per-call x402 endpoint — no OpenAI account or API key needed, pay $0.005 per request in USDC. Standard OpenAI chat.completions request/response shape, capped input and output.

Multilingual text embeddings (384-dim) served in-house, no OpenAI dependency, no API key. NetIntel's cheapest embeddings at $0.001/call, batches up to 256 texts. Supports query/passage input types for retrieval (e5). Pairs with /text/chunk for a full chunk→embed RAG pipeline on one provider.

Split text into overlapping chunks for RAG ingestion — by characters or words, with configurable chunk size and overlap. Deterministic (same input → same chunks), returns each chunk with its index and start/end offsets. No API key, no LLM. Pairs with /v1/embeddings for a full chunk→embed pipeline.

Fetch historical orderbook snapshots for a Kalshi market

Get raw book ticker data at microsecond granularity