← All headings
AI models & inference
1,006 listings from 519 providers, 774 answering · counted
Filed by addrbook from the words in each listing, so a heading says what a listing claims to be for.
Showing 51–75, one row per provider, those answering first · names and descriptions as their source publishes them
- ai.agentapigate/github-huggingface-arxiv-papers-repos-search-api-mcpagentapigate.aiGitHub trending repos, HuggingFace trending AI models & arXiv academic paper search remote MCP API.Livechecked Evidence 3/4MCPWebsiteMCP Registry1 more from agentapigate.ai
- Pay With Promptcom.paywithprompt/pay-with-prompt · paywithprompt.comAgents answer prompts for credits, then spend one-time merchant vouchers.Livechecked Evidence 3/4MCPWebsiteMCP Registry
- Rota Nacionalbr.ia.rota-nacional/rota-nacional · rota-nacional.ia.brAI API compatible with OpenAI and Anthropic, with personal data handled before the model.Livechecked Evidence 3/4MCPWebsiteMCP Registry
- BlockRun.AIblockrun.aiAI chat completions API - pay per request with USDC on BaseLivechecked Evidence 2/4x402x402 Bazaar284 payers5 more from blockrun.ai
- Token countagent402.toolsCount exact LLM tokens for a string using the real OpenAI BPE (o200k_base for gpt-4o/o-series, cl100k_base for gpt-4/gpt-3.5). Deterministic, offline - budget context windows without calling a model.Livechecked Evidence 2/4x402x402 Bazaar2 payers26 more from agent402.tools
- DeepSeek V4.1 Flash chatx402.telnyx.comChat completions via Telnyx Inference (deepseek-ai/DeepSeek-V4.1-Flash-1017). OpenAI-compatible. Up to $0.013389 USDC per call, quoted to your request (input + max_tokens at list rates, no markup).Livechecked Evidence 2/4x402x402 Bazaar53 payers26 more from telnyx.com
- CheapTokens AI Inferencecheaptokens.aiOpenAI-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.Livechecked Evidence 2/4x402x402 Bazaar28 payers
- Gondolaapi.gondola-ai.comOpenAI-compatible image generation 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. Each request is priced by its model and size, so a listed amount is one recent request, not a fixed price. Model ids and live prices: GET https://api.gondola-ai.com/v1/models.Livechecked Evidence 2/4x402x402 Bazaar26 payers1 more from gondola-ai.com
- Chit402api.chit402.comSigned spend receipts for agent x402 payments — who paid which call, verifiable by a third party. Treasury desk and possession book for agent spend — export, policy, evidence. POST /v1/chat/completions is the x402 USDC door on Base and Solana. Returns signed receipt + public verify_url. Paying this host is real mainnet USDC.Livechecked Evidence 2/4x402x402 Bazaar16 payers
- SingIt LLM Chat - spend limitsask.singitai.appLLM chat completions API for Claude, GPT, Gemini, DeepSeek and Kimi. Pay in USDC on Base or Solana. Owner-set spend limits via MCP/API keys.Livechecked Evidence 2/4x402x402 Bazaar15 payers44 more from singitai.app
- notary.forgemesh.io/api/notarizenotary.forgemesh.ioNotarize AI output: POST a prompt, the model response and model_id; get back a signed Ed25519 attestation with attestation_id, sha256 content_hash, signature, signer_pubkey, a private receipt_token, receipt_url and Merkle anchor status. A cryptographic receipt for one AI inference that proves an AI said X; anyone can verify it free at /api/verify. The prompt and response are hashed, not stored.Livechecked Evidence 2/4x402x402 Bazaar13 payers2 more from forgemesh.io
- Chat completions (LLM inference)coord.taifoon.devOpenAI-compatible chat completion on 76 models: name one in `model` (l3-8b-lunaris-v1, llama-3.1-8b-instruct, mistral-small-24b-instruct-2501, gemma-3-4b-it, gpt-oss-20b, phi-4, qwen2.5-7b-instruct, gemma-3-12b-it, qwen3.5-9b, gemma-3-27b-it, ling-3.0-flash and 64 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 when no model is named). Messages in, the answer and its token usage out; ma…Livechecked Evidence 2/4x402x402 Bazaar12 payers65 more from taifoon.dev
- x402.onhub.ai/v1/chat/completionsx402.onhub.aiText completion using the model selected in the request body.Livechecked Evidence 2/4x402x402 Bazaar11 payers2 more from onhub.ai
- OpenCheapapi.opencheap.siOpenAI-compatible chat completions for hundreds of open and closed models (DeepSeek, Kimi, GLM, Qwen, Llama, Claude, GPT, Gemini) through one endpoint, each call routed to the cheapest healthy provider for that model. Pay per call in USDC on Base with no API key or account: the 402 quotes this prompt plus max_tokens (up to 4,096). Streaming and tool calls supported. Model ids and prices: https://app.opencheap.si/api/v1/modelsLivechecked Evidence 2/4x402x402 Bazaar11 payers
- SiteCheckapi.sitecheck-api.workers.devMultilingual text embeddings (BGE-M3, 1024 dimensions) for up to 100 texts per call. For search, RAG and clustering.Livechecked Evidence 2/4x402x402 Bazaar10 payers1 more from sitecheck-api.workers.dev
- AI Pricing Hubio.github.gishh/aipricinghub · aipricinghub.comSource-backed AI model pricing, rankings, history, and benchmark data.Livechecked Evidence 2/4MCPWebsiteMCP Registry
- io.github.mikerawsonnz/authenticated-mcp-agentbcrypt-langchain-core-mcp-25b8f1.getvda.aiJWT-gated LLM gateway: authenticate (bcrypt/JWT), then run a LangChain-on-Vertex Gemini completion.Livechecked Evidence 2/4MCPWebsiteMCP Registry5 more from getvda.ai
- ATOM Pricing Intelligenceio.github.A7OM-AI/atom-mcp-server · a7om.comThe Global Price Benchmark for AI Inference. 1,600+ SKUs, 40+ vendors, 14 price indexes.Livechecked Evidence 2/4MCPWebsiteMCP Registry
- Local Model Suitability MCPio.github.OjasKord/local-model-suitability-mcp · kordagencies.comCheck if a task runs locally vs cloud. Save money on calls that don't need cloud inference.Livechecked Evidence 2/4MCPWebsiteMCP Registry
- CoverCraft AI by Ambuj Kumar Tripathiio.github.Ambuj123-lab/covercraft-mcp · career-workspace-ambujsystems.vercel.appLive Hugging Face model proofing, ATS resume scoring and career tools by Ambuj Kumar TripathiLivechecked Evidence 2/4MCPWebsiteMCP Registry
- Agent Data Tools: AIio.github.Nutshell2000/agent-data-tools-ai · agent-data-tools.revmesh2074.workers.dev33 tools: LLM chat, summaries, translation, embeddings, speech, images. 25 free calls.Livechecked Evidence 2/4MCPWebsiteMCP Registry22 more from revmesh2074.workers.dev
- ia-skills: prompts y skills de IA en españolio.github.ericrodri/ia-skills · ia-skills.comBusca y lee miles de prompts y skills de IA en español, por profesión. Remoto o local.Livechecked Evidence 2/4MCPWebsiteMCP Registry
- IDLE Protocolcom.earnidle/mcp · earnidle.comWeb scraping, inference, DNS, monitoring from residential IPs — pay per request in USDCLivechecked Evidence 2/3WebsiteMCP Registry
- OpenAI Billingio.github.mcp-dir/openai_billing-mcp · api.mcp.aiOpenAI organization usage and cost reporting through an admin API key connected by the user.Livechecked Evidence 2/4MCPMCP Registry1 more from mcp.ai
- Land the Labcom.landthelab/interview-prep · landthelab.comPrep for OpenAI, Anthropic and top AI lab interviews: real loops, asked questions, worked answers.Live, sign-in requiredchecked Evidence 2/3MCPWebsiteMCP Registry