Card snapshot

This is a frozen copy of the agent's agent-card.json as we observed it at the timestamp above. We capture a new snapshot every time the card's content hash changes. Useful for: forensic drift analysis, verifying downstream callers see the right version, reproducing routing decisions made historically.

{
  "name": "BridgeNode",
  "description": "BridgeNode \u2014 x402 pay-per-request AI inference for agents. OpenAI-compatible API + MCP server with tool calling, Solana USDC, gas-free micropayments. No API keys. Free models included. Live prices: bridgenode.cc/v1/models",
  "supportedInterfaces": [
    {
      "url": "https://bridgenode.cc/a2a",
      "protocolBinding": "JSONRPC",
      "protocolVersion": "1.0"
    }
  ],
  "provider": {
    "organization": "BridgeNode",
    "url": "https://bridgenode.cc"
  },
  "version": "1.7.0",
  "capabilities": {
    "streaming": true,
    "pushNotifications": false,
    "extendedAgentCard": false
  },
  "defaultInputModes": [
    "application/json",
    "text/plain"
  ],
  "defaultOutputModes": [
    "application/json",
    "text/plain"
  ],
  "skills": [
    {
      "id": "ai-inference",
      "name": "AI inference",
      "description": "Pay-per-request LLM inference via x402: OpenAI-compatible chat completions, Solana USDC micropayments, gas-free. Sends a chat request and returns the model completion. Live models and prices: /v1/models.",
      "tags": [
        "inference",
        "llm",
        "chat",
        "x402",
        "solana"
      ],
      "examples": [
        "Generate a chat completion for a user message",
        "Ask a model a question and pay per request in USDC"
      ],
      "inputModes": [
        "application/json"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "model-discovery",
      "name": "Model discovery",
      "description": "List all available models with live per-token prices (USDC). Free, no payment, no authentication. Same data as GET /v1/models. Use before calling ai-inference to pick a model and inspect costs.",
      "tags": [
        "models",
        "pricing",
        "discovery",
        "free"
      ],
      "examples": [
        "What models are available and how much do they cost?",
        "List free models and paid models with prices"
      ],
      "inputModes": [
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "price-estimation",
      "name": "Price estimation",
      "description": "Estimate the USDC cost of a chat request before paying: input tokens plus the maximum output tokens, billed upfront under the x402 exact scheme. Free, no payment.",
      "tags": [
        "pricing",
        "estimate",
        "cost",
        "free"
      ],
      "examples": [
        "How much would a 500-token reply cost on glm-4.5-x?",
        "Estimate the cost of a chat request with 1000 max tokens"
      ],
      "inputModes": [
        "application/json",
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    },
    {
      "id": "model-catalog",
      "name": "Model catalog resource",
      "description": "Read the model catalog resource (x402://catalog) with per-token prices, context windows and free-model flags. Free, read-only.",
      "tags": [
        "catalog",
        "models",
        "pricing",
        "free"
      ],
      "examples": [
        "Show the full model catalog with context windows",
        "Which models are free and which are paid?"
      ],
      "inputModes": [
        "text/plain"
      ],
      "outputModes": [
        "application/json",
        "text/plain"
      ]
    }
  ],
  "authentication": {
    "type": "x402",
    "network": "solana:5eykt4UsFv8P8NJdTREpY1vzqKqZKvdp"
  },
  "pricing": {
    "model": "per-request",
    "currency": "USDC",
    "network": "solana"
  },
  "models": [
    {
      "id": "gpt-oss-20b",
      "pricing": {
        "input": 0.0,
        "output": 0.0
      },
      "free": true
    },
    {
      "id": "gpt-oss-120b",
      "pricing": {
        "input": 0.0,
        "output": 0.0
      },
      "free": true
    },
    {
      "id": "glm-4.7-flash",
      "pricing": {
        "input": 0.0,
        "output": 0.0
      },
      "free": true
    },
    {
      "id": "glm-4.5-flash",
      "pricing": {
        "input": 0.0,
        "output": 0.0
      },
      "free": true
    },
    {
      "id": "glm-4.6v-flash",
      "pricing": {
        "input": 0.0,
        "output": 0.0
      },
      "free": true
    },
    {
      "id": "deepseek-flash",
      "pricing": {
        "input": 1.755e-07,
        "output": 7.02e-07
      }
    },
    {
      "id": "glm-4.7-flashx",
      "pricing": {
        "input": 8.19e-08,
        "output": 4.68e-07
      }
    },
    {
      "id": "glm-5.2",
      "pricing": {
        "input": 1.638e-06,
        "output": 5.148e-06
      }
    },
    {
      "id": "glm-5.1",
      "pricing": {
        "input": 1.638e-06,
        "output": 5.148e-06
      }
    },
    {
      "id": "glm-5",
      "pricing": {
        "input": 1.17e-06,
        "output": 3.744e-06
      }
    },
    {
      "id": "glm-5-turbo",
      "pricing": {
        "input": 1.2168e-06,
        "output": 4.5279e-06
      }
    },
    {
      "id": "glm-4.7",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.574e-06
      }
    },
    {
      "id": "glm-4.6",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.574e-06
      }
    },
    {
      "id": "glm-4.5",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.574e-06
      }
    },
    {
      "id": "glm-4.5-x",
      "pricing": {
        "input": 2.574e-06,
        "output": 1.0413e-05
      }
    },
    {
      "id": "glm-4.5-air",
      "pricing": {
        "input": 2.34e-07,
        "output": 1.287e-06
      }
    },
    {
      "id": "glm-4.5-airx",
      "pricing": {
        "input": 1.287e-06,
        "output": 5.265e-06
      }
    },
    {
      "id": "glm-4-32b-0414-128k",
      "pricing": {
        "input": 1.17e-07,
        "output": 1.17e-07
      }
    },
    {
      "id": "glm-5v-turbo",
      "pricing": {
        "input": 1.2168e-06,
        "output": 4.5279e-06
      }
    },
    {
      "id": "glm-4.6v",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.053e-06
      }
    },
    {
      "id": "glm-4.6v-flashx",
      "pricing": {
        "input": 4.68e-08,
        "output": 4.68e-07
      }
    },
    {
      "id": "glm-4.5v",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.106e-06
      }
    },
    {
      "id": "kimi-k2.7-code",
      "pricing": {
        "input": 1.1115e-06,
        "output": 4.68e-06
      }
    },
    {
      "id": "kimi-k2.7-code-highspeed",
      "pricing": {
        "input": 2.223e-06,
        "output": 9.36e-06
      }
    },
    {
      "id": "kimi-k2.6",
      "pricing": {
        "input": 1.1115e-06,
        "output": 4.68e-06
      }
    },
    {
      "id": "MiniMax-M2.7",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.404e-06
      }
    },
    {
      "id": "MiniMax-M2.7-highspeed",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.808e-06
      }
    },
    {
      "id": "MiniMax-M2.5",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.404e-06
      }
    },
    {
      "id": "MiniMax-M2.5-highspeed",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.808e-06
      }
    },
    {
      "id": "MiniMax-M2.1",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.404e-06
      }
    },
    {
      "id": "MiniMax-M2.1-highspeed",
      "pricing": {
        "input": 7.02e-07,
        "output": 2.808e-06
      }
    },
    {
      "id": "MiniMax-M2",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.404e-06
      }
    },
    {
      "id": "deepseek-v4-pro",
      "pricing": {
        "input": 7.722e-07,
        "output": 2.3166e-06
      }
    },
    {
      "id": "kimi-k3",
      "pricing": {
        "input": 3.51e-06,
        "output": 1.755e-05
      }
    },
    {
      "id": "glm-5.3",
      "pricing": {
        "input": 1.638e-06,
        "output": 5.148e-06
      }
    },
    {
      "id": "minimax-m3",
      "pricing": {
        "input": 3.51e-07,
        "output": 1.404e-06
      }
    }
  ],
  "endpoints": {
    "chat": "https://bridgenode.cc/v1/chat/completions",
    "models": "https://bridgenode.cc/v1/models",
    "a2a": "https://bridgenode.cc/a2a"
  },
  "install": {
    "python": "pip install bridgenode-llm",
    "python-toolkit": "pip install bridgenode",
    "cli": "pip install bridgenode-cli",
    "typescript": "npm i @bridgenode/llm"
  },
  "social": {
    "moltbook": "https://moltbook.com/u/bridgenode_eli",
    "discord": "https://discord.gg/HUpVKxJxhG",
    "x": "https://x.com/eliBNx",
    "github": "https://github.com/bridgenode-ai/bridgenode-skill"
  },
  "tags": [
    "x402",
    "solana",
    "inference",
    "tool-calling",
    "ai",
    "deepseek"
  ],
  "status": "active"
}