Stats
Actions
Tags
From bankr-agent
Sets up Bankr LLM Gateway for unified access to Claude, Gemini, GPT models with credits management, CLI tools, and integrations for Claude Code, Cursor, OpenClaw.
How this skill is triggered — by the user, by Claude, or both
Slash command
/bankr-agent:bankr-llm-gatewayThe summary Claude sees in its skill listing — used to decide when to auto-load this skill
The Bankr LLM Gateway is a unified API for Claude, Gemini, GPT, and other models — multi-provider access, cost tracking, automatic failover, and SDK compatibility through a single endpoint.
The Bankr LLM Gateway is a unified API for Claude, Gemini, GPT, and other models — multi-provider access, cost tracking, automatic failover, and SDK compatibility through a single endpoint.
Base URL: https://llm.bankr.bot
Uses your LLM key. Resolution order:
BANKR_LLM_KEY environment variablellmKey in ~/.bankr/config.jsonBANKR_API_KEYMost users only need one key for both agent API and LLM gateway.
New wallets start with $0 LLM credits. Top up before first use or all requests return HTTP 402.
LLM credits (USD) and trading wallet (crypto) are completely separate balances.
bankr llm credits # Check balance
bankr llm credits add 25 # Top up $25 (USDC)
bankr llm credits add 50 --token 0x... # Top up from specific token
bankr llm credits auto --enable --amount 25 --threshold 5 --tokens USDC # Auto top-up
bankr llm credits auto --disable # Disable auto top-up
| Model | Provider | Best For |
|---|---|---|
claude-opus-4.6 | Anthropic | Most capable, advanced reasoning |
claude-sonnet-4.6 | Anthropic | Balanced speed and quality |
claude-haiku-4.5 | Anthropic | Fast, cost-effective |
gemini-3-pro | Long context (2M tokens) | |
gemini-3-flash | High throughput | |
gpt-5.2 | OpenAI | Advanced reasoning |
gpt-5-mini | OpenAI | Fast, economical |
kimi-k2.5 | Moonshot AI | Long-context reasoning |
qwen3-coder | Alibaba | Code generation |
bankr llm models # Fetch live model list
# Launch directly (recommended)
bankr llm claude
bankr llm claude --model claude-sonnet-4.6
# Or set env vars
bankr llm setup claude
# Outputs: export ANTHROPIC_BASE_URL and ANTHROPIC_AUTH_TOKEN
bankr llm setup openclaw --install # Auto-install provider config
In OpenClaw, prefix model IDs with bankr/ (e.g. bankr/claude-sonnet-4.6).
bankr llm setup opencode --install # Auto-install provider config
bankr llm setup cursor # Get step-by-step setup instructions
The gateway works with standard OpenAI and Anthropic SDKs — just override the base URL.
OpenAI format:
curl -X POST "https://llm.bankr.bot/v1/chat/completions" \
-H "Authorization: Bearer $BANKR_LLM_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-4.6", "messages": [{"role": "user", "content": "Hello"}]}'
Anthropic format:
curl -X POST "https://llm.bankr.bot/v1/messages" \
-H "x-api-key: $BANKR_LLM_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "claude-sonnet-4.6", "max_tokens": 1024, "messages": [{"role": "user", "content": "Hello"}]}'
| Error | Solution |
|---|---|
| 401 Unauthorized | Verify key: bankr config get llmKey |
| 402 Payment Required | Top up credits: bankr llm credits add 25 |
| Model not found | Check exact ID: bankr llm models |
| Claude Code not found | Install Claude Code separately |
npx claudepluginhub bankrbot/claude-plugins --plugin bankr-agentRoutes LLM requests to OpenAI, Grok/xAI, Groq, DeepSeek, or OpenRouter using SwiftOpenAI-CLI agent mode with auto-setup and API key checks.
Provides expert guidance for Vercel AI Gateway configuration: model routing, provider failover, cost tracking, unified API for multiple AI providers like OpenAI, Anthropic, Gemini.
Unifies Python LLM API calls to 100+ providers (OpenAI, Anthropic, Ollama, llamafile) in OpenAI format with retries, fallbacks, exceptions, cost tracking. Triggers on litellm imports/completion().