All projects on Base matching “inference”

OpenAI-compatible LLM inference and chat completions via discounted Venice API credits. Pay USDC to receive a live Venice.ai API key for /api/v1 models, chat, images, audio, video, and embeddings. Same-Day credits are 30–90% below Venice direct and expire at 23:59 UTC; Prepaid API Keys support recurring agent jobs.

Text-to-speech (OpenAI-compatible /v1/audio/speech). 4,358 voices across 9 providers (KokoroTTS, AWS Polly, Azure, MiniMax, more — free catalog at GET /v1/audio/voices). Returns mp3. Up to 3000 chars. $0.000006 USDC per character (Telnyx list rate, zero margin): pay per character via the upto scheme (min $0.002 network settlement floor, so ≤333-char calls settle at $0.002), or flat $0.018 exact.

Normalize an agent payload to a PHION service schema without changing payment-critical values; return a signed repair receipt

Fix broken JSON (trailing commas, single quotes, unquoted keys). Returns only valid JSON.

Return one current Coinbase spot-product snapshot for an exact BASE-QUOTE product id, including venue price, 24-hour price change and provider-reported 24-hour product volume. Forest reads only Coinbase Advanced Trade public market data; it does not infer tickers, infer the provider volume denomination, aggregate venues, read an account or wallet, place orders, provide an executable quote, forecas

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.

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...

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

Purpose-bound Adobe Fonts (Typekit) observation (fonts) using the existing fresh Stack-Monitor. Returns stack_adobe_fonts_decision, direct versus inferred status, evidence, optional version difference against a caller-owned baseline and reusable snapshot. Missing fingerprints do not prove absence. No background scheduling, CVE, compatibility or installed-extension inventory. Existing outbound safe

Claude pricing table: what every Claude model costs per token right now — Claude 5, Claude Opus, Claude Sonnet, Claude Haiku — from Anthropic and every provider that resells or hosts them (Bedrock, Azure, Vertex, OpenRouter, Fireworks). Input, output, cache and batch USD per 1M tokens, sorted cheapest first, so you can compare Claude inference cost across hosts and pick the cheapest place to run o

LLM chat completion in ONE call (Llama 3.1 8B via Cloudflare Workers AI): POST {messages:[{role,content}]} or {prompt:'...'} — per-call AI inference, zero signup, zero API keys

DeepSeek V4 Flash Chat API (deepseek/deepseek-chat): LLM inference via OpenAI-compatible chat completions, pay per call in USDC on Base with x402. No API key, no account. Suited for AI agents and scripts that need DeepSeek V4 Flash Chat on demand. When listed, this request cost 30% less than the same request on BlockRun. Streaming and function calling supported. Exact price in the 402 quote before

Accessible transport place allocation audit on the actual proposed delivery routes. Sum declared wheelchair_places across all jobs of each active route and compare with vehicle wheelchair_places. No pickup occupancy or certification inferred. Uses the paid-qualified existing VRP planner unchanged, then checks this business rule against the actual proposed route. A rule violation yields dispatch_re

Repair one x402 route's Bazaar discovery metadata in one call. Send a resource URL and one real sample output; get the defect report plus a complete discovery package — full output schema inferred from the sample, a sub-500-char description with a use-when sentence, OpenAPI and well-known snippets, paste-in instructions — that ships only after passing both x402 SDK validators. Use this when your l

Verified inference (Prova). OpenAI-compatible chat completions run inside a TEE (NVIDIA + Intel), hardware-attested, and anchored on Solana — every response returns an on-chain proof + Solscan link. Select a model via the body `model` field; price varies by tier (standard/premium/flagship).

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

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Deepent Research — refusal-free LLM inference (per-request)

Quick pre-flight quality score: composite (0-100) + grade (A-F) + three framework sub-scores (PEEM, RAGAS, G-Eval) + verdict. Run upstream of any other paid call to filter weak prompts before inference. The cheapest gate on the AI input quality problem.

Given a Portuguese company NIF/NIPC, return official Portugal 2030 EU-funded project facts and evidence-based inferred investment and purchasing categories for company intelligence, sales research and procurement opportunity screening. Includes funding, rule-based confidence, provenance, snapshot freshness and a conservative commercial-opportunity assessment. Not confirmed purchase intent, open te

Parse JSON or profile a JSON value. Returns canonical JSON, a SHA-256 fingerprint, structural metrics, and an inferred shape.

agentic.no inference: OpenAI-compatible audio transcription (POST /v1/audio/transcriptions)

$0.01 USDC required (x402 / Base or Solana) Paid 0.01 USDC, and only when there is something to deliver. Changes recorded across every member of a named set (inference or devtools) after your since cursor, newest first, each with the slug, detection time, source page and the same change object the per-slug endpoint returns. An empty window is answered free (charged false) and never reaches this p

Neural and keyword web search. Optional category filter: company, research paper, news, pdf, github, tweet, personal site, linkedin profile, financial report.

Anthropic Messages compatible 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.

Breached password check: is this password in known data breaches, and how often? Send only the SHA-1 hash (never the password); just the first 5 characters reach Have I Been Pwned (k-anonymity). Up to 50 hashes per call.

Use when you need a wallet portfolio value in USD, a wallet net worth or token balances with USD value for a 0x address. Do not use for solana wallets, transaction history, NFTs, DeFi positions or long-tail tokens. Returns JSON with a wallet's USD value on Ethereum and Base in one call: native and major-token balances priced on-chain from Uniswap v3 pools on Base, per-chain totals and the tokens l

OpenAI-compatible chat completion on 22 models: name one in `model` (meta-llama/Meta-Llama-3.1-8B-Instruct, deepseek-ai/DeepSeek-V4-Flash, openai/gpt-oss-120b, deepseek-v4-flash, openai-gpt-oss-120b, meta-llama/Llama-3.3-70B-Instruct and 15 more) and the 402 prices that model per request; served by DeepInfra, Venice AI, NEAR AI Cloud and Taifoon's own GPU (nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 whe

Routes requests across open-weight models using task fit, tool calling, vision, JSON format, context, output capacity, provider availability, and price. Send POST application/json with model set to ai-open-models/auto and a non-empty messages array. task_type is optional; when omitted, Auto classifies the request. Supports function tools, JSON responses, and mixed text/image messages using public

Linkrra Synap: Google Gemma 4 26B A4B Instruct (model "gemma-4-26b-a4b-it") - fast general model, long context. OpenAI-compatible chat completions for this one model, 128K context, served only on dedicated GPUs we operate, 4-bit AWQ. Pay per call in USDC on Base via x402 - no account, no API key. From $0.001 per call, usage-priced per token above that (GET /v1/models). Streaming supported. Product