Browse documentation

Pick the model for the job, then see exactly what it costs.

Broker execution and broker credentials stay on your computer. Managed AI requests and billing use cloud services. BrokerBridge manages the provider connection. You choose the model, use prepaid AI credits, and keep the selected model visible in the app. Use AI Arena to compare published decisions, trades, modeled costs, drawdowns, and failures before you choose.

BrokerBridge creates and manages your AI provider credential internally. No keys to create or manage. Whichever model you pick, it reads market data, the rules you set, and your current account context, which includes your open positions, your profit and loss for the day, and how much of your account is in the market. How you approve stays your choice, set per strategy. Supported models include Anthropic (Claude), OpenAI (GPT), Google (Gemini 3.5), xAI (Grok 4.5), and DeepSeek v4.

Provider comparison

ModelRouteBilling sourceAvailability
Anthropic (Claude)Managed model planeBrokerBridge creditsPay-as-you-go, from the dashboard
OpenAI (GPT)Managed model planeBrokerBridge creditsPay-as-you-go, from the dashboard
Google (Gemini)Managed model planeBrokerBridge creditsPay-as-you-go, from the dashboard
xAI (Grok)Managed model planeBrokerBridge creditsPay-as-you-go, from the dashboard
DeepSeekManaged model planeBrokerBridge creditsPay-as-you-go, from the dashboard

BrokerBridge-managed credits

AI credits are pay-as-you-go. A wallet in the dashboard reserves an authorized amount before a model turn and settles recorded usage afterward. Running out of credits blocks the next model turn until you top up.

Credits pay for the complete BrokerBridge-managed operation, meaning model inference, metered tools, infrastructure, and service margin. They are not a resale of raw provider tokens.

Managed-credit pack pricing
PackCreditsPrice
$10 pack1,000 credits$10
$20 pack2,200 credits$20
$50 pack6,000 credits$50
$250 pack35,000 credits$250

Before you buy

Preview your managed-credit spend receipt

Select a listed pack to see the exact one-time amount and wallet credit before checkout opens. This preview changes no account state and never charges a card.

Selected package
$10 pack · 1,000 credits
One-time charge
$10.00 before checkout
Expected usage
No fixed number of model turns is promised. Each turn reserves and settles recorded usage, which varies with the model, context, and tools.
Recurring state
Auto-refill stays off unless you turn it on from the dashboard. Nothing is charged on a schedule until then.

After checkout, return to the BrokerBridge desktop app to see the settled balance. If you stay in the browser, use the account dashboard as a read-only fallback.

1 credit = $0.01 of usage. The $10 pack is list rate; $20, $50, and $250 grant tiered volume bonuses (+10%, +20%, and +40%). You can also enter a custom amount from $10 to $2,000 instead of a listed pack; a custom amount always grants at least what the same money would buy in packs, so $500 grants 70,000 credits and $2,000 grants 280,000 credits. You are never worse off for typing an amount instead of buying packs. A card is required only when you choose this managed-credit route, through Stripe-hosted checkout on an explicit first pack purchase, never implied by, or bundled into, a subscription. Your card is saved on any credit purchase, whether a listed pack or a custom amount, so that a future automatic top-up would not need you to re-enter it. Auto-refill is optional and off by default. Switching it on from the account dashboard requires explicit consent covering the refill amount, the balance threshold that triggers it, a monthly cap, and a one-tap revocation control. A zero credit balance blocks managed-model work only, never your account, the desktop app, or your broker connection.

Buying credits: purchase a pack from the dashboard whenever you need one, no separate approval step. Automatic refill stays off unless you explicitly enable it.

Anthropic (Claude)

Claude is one of the models BrokerBridge routes through its managed model plane. Pick it in Settings and pay with AI credits. There is no API key to create and no subscription to sign in with.

Select from the Claude models BrokerBridge currently offers in Settings. Static model IDs age quickly and are not a launch contract.

OpenAI

GPT is one of the models BrokerBridge routes through its managed model plane. Pick it in Settings and pay with AI credits. There is no API key to create and no subscription to sign in with.

Select from the GPT models BrokerBridge currently offers in Settings. BrokerBridge does not silently substitute a different model or billing route.

DeepSeek

DeepSeek is one of the models BrokerBridge routes through its managed model plane. Pick it in Settings and pay with AI credits. There is no API key to create and no subscription to sign in with.

Select from the DeepSeek models BrokerBridge currently offers in Settings and confirm its usage price before relying on it.

Google AI

Gemini is one of the models BrokerBridge routes through its managed model plane. Pick it in Settings and pay with AI credits. There is no API key to create and no subscription to sign in with.

Select from the Gemini models BrokerBridge currently offers in Settings; avoid copying a model ID from an old setup guide.

xAI (Grok)

Grok is one of the models BrokerBridge routes through its managed model plane. Pick it in Settings and pay with AI credits. There is no API key to create and no subscription to sign in with.

Select from the Grok models BrokerBridge currently offers in Settings; avoid copying a model ID from an old setup guide.

How AI decisions work

When BrokerBridge identifies a trade setup, it sends the AI a structured prompt containing:

  • Price action data (recent OHLCV bars and extracted features)
  • Evidence snapshots from data source plugins (scanner signals, flow data)
  • Current portfolio state (open positions, daily P&L, exposure)
  • Your rules (the limits you configured)

The AI returns a structured decision: approve or reject, with a confidence score (0-1), reasoning summary, suggested position size, and risk/reward ratio. This decision is recorded in the decisions CSV and presented alongside the original trade plan.

Important:Model output alone doesn't place a trade. Supervised strategies need your approval on each trade plan. I confirm from the alert strategies need a tap within the time window before the setup expires. I approve the strategy up front strategies need your standing approval and a passed review, and only trade inside their configured money limit, your rules, allowed instruments, schedule, and broker mode. AI Arena publishes same-market results when a snapshot is published and never places a real broker order.