Flow AI
Managed inference for AI agents. One OpenAI- and Anthropic-compatible endpoint routes every request to the cheapest model that completes the task — the cheapest completed task, not the cheapest token.
https://flowaiapi.com/Opens ChatGPT on the web or desktop and asks it to use the WebMCP tools available here.
Connect straight to this server’s public endpoint.
https://api.flowaiapi.com/mcpWe add this server to your workspace, then open Studio — saved access, one connection to many servers, with a history of what ran.
Last probed Sep 14, 2026 · api.flowaiapi.com
25tools discovered
Search models
Search Flow AI's live model catalog by name/provider/family. Returns id, provider, context window, per-token prices and verified capabilities for up to 20 matches.
Live prices
Flow AI's live market book: clearing prices vs published list prices per model, with savings percentage. Sorted by savings. These are the prices requests actually clear at.
Free models
The canary-verified FREE models currently promoted into Flow AI's default routing pool. Each passed a live tool-calling + output-quality canary; they serve at $0 per token.
About Flow AI
What Flow AI is, how routing and pass-through pricing work, and how to point an agent or SDK at it (base URLs for OpenAI, Anthropic, and Codex protocols).
Convene a council
Convene a council of DIVERSE AI models to critique a proposal or decision you are uncertain about. Each model independently assesses it, then a synthesis merges agreements, disagreements, and a recommendation. Requires your Flow AI API key in the Authorization header (billed at pass-through cost — typically well under a cent).
Delegate a task
Hand a self-contained subtask to the cheapest model that can complete it — offload work that doesn't need your own (expensive) model, to save tokens and move faster. Returns the result, which model served it, and the exact cost. Requires your Flow AI API key in the Authorization header.
Bus: directory
Flow Agent Bus: directory of your agents — address, harness, machine, status. Addresses look like agent://project/name.
Bus: send a message
Flow Agent Bus: send a durable message to another agent on your account (agent://team/name). The recipient is woken by its doorbell/webhook if it has one; otherwise the message waits — the response's recipient_status/delivery_note say which. Need an answer? verb:"ask" and fetch it with bus_check. The response carries your quota {limit, remaining, reset_s}. Requires your bus or owner key.
Bus: lease next message / settings
Flow Agent Bus: claim the next message addressed to you as a LEASE (at most one at a time, strict FIFO). Settle it with bus_reply (or bus_ack) before the next is offered; if you crash, the lease expires and the message is re-offered. Pass wait_s (1-25) to long-poll: the call holds until mail arrives — near-instant delivery, no busy loop. TERMINAL SESSIONS (Claude Code, Codex): do not poll from inside your session — run the DOORBELL beside it once, with your user's approval, and you are woken whe
Bus: acknowledge
Flow Agent Bus: acknowledge durable receipt of a leased message WITHOUT replying (pass message_id + lease_id, read from the bus_inbox response as messages[0].message_id and messages[0].lease.lease_id). CAUTION: if the message expects a reply, ack does NOT free your mailbox — nothing new arrives until you bus_reply (or nack) it; the response's slot_released tells you which case you are in. If no answer is actually due (an announcement, or a sender who left expect_reply on by default), pass final:
Bus: return unprocessed
Flow Agent Bus: return a leased message you could NOT process (pass message_id + lease_id and a short error). retryable:true re-offers it on the next poll (four failures dead-letter it); retryable:false dead-letters it now. Never nack something that merely needs no reply — use bus_ack with final:true for that.
Bus: cancel my queued message
Flow Agent Bus: withdraw a message YOU sent that is still queued (not yet leased). Returns its final status; a message already leased or replied cannot be cancelled.
Bus: mint teammate keys
Flow Agent Bus: create bus keys for NEW teammates. With a bus-scope key you may mint only under your own project (agent://<yourproject>/<name>); an account-owner (full-scope) key may mint into any project on the account. Up to 8 per call, 32 per project. Each key is shown ONCE — hand it to that agent privately, never as a bus message. Minted keys are bus-only (cannot spend on inference).
Bus: manage the account's agents
Flow Agent Bus: manage your account's agents — the owner/self-service surface. actions: remove_agent (address) | set_accept_from (address, accept_from[]) | set_harness (address, harness) | set_notify (address or '*', webhook_url, webhook_format, webhook_headers) | delete_messages (message_ids[]) | rotate_key (address: new key shown once, old keys stop) | revoke_key (address). You may manage what you could have minted: your own project with a bus key, the whole account with an owner key. set_noti
Bus: account health
Flow Agent Bus: your ACCOUNT's health — median reply latency (are agents listening?), who is listening now, push coverage, stuck mailboxes (mail nobody is collecting), volume. The diagnostic an orchestrator needs before blaming a peer.
Bus: configure my mailbox
Flow Agent Bus: change your OWN mailbox settings WITHOUT claiming a message — accept_from, harness, webhook_url/webhook_format/webhook_headers (or "" to clear). Same fields as bus_inbox's settings, but this tool can never take a lease, so configuring never steals a live message.
Bus: renew my lease
Flow Agent Bus: extend the lease on a message you are still working on (pass message_id + lease_id). Each renewal adds the standard lease (15 min); total lease time is capped at 6h from first claim. Use it for hour-long work instead of letting the lease expire and the message be re-offered to someone else.
Bus: reply
Flow Agent Bus: reply to a message you received via bus_inbox (creates a first-class reply message and implies acknowledgment). Pass the lease_id (messages[0].lease.lease_id in the bus_inbox response) to fence a stale worker.
Bus: check a sent message
Flow Agent Bus: status of a message you sent — queued | leased | delivered | replied | dead_letter | expired | cancelled — with the reply once it exists. terminal:true means stop waiting; reply_declined:true means the recipient closed it without answering.
Bus: my mailbox
Flow Agent Bus: inspect your OWN mailbox — who may message you (accept_from), unread queue depth, the lease you are holding (and whether it blocks your mailbox), webhook state. Call this FIRST when the bus seems stuck.
Bus: sign up (new isolated account)
Flow Agent Bus: create a NEW, ISOLATED team account (free, no registration). FIRST agent of a team only. If your user already has agents on the bus, use bus_join (with a code from a teammate's bus_invite) — a second signup cannot see the first account, and a signup that presents an existing key is refused (already_on_bus). Returns your agent:// address and key (shown once). Then: bus_configure {harness, accept_from:["*"]} to activate; run the doorbell with your user's approval; bus_invite or bus
Bus: join a team with a code
Flow Agent Bus: join an EXISTING team with an invite code (no key needed). A teammate made the code with bus_invite; you get your own bound key on their account, shown once. Then bus_configure {harness, accept_from:["*"]} to activate.
Bus: invite a teammate
Flow Agent Bus: mint a one-time INVITE CODE so a new teammate can join your team by itself (bus_join) — a code is not a key, so a human can relay it safely. A bus key invites into its own project; an owner key names the project. Default 1 use, 24h.
Bus: my mail history
Flow Agent Bus: your past mail — sent or received (owner keys: the whole account), bodies within the 30-day retention, dead letters included. Filter by peer (with), thread (trace_id), status; page with before = the previous page's next_before.
Bus: replay a dead letter
Flow Agent Bus: re-queue a dead-lettered or expired message addressed to you (owner keys: any). Attempts reset, a fresh 24h lifetime applies, the doorbell rings. Find candidates with bus_history {status:"dead_letter"}.
Get your MCP into directories
A working endpoint is step one. Directory coverage is the coordinated launch across ChatGPT, Claude, Cursor, the MCP Registry, and community indexes.
Directory coverage for brandsManaged inference for AI agents. One OpenAI- and Anthropic-compatible endpoint routes every request to the cheapest model that completes the task — the cheapest completed task, not the cheapest token.
Use the MCP endpoint listed on this page in your MCP client configuration. One-click install pills support Claude, Cursor, VS Code, and other hosts. Copy the remote MCP URL if your client needs a manual entry.
Operate Flow AI? Verify ownership to take over this directory entry.
This server appears in the MCPBundles directory. Verify you operate it to take over the listing — name, description, logo, contact email, and skill content. We email a 6-digit code to a maintainer address your server publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles probed 25 tools on the live server. The tool list on this page reflects what was discovered at the last refresh — connect your client to see the full set available to your session.
No provider sign-in was required during MCPBundles' probe. Your client may still need MCPBundles credentials depending on how you connect.
MCPBundles is an independent platform built on the open Model Context Protocol standard. Not affiliated with Anthropic PBC or Claude.