AI agents can now pay for API calls autonomously. This directory tracks which developer services accept payments via x402 (HTTP 402 protocol) and Stripe MPP (Machine Payments Protocol) — the two leading standards for machine-to-machine payments.
x402 uses the HTTP 402 “Payment Required” status code to enable pay-per-call API access. When an agent hits a 402 response, it reads the payment requirements from the response headers, completes the payment (typically via stablecoin on Base), and retries the request with proof of payment. No accounts or API keys needed — just a wallet. Founded by Coinbase with backing from Stripe, Cloudflare, Shopify, Visa, and Mastercard.
Stripe’s Machine Payments Protocol (MPP) extends Stripe’s payment infrastructure for agent-to-service transactions. MPP adds agent identity verification, configurable spending limits, budget controls, and full audit trails. Built on familiar Stripe APIs, making adoption straightforward for services already using Stripe for billing. Agents pay with Stripe-managed wallets rather than crypto.
| Feature | x402 | Stripe MPP |
|---|---|---|
| Backed by | Linux Foundation (Coinbase) | Stripe |
| Launched | April 2026 | March 2026 |
| Payment method | USDC stablecoin on Base | Stablecoin + fiat (cards, BNPL) |
| Account required | No — wallet only | Stripe-managed wallet |
| Integration effort | HTTP 402 handler + wallet | Stripe SDK integration |
| Budget controls | Wallet balance limits | Configurable per-agent spending limits |
| Audit trail | On-chain (Base L2) | Stripe dashboard + API |
| Best for | Instant access, no accounts | Fiat support, Stripe ecosystem |
54 developer services accepting autonomous agent payments. 53 via x402, 10 via Stripe MPP, 9 supporting both.
| Service | Category | Protocol(s) | Free Tier | Details |
|---|---|---|---|---|
| Vercel | Cloud Hosting | x402 Stripe MPP | Hobby | Hobby plan with 100 GB/month Fast Data Transfer, 1M function invocations, 4 hrs Active CPU, 360 GB-hrs Provisioned Memor |
| Render | Cloud Hosting | x402 Stripe MPP | Hobby | Free web services (512 MB RAM, 0.1 CPU), free PostgreSQL (256 MB RAM, 30-day expiry), free Redis (25 MB) |
| Cloudflare Workers | Cloud Hosting | x402 | Free | Edge compute with 100K requests/day, 10ms CPU time per invocation |
| Cloudflare Pages | Cloud Hosting | x402 | Free | Up to 100 sites (soft limit), unlimited bandwidth, 500 builds/month, 100 custom domains per project |
| Railway | Cloud Hosting | x402 Stripe MPP | Free | Free plan: $0/month with one-time $5 credit (30-day trial), 1 vCPU, 0.5 GB RAM per service, 0.5 GB volume storage, 1 pro |
| Fly.io | Cloud Hosting | x402 | Legacy Free | Pay-as-you-go only — no free tier for new accounts (since Oct 2024) |
| Deno Deploy | Cloud Hosting | x402 | Free | Edge runtime — 1M requests/month, 20 GiB egress, 10 hr active CPU/month, 150 GiB-hr memory time, 1 GiB KV storage, 1M KV |
| Supabase | Databases | x402 Stripe MPP | Free | Open source Firebase alternative — 500 MB Postgres database, 50K monthly active users, 1 GB file storage, 5 GB bandwidth |
| Neon | Databases | x402 Stripe MPP | Free | Serverless Postgres with branching — free tier includes 100 CU-hours/month per project, 0.5 GB storage per project, up t |
| Cloudflare D1 | Databases | x402 | Free | SQLite at the edge — 5M rows read/day, 100K rows written/day, 5 GB total storage |
| Cloudflare R2 | Storage | x402 | Free | Object storage with zero egress fees — 10 GB storage, 1M writes, 10M reads/month free |
| Cloudflare Queues | Messaging | x402 | Free | Message queues on Workers — 10K operations/day free (~300K/month) on the Workers Free plan, 24-hour message retention (n |
| Cloudflare KV | Databases | x402 | Free | Key-value store at the edge — 100K reads/day, 1K writes/day, 1 GB storage |
| Cloudflare Durable Objects | Cloud Hosting | x402 | Free | Stateful serverless compute — 100K requests/day on free plan |
| Firecrawl | Web Scraping | x402 | Free | Web scraping API — 500 credits (up to 500 pages), 2 concurrent requests, no credit card required |
| Cloudflare DNS | DNS & Domain Management | x402 | Free | Free authoritative DNS hosting — unlimited zones and queries, DDoS protection, free SSL/TLS |
| Stripe | Payments | Stripe MPP | Pay-as-you-go | Payment processing — no monthly fees, 2.9% + $0.30 per transaction |
| Hugging Face | AI / ML | x402 | Free | ML model hub — $0.10/month free inference credits, 200+ models via Inference Providers, unlimited model hosting on Hub |
| Groq | AI / ML | x402 Stripe MPP | Free | Ultra-fast LLM inference on LPU hardware — free tier: 30 RPM, 100K-500K tokens/day depending on model |
| Mistral AI | AI / ML | x402 | Experiment | Access to all Mistral models including Large, Codestral, Pixtral — 2 RPM, 1B tokens/month |
| OpenRouter | AI / ML | x402 Stripe MPP | Free | AI model router — ~30 free models (DeepSeek R1, Llama 3.3, Qwen3, Gemma 3), OpenAI-compatible API, ~20 RPM per model |
| Cloudflare Workers AI | AI / ML | x402 | Free | AI inference at the edge — 10,000 neurons/day free across text generation, image classification, translation, speech-to- |
| Zuplo | API Gateway | x402 | Free | 1M requests/month, 10 GB egress, up to 10 projects, unlimited production edge environments |
| Browserbase | Browser Automation | x402 Stripe MPP | Free | Headless browser infrastructure — 1 browser hour/mo, 1 concurrent browser, 15-minute max session, 7-day data retention, |
| Cerebras | AI / ML | x402 | Free | Ultra-fast LLM inference API |
| Cohere | AI / ML | x402 | Trial Key | AI model API |
| OpenAI | AI / ML | x402 | Free | AI API platform — free tier limited to GPT-3.5 Turbo model only, 3 requests/minute rate limit |
| Pinecone | AI / ML | x402 | Starter | Vector database — 2 GB storage, 2M write units/month, 1M read units/month, 5 indexes, 5M embedding tokens/month |
| Qdrant | AI / ML | x402 | Free Forever | Vector database — 1 GB free forever cluster, fully managed on AWS/GCP/Azure |
| Deepgram | AI / ML | x402 | Free Credits | Speech-to-text and text-to-speech API — $200 free credits on signup (no credit card required), ~43K minutes transcriptio |
| AssemblyAI | AI / ML | x402 | Free | Speech-to-text and audio intelligence API — free: $50 in credits (~185 hours pre-recorded transcription) |
| Replicate | AI / ML | x402 Stripe MPP | Free | ML model hosting and inference platform — free runs on curated model collection without billing |
| Baseten | AI / ML | x402 | Basic (Free Credits) | ML model deployment platform — $30 in free credits for new accounts |
| Composio | AI / ML | x402 | Free | Integration platform for AI Agents and LLMs |
| Reducto | AI / ML | x402 | Free | Turn any unstructured documents (PDF, XLSX, JPG, PPTX, etc.) into structured JSON data |
| Tavily AI | AI / ML | x402 | Free | API for online search and rapid insights and comprehensive research, with the capability of organization of research res |
| Langfuse | AI / ML | x402 | Free | Open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on their LLM applicati |
| Portkey | AI / ML | x402 | Free | Control panel for Gen AI apps featuring an observability suite & an AI gateway |
| Pinata IPFS | Storage | x402 | Free | Pinata is the simplest way to upload and manage files on IPFS |
| xAI | AI / ML | x402 | Free Credits | Sign-up gives $25 in free API credits |
| Anthropic API | AI / ML | x402 | Pay-as-you-go | Claude API access with usage-based pricing |
| NVIDIA NIM | AI / ML | x402 | Free | Free serverless APIs for LLM inference — access Llama 3.1, Mistral, and NVIDIA models |
| SiliconFlow | AI / ML | x402 | Free (Limited) | Free inference for open-source models with 100 requests/day limit and $1 free credits |
| DeepSeek API | AI / ML | x402 | Free Credits + Pay-as-you-go | Among the cheapest LLM APIs available |
| Exa | AI / ML | x402 | Free | AI-native search engine API — x402 pay-per-query search, semantic and keyword search, auto-generated summaries, contents |
| Hyperbrowser | Browser Automation | x402 | Pay-per-use | Pay-per-use cloud browser sessions for AI agents — x402 micropayments, no API key needed |
| OpenVPS | Cloud Hosting | x402 | Pay-per-use | AI agent VPS hosting — Firecracker microVMs from $0.005/hour via x402 micropayments |
| GPU-Bridge | AI / ML | x402 | Pay-per-use | Multi-provider GPU inference API — 30+ AI services (LLM, image generation, embeddings, speech) accessible via x402 micro |
| Strale | Dev Utilities | x402 | Pay-per-use | 250+ business compliance APIs — IBAN validation, VAT lookup, sanctions screening, company data, and more via x402 microp |
| tollbooth | Dev Utilities | x402 | Free | Open-source x402 payment gateway — gate any API behind micropayments with YAML config |
| E2B | AI / ML | x402 | Free (100 sandbox hrs/mo) | Cloud sandboxes for AI agents |
| Together AI | AI / ML | x402 | Free ($1 credits) | Fast inference API for open-source LLMs (Llama, Mixtral, Code Llama) |
| Fireworks AI | AI / ML | x402 | Free ($1 credits) | Fast inference platform for LLMs and image models |
| Modal | AI / ML | x402 | Free ($30/mo credits) | Serverless cloud for AI/ML |
Free
ML model hub — $0.10/month free inference credits, 200+ models via Inference Providers, unlimited mo
Free
Ultra-fast LLM inference on LPU hardware — free tier: 30 RPM, 100K-500K tokens/day depending on mode
Experiment
Access to all Mistral models including Large, Codestral, Pixtral — 2 RPM, 1B tokens/month
Free
AI model router — ~30 free models (DeepSeek R1, Llama 3.3, Qwen3, Gemma 3), OpenAI-compatible API, ~
Free
AI inference at the edge — 10,000 neurons/day free across text generation, image classification, tra
Free
AI API platform — free tier limited to GPT-3.5 Turbo model only, 3 requests/minute rate limit
Starter
Vector database — 2 GB storage, 2M write units/month, 1M read units/month, 5 indexes, 5M embedding t
Free Forever
Vector database — 1 GB free forever cluster, fully managed on AWS/GCP/Azure
Free Credits
Speech-to-text and text-to-speech API — $200 free credits on signup (no credit card required), ~43K
Free
Speech-to-text and audio intelligence API — free: $50 in credits (~185 hours pre-recorded transcript
Free
ML model hosting and inference platform — free runs on curated model collection without billing
Basic (Free Credits)
ML model deployment platform — $30 in free credits for new accounts
Free
Turn any unstructured documents (PDF, XLSX, JPG, PPTX, etc.) into structured JSON data
Free
API for online search and rapid insights and comprehensive research, with the capability of organiza
Free
Open-source LLM engineering platform that helps teams collaboratively debug, analyze, and iterate on
Free
Free serverless APIs for LLM inference — access Llama 3.1, Mistral, and NVIDIA models
Free (Limited)
Free inference for open-source models with 100 requests/day limit and $1 free credits
Free
AI-native search engine API — x402 pay-per-query search, semantic and keyword search, auto-generated
Pay-per-use
Multi-provider GPU inference API — 30+ AI services (LLM, image generation, embeddings, speech) acces
Free ($1 credits)
Fast inference API for open-source LLMs (Llama, Mixtral, Code Llama)
Hobby
Hobby plan with 100 GB/month Fast Data Transfer, 1M function invocations, 4 hrs Active CPU, 360 GB-h
Hobby
Free web services (512 MB RAM, 0.1 CPU), free PostgreSQL (256 MB RAM, 30-day expiry), free Redis (25
Free
Up to 100 sites (soft limit), unlimited bandwidth, 500 builds/month, 100 custom domains per project
Free
Free plan: $0/month with one-time $5 credit (30-day trial), 1 vCPU, 0.5 GB RAM per service, 0.5 GB v
Free
Edge runtime — 1M requests/month, 20 GiB egress, 10 hr active CPU/month, 150 GiB-hr memory time, 1 G
Pay-per-use
AI agent VPS hosting — Firecracker microVMs from $0.005/hour via x402 micropayments
Free
Open source Firebase alternative — 500 MB Postgres database, 50K monthly active users, 1 GB file sto
Free
Serverless Postgres with branching — free tier includes 100 CU-hours/month per project, 0.5 GB stora
Free
SQLite at the edge — 5M rows read/day, 100K rows written/day, 5 GB total storage
Free
Object storage with zero egress fees — 10 GB storage, 1M writes, 10M reads/month free
Free
Headless browser infrastructure — 1 browser hour/mo, 1 concurrent browser, 15-minute max session, 7-
Pay-per-use
Pay-per-use cloud browser sessions for AI agents — x402 micropayments, no API key needed
Free
Message queues on Workers — 10K operations/day free (~300K/month) on the Workers Free plan, 24-hour
Free
Web scraping API — 500 credits (up to 500 pages), 2 concurrent requests, no credit card required
Free
Free authoritative DNS hosting — unlimited zones and queries, DDoS protection, free SSL/TLS
Free
1M requests/month, 10 GB egress, up to 10 projects, unlimited production edge environments
x402 is an open HTTP-native payment protocol that uses the HTTP 402 status code to enable machine-to-machine payments. Launched by the x402 Foundation (Linux Foundation) in April 2026 with backing from Stripe, Cloudflare, Shopify, Visa, and Mastercard. It allows AI agents to autonomously pay for API calls without pre-provisioned accounts or API keys.
Currently 53 developer services indexed on AgentDeals accept x402 payments, including Firecrawl (web scraping), Cloudflare Workers/Pages/D1/R2/KV (cloud infrastructure), Vercel (hosting), Browserbase (browser automation), OpenAI and Anthropic (AI APIs), and Pinata IPFS (storage). The ecosystem is growing rapidly with 130+ services industry-wide.
MPP (Machine Payments Protocol) is Stripe's framework for agent-to-service payments launched March 2026. Currently 10 services in our index support MPP. It builds on Stripe's existing payment infrastructure to add agent identity, budget controls, and audit trails. MPP uses familiar Stripe APIs, making adoption simpler for services already using Stripe.
Agents use payment protocols like x402 or MPP to negotiate and complete payments in real-time. With x402, the agent receives a 402 response with payment requirements, completes the crypto payment, and retries with proof of payment. With MPP, agents use Stripe-managed wallets with configurable spending limits.
Yes. All 53 x402-enabled services indexed here also offer traditional free tiers. x402 is an additional payment option — it doesn't replace free tier access. Agents can use free tiers first and fall back to x402 when limits are exceeded.
API: /api/agent-payments · Filter: ?protocol=x402 · ?protocol=stripe-mpp · MCP: search_deals({payment_protocol: "x402"})
Search for agent-payment-enabled services, compare pricing, and build autonomous stacks — directly in your AI editor.
claude mcp add agentdeals -- npx -y agentdealsWorks with Claude Desktop, Cursor, Cline, Windsurf → Full setup guide