← All headings
AI models & inference
998 listings from 488 providers, 782 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 151–175, one row per provider, those answering first · names and descriptions as their source publishes them
- Text Embeddings and Rerankagentsvc.ioSentence embeddings (all-MiniLM-L6-v2, 384 dimensions, L2-normalized, multilingual input works best in English) for semantic search, clustering and deduplication, or rerank mode: pass query + documents to get documents sorted by cosine similarity. Runs locally, texts are not stored. Params: texts (1 to 32 strings, max 2000 chars each) for embed mode, or query + documents (up to 64) and top_k for rerank mode.Livechecked Evidence 1/4x402x402 Bazaar7 payers
- NetIntelnetintel.devMultilingual 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.Livechecked Evidence 1/4x402x402 Bazaar7 payers20 more from netintel.dev
- x402-v2-mint-context-condense.vercel.app/v1/context-condensex402-v2-mint-context-condense.vercel.appCondense text for token budgets: retained-fact list + dropped-content log + before/after token counts (OpenRouter free-first + approx counter). Audit loss.Livechecked Evidence 1/4x402x402 Bazaar7 payers
- offrouter.org/v1/chat/completionsoffrouter.orgPrivate, OpenAI-compatible chat completions. Every model (Kimi, DeepSeek, Qwen, GLM, gpt-oss and more) runs inside a confidential GPU enclave (Intel TDX + NVIDIA): prompts are encrypted in use, never cached or logged, and each answer carries a signed receipt. Suited to tasks with sensitive data. Priced per call from the input and max_tokens; the unused part is refunded. Model ids: GET /v1/models.Livechecked Evidence 1/4x402x402 Bazaar7 payers
- api.data4agents.dev/v1/latency/globalapi.data4agents.devLLM Gateway Data - Live Provider Latency, pay-per-call via x402Livechecked Evidence 1/4x402x402 Bazaar7 payers2 more from data4agents.dev
- dev-5090 uncensored inferencedev-5090-box.tailfb4c1f.ts.netText embeddings (768-dim). Send {"input": "text"} or {"input": ["a","b"]}.Livechecked Evidence 1/4x402x402 Bazaar7 payers23 more from tailfb4c1f.ts.net
- AI ASKx402-data-api.sigrunner.workers.devCheap LLM answer (Llama 3.2 3B on Workers AI) for a prompt up to 500 chars. Pay per call, no API key.Livechecked Evidence 1/4x402x402 Bazaar6 payers
- x402-v2-mint-sentiment-drift.vercel.app/v1/sentiment-driftx402-v2-mint-sentiment-drift.vercel.appTEXT-IN ONLY sentiment trajectory: per-item score, inflection points, drift magnitude + model version. Not a trading signal. No scrape / no X. OpenRouter free-first.Livechecked Evidence 1/4x402x402 Bazaar6 payers
- x402-v2-mint-similarity-dedupe.vercel.app/v1/similarity-dedupex402-v2-mint-similarity-dedupe.vercel.appLexical similarity suite: Levenshtein, Jaro-Winkler, Jaccard, SimHash Hamming + duplicate verdict. No embeddings.Livechecked Evidence 1/4x402x402 Bazaar6 payers
- modelprices.xyz/gpt-pricingmodelprices.xyzGPT pricing table: what every GPT model costs per token right now — GPT-5, GPT-5 mini, GPT-4o, GPT-4.1, o3 — from OpenAI 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 GPT inference cost across hosts and pick the cheapest place to run one. Normalized, cross-checked, refreshed hourly.Livechecked Evidence 1/4x402x402 Bazaar5 payers9 more from modelprices.xyz
- Annalistapi.annalist.devRetirement calendar for AI models across platforms: shutdown dates, 'not sooner than' floors, states and recommended replacements from the official Anthropic, OpenAI and Amazon Bedrock deprecation pages, plus Azure, Vertex, Gemini and others, recorded daily so moved dates show. The same model often retires on different dates on different platforms. One model with model=, or upcoming shutdowns. Signed.Livechecked Evidence 1/4x402x402 Bazaar4 payers1 more from annalist.dev
- KARP by SoulDriveragents.souldriver.com.auResearch cards from KARP, SoulDriver's multi-model research engine: GPT, Gemini, Grok and Claude debate a question and publish a conclusion. Each card: conclusion, key insight, warnings, dated figures, consensus, open questions, research date. Check your question first with the free POST /v1/coverage. Deepest on Alzheimer's, ageing biology, ancient scripts, AI governance, quantum computing. No wallet? Free research grant: POST /v1/grant. Usually 5-15 s.Livechecked Evidence 1/4x402x402 Bazaar4 payers1 more from souldriver.com.au
- Sift Web Toolssift.srv1996466.hstgr.cloudGenerate an image from a text prompt (PNG). Text-to-image with Google's Gemini image model. Aspect ratios 1:1, 3:2, 2:3, 3:4, 4:3, 4:5, 5:4, 9:16, 16:9, 21:9. Prompts refused by the model's safety filter are not charged.Livechecked Evidence 1/4x402x402 Bazaar4 payers
- GEDX402 Chatchat.gedx402.comOpenAI-compatible chat completions across many open models, paid per call in USDC with no API key. POST { model, messages, max_tokens? } and pick model from GET /v1/models (fast, smart, code, reasoning and 70B tiers, among others). The price is set from the model's rates and your request size, so short prompts on small models cost the least; the 402 shows the exact amount before you pay. Hero: GET /heroes/chat-completions.Livechecked Evidence 1/4x402x402 Bazaar4 payers1 more from gedx402.com
- fetchharbor.benlab.download/chatfetchharbor.benlab.downloadGenerate one bounded assistant response with the operator's self-hosted Ollama model. Use for short, single-message inference where local processing is preferred. Accepts up to 8,000 characters and returns the model name, response text, and token counts when Ollama supplies them.Livechecked Evidence 1/4x402x402 Bazaar4 payers
- Laminarity Relayapi.laminarity.ukOpenAI-compatible chat completion. Pay per request in USDC via x402: no signup, no API keys. Price scales with prompt size and max_tokens.Livechecked Evidence 1/4x402x402 Bazaar4 payers
- x402-v2-mint-moderation-brand-safety.vercel.app/v1/moderation-brand-safetyx402-v2-mint-moderation-brand-safety.vercel.appBrand-safety / moderation scores per category + offending spans + threshold pass/fail + model version. NOT a legal judgment. OpenRouter free-first (Detoxify too heavy for serverless).Livechecked Evidence 1/4x402x402 Bazaar4 payers
- agentdata-api.sander-van-aard.workers.dev/llm/chatagentdata-api.sander-van-aard.workers.devLLM chat completion per call — no account, no API key, no token math. Three flat-priced tiers: fast $0.002 (DeepSeek v4 Flash), smart $0.02 (GPT-5.4 mini), reasoning $0.03 (DeepSeek v4 Pro). Send OpenAI-style messages, get the assistant reply with finish_reason and token usage. Input capped per tier (16k-32k chars); the 402 quotes the exact tier price up front. Model or source unavailable means a 503 and you pay nothing. USDC on Base.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- HALOWERK creatorwerkcreator.halowerk.comCalculates cosine similarity between caller-supplied numeric embeddings and combines it with supplied spectral distance, pitch-contour correlation and timing distance using fixed weights. It processes no audio and cannot establish speaker identity, consent, cloning, authenticity or fraud.Livechecked Evidence 1/4x402x402 Bazaar3 payers18 more from halowerk.com
- masterclaw.dev/api/v1/chat/completionsmasterclaw.devOpenAI-compatible chat completions backed by DeepSeek (GET probe variant). Answers open-ended questions and returns reasoned analysis.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- x402.coinopai.com/api/searchx402.coinopai.comAutomation workflow search: keyword search over 819 ready-made agent automation prompts (Slack, Notion, CRM, email, GitHub and more). Pass q (required), optional limit (1-50) and offset. Returns JSON with results (slug, title, description, complexity, services) and total. A query with no match is answered 404 and not charged. Use the slug with /api/automation/{slug} to fetch the full executable prompt.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- pqs.onchainintel.net/api/pqs-gradepqs.onchainintel.netQuick 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.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- x402.orthogonal.com/baseten/v1/chat/completionsx402.orthogonal.comSend a conversation to a model and get a completion back. Works exactly like the OpenAI chat completions endpoint. Pass messages and a model slug, get a response with the assistant's reply. Supports streaming for real-time token delivery, tool calling for function execution, structured outputs via response_format, and controllable reasoning depth on supported models. | ERROR: Unable to calculate price.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- TenPrintrubric-protocol.comAttested 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.Livechecked Evidence 1/4x402x402 Bazaar3 payers
- LLM token counterapi.vextorium.comCount the tokens of a text with OpenAI tokenizers (o200k for GPT-4o/4.1/5, cl100k for GPT-4/3.5) plus estimates for Claude, Llama and Gemini, with characters per token. Budget LLM calls and split contexts.Livechecked Evidence 1/4x402x402 Bazaar3 payers1 more from vextorium.com