Tool platforms
OpenRouter for Tools: One API for Agent Capabilities
Understand the OpenRouter for tools idea: shared access to agent capabilities, with clear account choices, useful workflows, and recovery.
All articles
Aryah Oztanir is the co-founder and CEO of o11 (YC W26), the wallet that lets AI agents find, use, and pay per call for paid APIs and tools. Aryah writes about agent tools, MCP, provider pricing, and agent payments.
Articles
Developer guides
Claude Code Tools: Add Paid APIs Through o11 MCP
Configure Claude Code for o11 over HTTP MCP, inspect eligible operations, authorize one bounded task, and retain results for recovery.
Workflows
Build a Company Research Agent
Build a company research agent with evidence-linked search, page retrieval, selective enrichment, clear budgets, and a reviewable supplier brief.
Comparisons
Nevermined vs Composio vs o11: Paid Tools for Agents
Compare paid-tool access, connected accounts, setup effort, and execution evidence across o11, Composio Instant, and Nevermined.
Tool platforms
What Is an AI Tool Gateway? A Practical Guide
A practical guide to AI tool gateways: discovery, account access, execution contracts, and the recovery behavior developers should evaluate.
Tool platforms
How AI Agents Access Paid APIs
How shared tool access reduces separate provider setup, when customer accounts remain necessary, and how to evaluate paid API readiness.
Tool platforms
One API Key for Multiple AI Tools
Connect multiple AI tools with one scoped key while keeping supplier credentials, account access, spending authority, and recovery distinct.
Tool platforms
Model Routers and Tool Routers in an Agent Stack
Design an agent stack with separate model and tool access, explicit execution responsibility, source evidence, and complete workflow costs.
Tool platforms
Agent Tool Discovery: Find and Choose the Right Tool
A staged method for agent tool discovery: define the result, filter eligible operations, inspect contracts, and evaluate useful outcomes.
Tool platforms
Connected Accounts and Pay-per-Use Agent Tools
Combine connected provider accounts and pay-per-use tools with explicit ownership, account selection, billing context, and recovery rules.
Tool platforms
How to Choose an AI Tool Platform
Evaluate an AI tool platform using a real workflow, setup tasks, usable output, account boundaries, failure recovery, and complete costs.
Developer guides
Cursor Agent Tools: Search, Research, and Media
Configure Cursor for o11 over remote MCP, use search and media tools deliberately, and preserve project artifacts and invocation recovery.
Developer guides
Connect a Custom Agent to Paid Services
Build a small server-side HTTP adapter for custom agents with o11 discovery, explicit execution intents, validated results, and recovery.
Developer guides
MCP Gateway: Connect Many Services Through One Endpoint
Connect an MCP agent to multiple services through one endpoint while preserving provider contracts, account scope, and invocation state.
Developer guides
Vercel AI SDK Tools: Connect Agents to Paid APIs
Connect AI SDK 6 agents to o11 through server tool functions with scoped discovery, durable execution intents, and asynchronous recovery.
Developer guides
LangGraph Tools: Use Paid APIs in a LangGraph Agent
Connect LangGraph workflows to o11 with separate submission and status nodes, stable request intents, checkpoint planning, and recovery.
Developer guides
Build a Reusable Agent Tool Layer
Share agent tool access across projects using domain contracts, reusable transport, separate policies, provenance, and explicit recovery.
Developer guides
Migrate Agent Integrations to a Shared Tool Layer
Migrate agent integrations incrementally with a mapping worksheet, equivalent output checks, preserved account ownership, and rollback.
Workflows
Give a Coding Agent Tools to Build a Website
Give a coding agent a practical path from a scoped website brief to reviewed assets, working interactions, and an inspectable deployment preview.
Workflows
Build a Lead Research Agent with a Focused Tool Set
Build a lead research agent with observable fit rules, company evidence, selective enrichment, deduplication, and a human-reviewable shortlist.
Workflows
Text to Speech API: Turn Agent Research into Audio
Turn checked research into a written brief and audio summary with versioned evidence, a spoken script, pronunciation review, and reliable delivery.
Workflows
Image and Video Generation APIs in One Agent Workflow
Create product images and short videos with an asset specification, reviewed references, bounded revisions, durable jobs, and truthful product details.
Workflows
Extract Structured Data from PDFs with an Agent
Build a PDF extraction agent with page-linked evidence, explicit units, structural validation, arithmetic checks, and a reviewable exception queue.
Workflows
Build a Competitor Monitoring Agent
Monitor selected competitor pages, preserve comparable snapshots, classify meaningful changes, and prepare a weekly brief with clear coverage limits.
Workflows
Build a Content Agent with Research and Media Tools
Build a content agent workflow that connects research, useful visuals, and voice tools through an approved story and a versioned asset manifest.
Workflows
Build an AI Research Agent That Checks Its Sources
Build a research assistant that verifies individual claims, checks source scope and dates, reconciles numbers, and preserves uncertainty honestly.
Workflows
Prototype Agent Features with Paid Tools
Prototype one agent feature with a clear hypothesis, representative tasks, pay-per-use tools, explicit limits, and an evidence-backed product decision.
Comparisons
Composio vs Arcade vs o11: AI Agent Tool Platforms
Compare tool execution and account authorization across o11, Composio, and Arcade, with a practical lifecycle pilot for agent developers.
Comparisons
o11 vs Anyway: Paid API Access for Agents
Compare o11 and Anyway Agents for paid API access, setup time, service coverage, purchase limits, and useful agent outputs.
Comparisons
Composio vs Pipedream Connect vs Nango for AI Agents
Choose agent integrations by authorization, prebuilt actions, custom functions, synchronization, and the maintenance your product needs to own.
Comparisons
MCP vs Unified Tool APIs vs Direct Integrations
Understand how MCP, unified tool APIs, and direct provider integrations fit together, and assign setup, access, execution, and recovery ownership.
Comparisons
Pay-per-Use Tools vs Subscriptions vs Your Accounts
Compare pay-per-use tools, subscriptions, and provider accounts using setup effort, commitments, accepted outputs, and explicitly illustrative economics.
Comparisons
Exa vs Tavily vs Brave Search API for AI Agents
Compare Exa, Tavily, and Brave Search by evidence quality, freshness, content retrieval, and cost per accepted research answer.
Comparisons
Firecrawl vs Browserbase vs Direct Fetch
Choose direct HTTP retrieval, Firecrawl, or Browserbase by the content, rendering, interaction, and provenance your agent actually needs.
Comparisons
Replicate vs fal.ai vs Direct Image Generation APIs
Compare Replicate, fal, and direct image APIs by exact model support, accepted-image quality, job handling, artifact ownership, and setup burden.
Comparisons
ElevenLabs vs Cartesia vs OpenAI TTS API for Agents
Compare voice generation for agents using the right speech API, listening rubric, playback measurements, and accepted audio economics.
Setup and costs
The Hidden Cost of Setting Up APIs for Agents
Measure the hidden setup cost of another agent API, from accounts and credentials to error handling, maintenance, and a verified useful result.
Setup and costs
Pay-per-Use API Break-Even: A Worked Example
Calculate when pay-per-use tools cost less than an API subscription using usage scenarios, allowances, overages, setup work, and accepted outputs.
Setup and costs
Manage Provider Credentials for AI Agents
Manage provider credentials across agent projects with clear ownership, scoped connections, safe rotation, revocation, and preserved spending history.
Setup and costs
Estimate Costs for a Multi-Tool Agent Workflow
Estimate multi-tool agent costs from task graphs, billing units, conditional calls, retries, fixed commitments, and the cost per accepted result.
Setup and costs
Avoid Unused API Subscriptions in Agent Projects
Avoid idle API subscriptions with a project inventory, commercial stop rules, usage review, renewal decisions, and a safe account retirement path.
Setup and costs
Reduce Agent Tool Setup Time
Design faster agent-tool onboarding from targeted discovery through account choice and authorization to a verified useful result and safe recovery.
Setup and costs
Recover from Agent Tool Failures
Recover agent tool failures by classifying errors, checking existing calls, bounding retries, preserving partial results, and reconciling uncertainty.
Setup and costs
Set Spending Limits for Agent Tools
Set agent spending limits with task allowances, card budgets, atomic reservations, verified settlement, and recoverable approval or uncertainty paths.
Setup and costs
Handle Async Image and Video Jobs in AI Agents
Handle long-running image and video jobs by submitting once, persisting identity, observing completion, validating files, and resuming safely.
Setup and costs
Choose the Tools Your Agent Actually Needs
Choose an agent tool set by mapping useful outcomes to capabilities, inspecting contracts, scoping authority, and evaluating representative tasks.
Research
An Evaluation Framework for Agent-Ready APIs
Evaluate an API operation for agent use with evidence levels, task fixtures, semantic usability, useful results, and recoverable execution.
Research
Measure Time to First Successful Agent Tool Call
Measure agent tool setup fairly with clean and configured conditions, event timelines, intervention logs, completion rates, and accepted outputs.
Research
Compare Research Workflow Costs Across Tool Stacks
Compare research stacks by accepted briefs, complete consumption ledgers, setup and correction effort, commitments, and matched quality review.
Research
Test Whether Agents Can Use Tools from Their Schemas
Test whether agents can use unfamiliar tools with controlled contracts, semantic fixtures, separate stage scores, and auditable traces.
Developer guides
HTTP 402 Payment Required: How AI Agents Handle It
Recognize x402, MPP, and pay per crawl 402s, decide whether to pay, cap, skip, or fall back, and log a receipt for every paid request.
Comparisons
x402 vs MPP vs ACP vs AP2: Agent Payment Protocols
Sort x402, MPP, ACP and AP2 by layer, see which ones a tool-calling agent touches, and compare settlement, fiat support and spending caps.
Tool platforms
Smithery Shutdown: Migrate MCP Connections by Oct 31
What stops on October 31, 2026, commands to find run.tools and server.smithery.ai URLs in Claude Code, Cursor, VS Code and Codex, and three replacements.
Research
MCP Token Usage: Measure Tool Definition Cost
A reproducible method and Bun script to count MCP tool definition and result tokens, compare tool search on and off, and estimate cost per 1,000 turns.
Setup and costs
Idempotency Keys for Paid API and Tool Calls
How to retry paid agent tool calls safely: MCP annotations, idempotency keys, async job dedupe, charge reconciliation, and a local drop test.
Comparisons
Web Search API vs Built-in LLM Web Search for Agents
Compare Anthropic, OpenAI, and Gemini web search tools with Exa, Tavily, and Parallel on documented pricing and behavior, plus a reproducible evaluation method.
Developer guides
MCP Tool Pricing: See the Cost Before an Agent Calls
MCP has no standard price field. See the conventions in use, an illustrative _meta price block, and three ways to budget before a paid call.
Setup and costs
MCP Security Checklist: Vet MCP Servers Before Install
A copyable pre-install and update checklist for third-party MCP servers, mapped to named CVEs and the NSA's 2026 MCP guidance, with spend controls.
Developer guides
Sora API Shutdown: Alternatives for Video Agents
The Sora API shut down September 24, 2026. Map Sora requests to Veo, Gemini Omni Flash, Kling, and Seedance, and make the next switch a config change.
Developer guides
Web Bot Auth and Signed Agents: RFC 9421 Guide
Sign agent requests for Web Bot Auth in TypeScript with WebCrypto Ed25519, host a signed key directory, and know which header format Cloudflare verifies.