@ailib-official/ai-protocol 0.8.4

package/dist/v1/models/nvidia.json

@@ -0,0 +1,212 @@
+{
+  "$schema": "https://raw.githubusercontent.com/ailib-official/ai-protocol/main/schemas/v1.json",
+  "protocol_version": "1.1",
+  "models": {
+    "nvidia-nemotron-4-340b-instruct": {
+      "provider": "nvidia",
+      "model_id": "nvidia-nemotron-4-340b-instruct",
+      "display_name": "Nemotron 4 340B Instruct",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "NVIDIA flagship 340B chat model; OpenAI-compatible chat completions."
+      },
+      "context_window": 128000,
+      "capabilities": [
+        "chat",
+        "vision",
+        "tools",
+        "streaming",
+        "agentic",
+        "parallel_tools",
+        "reasoning"
+      ],
+      "status": "active",
+      "tags": [
+        "nvidia",
+        "nemotron",
+        "flagship",
+        "reasoning",
+        "tools"
+      ]
+    },
+    "nvidia/llama3-chatqa-1.5-70b": {
+      "provider": "nvidia",
+      "model_id": "nvidia/llama3-chatqa-1.5-70b",
+      "display_name": "Llama 3 ChatQA 1.5 70B",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "70B chat QA model on NVIDIA API Catalog."
+      },
+      "context_window": 32768,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "status": "active",
+      "tags": [
+        "nvidia",
+        "llama",
+        "chatqa",
+        "70b"
+      ]
+    },
+    "deepseek-ai/deepseek-r1": {
+      "provider": "nvidia",
+      "model_id": "deepseek-ai/deepseek-r1",
+      "display_name": "DeepSeek R1 (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "Reasoning model available on NVIDIA API Catalog."
+      },
+      "context_window": 64000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "reasoning"
+      ],
+      "status": "active",
+      "tags": [
+        "deepseek",
+        "reasoning",
+        "nvidia-catalog"
+      ]
+    },
+    "mistralai/mistral-large-2-instruct": {
+      "provider": "nvidia",
+      "model_id": "mistralai/mistral-large-2-instruct",
+      "display_name": "Mistral Large 2 Instruct (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "Mistral flagship instruct model on NVIDIA API Catalog."
+      },
+      "context_window": 128000,
+      "capabilities": [
+        "chat",
+        "vision",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "status": "active",
+      "tags": [
+        "mistral",
+        "instruct",
+        "nvidia-catalog"
+      ]
+    },
+    "mistralai/mixtral-8x22b-instruct": {
+      "provider": "nvidia",
+      "model_id": "mistralai/mixtral-8x22b-instruct",
+      "display_name": "Mixtral 8x22B Instruct (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "MoE 8x22B instruct model on NVIDIA API Catalog."
+      },
+      "context_window": 65536,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "status": "active",
+      "tags": [
+        "mistral",
+        "mixtral",
+        "moe",
+        "nvidia-catalog"
+      ]
+    },
+    "meta/llama3-70b": {
+      "provider": "nvidia",
+      "model_id": "meta/llama3-70b",
+      "display_name": "Llama 3 70B (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/llm-apis",
+        "notes": "Meta Llama 3 70B on NVIDIA API Catalog."
+      },
+      "context_window": 8192,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming"
+      ],
+      "status": "active",
+      "tags": [
+        "meta",
+        "llama",
+        "70b",
+        "nvidia-catalog"
+      ]
+    },
+    "moonshotai/kimi-k2-instruct": {
+      "provider": "nvidia",
+      "model_id": "moonshotai/kimi-k2-instruct",
+      "display_name": "Kimi K2 Instruct (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/moonshotai-kimi-k2-instruct",
+        "notes": "Moonshot Kimi K2 MoE 1T/32B; agentic, tools, 128K context on NVIDIA API Catalog."
+      },
+      "context_window": 128000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic",
+        "reasoning"
+      ],
+      "status": "active",
+      "tags": [
+        "moonshot",
+        "kimi",
+        "moe",
+        "nvidia-catalog",
+        "agentic"
+      ]
+    },
+    "minimaxai/minimax-m2": {
+      "provider": "nvidia",
+      "model_id": "minimaxai/minimax-m2",
+      "display_name": "MiniMax M2 (via NVIDIA)",
+      "verification": {
+        "status": "verified",
+        "verified_at": "2026-02-04",
+        "source": "https://docs.api.nvidia.com/nim/reference/minimaxai-minimax-m2",
+        "notes": "MiniMax M2 MoE 230B/10B; coding, reasoning, tool-use, 128K context on NVIDIA API Catalog."
+      },
+      "context_window": 128000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic",
+        "reasoning"
+      ],
+      "status": "active",
+      "tags": [
+        "minimax",
+        "moe",
+        "nvidia-catalog",
+        "coding",
+        "agentic"
+      ]
+    }
+  }
+}

package/dist/v1/models/palmyra.json

@@ -0,0 +1,103 @@
+{
+  "$schema": "https://raw.githubusercontent.com/ailib-official/ai-protocol/main/schemas/v1.json",
+  "protocol_version": "1.5",
+  "models": {
+    "palmyra-x-004": {
+      "provider": "writer",
+      "model_id": "palmyra-x-004",
+      "display_name": "Palmyra X 004",
+      "verification": {
+        "status": "unverified",
+        "source": "manual",
+        "notes": "Flagship model for enterprise writing"
+      },
+      "context_window": 128000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic",
+        "reasoning"
+      ],
+      "pricing": {
+        "input_per_token": null,
+        "output_per_token": null
+      },
+      "status": "active",
+      "tags": [
+        "palmyra",
+        "writer",
+        "enterprise",
+        "writing",
+        "reasoning"
+      ],
+      "agentic_capabilities": {
+        "reasoning_effort": "medium",
+        "thinking_blocks": false,
+        "parallel_tools": false,
+        "builtin_tools": [
+          "web_search",
+          "fact_check",
+          "compliance"
+        ]
+      }
+    },
+    "palmyra-med": {
+      "provider": "writer",
+      "model_id": "palmyra-med",
+      "display_name": "Palmyra Med",
+      "verification": {
+        "status": "unverified",
+        "source": "manual",
+        "notes": "Specialized for medical and healthcare content"
+      },
+      "context_window": 64000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "pricing": {
+        "input_per_token": null,
+        "output_per_token": null
+      },
+      "status": "active",
+      "tags": [
+        "palmyra",
+        "writer",
+        "medical",
+        "healthcare",
+        "enterprise"
+      ]
+    },
+    "palmyra-fin": {
+      "provider": "writer",
+      "model_id": "palmyra-fin",
+      "display_name": "Palmyra Fin",
+      "verification": {
+        "status": "unverified",
+        "source": "manual",
+        "notes": "Specialized for financial content"
+      },
+      "context_window": 64000,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "pricing": {
+        "input_per_token": null,
+        "output_per_token": null
+      },
+      "status": "active",
+      "tags": [
+        "palmyra",
+        "writer",
+        "finance",
+        "enterprise"
+      ]
+    }
+  }
+}

package/dist/v1/models/perplexity.json

@@ -0,0 +1,143 @@
+{
+  "$schema": "https://raw.githubusercontent.com/ailib-official/ai-protocol/main/schemas/v1.json",
+  "protocol_version": "1.1",
+  "models": {
+    "llama-3.1-sonar-small-128k-online": {
+      "provider": "perplexity",
+      "model_id": "llama-3.1-sonar-small-128k-online",
+      "display_name": "Sonar Small Online (8B)",
+      "verification": {
+        "status": "unverified",
+        "verified_at": "2026-01-31",
+        "source": "documentation",
+        "notes": "Llama 3.1 8B with real-time web search."
+      },
+      "context_window": 127072,
+      "capabilities": [
+        "chat",
+        "streaming",
+        "online_search"
+      ],
+      "status": "active",
+      "tags": [
+        "perplexity",
+        "sonar",
+        "online",
+        "search"
+      ],
+      "pricing": {
+        "input_per_token": 2e-7,
+        "output_per_token": 2e-7
+      }
+    },
+    "llama-3.1-sonar-large-128k-online": {
+      "provider": "perplexity",
+      "model_id": "llama-3.1-sonar-large-128k-online",
+      "display_name": "Sonar Large Online (70B)",
+      "verification": {
+        "status": "unverified",
+        "verified_at": "2026-01-31",
+        "source": "documentation",
+        "notes": "Llama 3.1 70B with real-time web search."
+      },
+      "context_window": 127072,
+      "capabilities": [
+        "chat",
+        "streaming",
+        "online_search"
+      ],
+      "status": "active",
+      "tags": [
+        "perplexity",
+        "sonar",
+        "online",
+        "search",
+        "large"
+      ],
+      "pricing": {
+        "input_per_token": 0.000001,
+        "output_per_token": 0.000001
+      }
+    },
+    "llama-3.1-sonar-huge-128k-online": {
+      "provider": "perplexity",
+      "model_id": "llama-3.1-sonar-huge-128k-online",
+      "display_name": "Sonar Huge Online (405B)",
+      "verification": {
+        "status": "unverified",
+        "verified_at": "2026-01-31",
+        "source": "documentation",
+        "notes": "Llama 3.1 405B with real-time web search."
+      },
+      "context_window": 127072,
+      "capabilities": [
+        "chat",
+        "streaming",
+        "online_search"
+      ],
+      "status": "active",
+      "tags": [
+        "perplexity",
+        "sonar",
+        "online",
+        "search",
+        "flagship"
+      ],
+      "pricing": {
+        "input_per_token": 0.000005,
+        "output_per_token": 0.000005
+      }
+    },
+    "llama-3.1-sonar-small-128k-chat": {
+      "provider": "perplexity",
+      "model_id": "llama-3.1-sonar-small-128k-chat",
+      "display_name": "Sonar Small Chat (8B)",
+      "verification": {
+        "status": "unverified",
+        "verified_at": "2026-01-31",
+        "source": "documentation"
+      },
+      "context_window": 131072,
+      "capabilities": [
+        "chat",
+        "streaming"
+      ],
+      "status": "active",
+      "tags": [
+        "perplexity",
+        "sonar",
+        "chat"
+      ],
+      "pricing": {
+        "input_per_token": 2e-7,
+        "output_per_token": 2e-7
+      }
+    },
+    "llama-3.1-sonar-large-128k-chat": {
+      "provider": "perplexity",
+      "model_id": "llama-3.1-sonar-large-128k-chat",
+      "display_name": "Sonar Large Chat (70B)",
+      "verification": {
+        "status": "unverified",
+        "verified_at": "2026-01-31",
+        "source": "documentation"
+      },
+      "context_window": 131072,
+      "capabilities": [
+        "chat",
+        "streaming"
+      ],
+      "status": "active",
+      "tags": [
+        "perplexity",
+        "sonar",
+        "chat",
+        "large"
+      ],
+      "pricing": {
+        "input_per_token": 0.000001,
+        "output_per_token": 0.000001
+      }
+    }
+  }
+}

package/dist/v1/models/qwen.json

@@ -0,0 +1,49 @@
+{
+  "$schema": "https://raw.githubusercontent.com/ailib-official/ai-protocol/main/schemas/v1.json",
+  "protocol_version": "1.1",
+  "models": {
+    "qwen-max": {
+      "provider": "qwen",
+      "model_id": "qwen-max",
+      "display_name": "Qwen Max",
+      "verification": {
+        "status": "unverified",
+        "source": "manual"
+      },
+      "context_window": 262144,
+      "capabilities": [
+        "chat",
+        "tools",
+        "streaming"
+      ],
+      "status": "active",
+      "tags": [
+        "alibaba",
+        "qwen",
+        "strong"
+      ]
+    },
+    "qwen-turbo": {
+      "provider": "qwen",
+      "model_id": "qwen-turbo",
+      "display_name": "Qwen Turbo",
+      "verification": {
+        "status": "unverified",
+        "source": "manual"
+      },
+      "capabilities": [
+        "chat",
+        "vision",
+        "tools",
+        "streaming",
+        "agentic"
+      ],
+      "status": "active",
+      "tags": [
+        "alibaba",
+        "qwen",
+        "fast"
+      ]
+    }
+  }
+}