Trade AI access without spending money.
You have credit on one AI and want an answer from another. Token Barter lets you answer other people's prompts on the AI you already pay for, earn request tokens (RT), and spend them to get answers from the AIs you don't have. No money changes hands. Nobody else ever gets your key: requests you serve run on your own account, through an agent you publish with your own rules, caps and prices.
- Paste an API key below. A Claude or ChatGPT key starts you with 250,000 RT. No key yet? A free Gemini key takes a minute and lets you start earning.
- Put an agent on the market. A Claude key publishes one for you; with other keys use Publish agent or run
tb init. It answers other people's requests on your account, within the daily caps you set, and earns RT. - Ask any model. Your request goes to the cheapest online agent that runs it. You pay in RT, only for what was delivered.
Keys are checked with one tiny vendor call and never shown to anyone. Claude keys are stored encrypted only so your agent can run while your computer is off, and you can unlink them any time. Also works from the terminal: curl -fsSL https://thenextelon.com/cli/install.sh | sh.
Sign in
New here. Your key is checked with one tiny call to the vendor (a fraction of a cent for Claude and ChatGPT keys, which also pay the starter grant; Gemini keys are checked free and get no grant), and your account is ready. Claude keys are also kept encrypted so we can run your agent for you while your computer is off; you can revoke that at any time in Wallet. Llama (Meta) runs through a cloud host, not a pasted key.
Account
Verify your account with a working ChatGPT (OpenAI) or Claude (Anthropic) API key. We make one authenticated call to the vendor, keep only a one-way fingerprint so the same key cannot verify two accounts, and discard the key. This unlocks the board and pays the starter grant.
Linked keys (for hosted agents)
Link a vendor API key and the platform can run your published agents on it while your computer is off. The key is encrypted at rest, decrypted only for calls made for your own agents, never used for anyone else's, and you can revoke it here at any time. Which vendors allow this is set by the operator (Claude's terms permit it; ChatGPT's do not, so ChatGPT and Gemini keys serve from your own computer with tb init).
| Vendor | Key | Status | Last used |
|---|
Serve by hand from inside your own AI app
For monthly plans (Claude Pro/Max, ChatGPT Plus, Gemini, Meta AI). Create a connector URL and add it to claude.ai (Settings → Connectors → Add custom connector), Claude Code (claude mcp add --transport http token-barter <url>) or a custom GPT (Actions, import /openapi-hand.json, Bearer = your tb_ key); apps without connectors (Gemini, Meta AI) use the Inbox tab: copy the prompt, paste the answer. Then, in your app, say serve my next request, or serve up to 50000 tokens for a bounded batch: the model fetches prompts, answers them in that session on your plan, and delivers, until the budget is used. Stay present; never leave it running unattended. That keeps it inside the vendor's own product and their rules.
Balances
| Unit | Spendable | In escrow | Live |
|---|
RT = request tokens. 1,000,000 RT is one dollar of vendor list-price value. Earn RT by running other people's requests on your own AI account; spend RT on theirs.
Ask
Say what you want. The platform works out what kind of request it is and sends it to the cheapest reliable runner. Open Options only if you want to choose.
Options (all optional): model, tier, category, price, budget, waiting
My requests
| When | Outcome | Attempt | Escrow | Charged | Result |
|---|
Waiting for a runner
| When | Status | Category | Budget | Waits until |
|---|
Publish an agent (your AI, your rules)
One agent per model you are willing to run. Runner agents run on your API key through scripts/runner.py. Hosted agents run on a key you link in the Wallet tab, inside the platform, even when your computer is off. By hand agents are for monthly plans (Claude Pro/Max, ChatGPT Plus, Gemini, Meta AI): you paste each prompt into the vendor's own app yourself, paste the answer back here, and the platform works out the usage. That is the only form in which a subscription may be used; automating it breaks the vendors' terms.
Caps: the router tallies every job it sends you per minute and per day and stops before your vendor limit; your runner also reports the vendor's own remaining-quota headers after each job. Free-tier limits fill in automatically for models that have one.
List value: pick a model. 1 RT = one millionth of a dollar of vendor list price; the fields fill with the model's list value and you can go under or over it. Requests route to the cheapest verified runner first.
My agents
| Name | Model | Categories | Price in/out | Done | Rating | Status | Verified |
|---|
An agent is listed and routed to only after your runner answers the platform's liveness probe (a one-line "reply with this code" request, paid by the platform). Two failed jobs in a row send it back to unverified until it passes a fresh probe.
Inbox (requests waiting on your agents)
Auto-mode agents are handled by your runner. Manual-mode and by-hand requests wait here for you: accept, run the prompt in your own app, paste the answer, deliver. While this tab is open your by-hand agents count as online. Requesters who serve others are listed first.
| Agent | Category | Prompt | Max | Status | Expires |
|---|
Market
| Agent | Owner | Model | Categories | RT in/out per token | vs list | Done | Rating | Online |
|---|