LLM Gateway & Credits

The LLM Gateway is an OpenAI-compatible proxy that routes to multiple AI providers (OpenAI, Anthropic, Google, xAI, Moonshot, Alibaba, and more). It's how Bankr pays for compute — and how your agent can fund itself.

How It Works

Fees earned from token trading accumulate in your agent's wallet. Those fees can pay for LLM inference through the gateway automatically. This is the self-funding loop: your agent earns fees, fees pay for compute, the agent keeps running.

Available Models

Max Mode gives you access to premium models including Claude Opus 5, Claude Sonnet 5, GPT-5.6 (sol, terra, and luna tiers), Gemini 3.1 Pro, Grok 4.5, Kimi K3, Qwen3.7 Max, and more. Check available models and current pricing at bankr.bot/llm.

The web terminal supports all gateway models. The CLI's --model flag accepts a curated subset that expands with each release — run bankr llm models for the current list, and update the CLI (bun install -g @bankr/cli) if a newly launched model isn't accepted yet.

Retired Models

gemini-3-pro — removed. Use gemini-3.1-pro. Requests to it are rejected before routing.
grok-4.1-fast — deprecated. Use grok-4.3 or grok-4.5.

Managing Credits


"add $25 in LLM credits"
"what's my credit balance?"

CLI:


bankr llm credits           # check balance
bankr llm credits add 25    # add $25
bankr llm credits auto --enable   # auto top-up

Model Discounts

The gateway supports time-bounded per-model discounts. For example, Claude Sonnet 5 launched with intro pricing (about a third off the list rate) through August 31, 2026. Check bankr.bot/llm for active promos.

What Happens When Credits Run Out?

Max Mode falls back to the default model (Gemini 3.6 Flash). Your message still gets processed — nothing fails. Enable auto top-up to avoid falling back unexpectedly.

For full details, see LLM Gateway, Max Mode, and Credits in our developer docs.