RubyGems - ruby_llm-providers-qiniu - Versions diffs - 0.1.1 - Mend

ruby_llm-providers-qiniu 0.1.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (90) hide show

data/models.json ADDED Viewed

@@ -0,0 +1,859 @@
+[
+  {
+    "id": "anthropic/claude-sonnet-5",
+    "name": "Claude Sonnet 5",
+    "provider": "qiniu",
+    "family": "claude-sonnet",
+    "created_at": "2026-06-29 00:00:00 UTC",
+    "context_window": 1000000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2026-01-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls",
+      "batch",
+      "citations"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 2,
+          "output_per_million": 10,
+          "cache_read_input_per_million": 0.2,
+          "cache_write_input_per_million": 2.5
+        }
+      }
+    },
+    "metadata": {
+      "source": "models.dev",
+      "provider_id": "anthropic",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": false,
+      "last_updated": "2026-06-30",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 2,
+        "output": 10,
+        "cache_read": 0.2,
+        "cache_write": 2.5
+      },
+      "limit": {
+        "context": 1000000,
+        "output": 128000
+      },
+      "knowledge": "2026-01-31"
+    }
+  },
+  {
+    "id": "gemini-3.1-flash-lite-preview",
+    "name": "Gemini 3.1 Flash Lite Preview",
+    "provider": "qiniu",
+    "family": "gemini-flash-lite",
+    "created_at": "2026-03-03 00:00:00 UTC",
+    "context_window": 1048576,
+    "max_output_tokens": 65536,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "video",
+        "audio",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "video",
+      "tool_choice",
+      "transcription",
+      "batch",
+      "caching"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.25,
+          "output_per_million": 1.5,
+          "cache_read_input_per_million": 0.025
+        }
+      },
+      "audio_tokens": {
+        "standard": {
+          "input_per_million": 0.5
+        }
+      }
+    },
+    "metadata": {
+      "version": "3.1-flash-lite-preview-03-2026",
+      "description": "Gemini 3.1 Flash Lite Preview",
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent",
+        "batchGenerateContent"
+      ],
+      "source": "models.dev",
+      "provider_id": "google",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-03-03",
+      "status": "deprecated",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "minimal",
+            "low",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.25,
+        "output": 1.5,
+        "cache_read": 0.025,
+        "input_audio": 0.5
+      },
+      "limit": {
+        "context": 1048576,
+        "output": 65536
+      },
+      "knowledge": "2025-01"
+    }
+  },
+  {
+    "id": "google/gemini-3.1-flash-lite",
+    "name": "Gemini 3.1 Flash Lite",
+    "provider": "qiniu",
+    "family": "gemini-flash-lite",
+    "created_at": "2026-05-07 00:00:00 UTC",
+    "context_window": 1048576,
+    "max_output_tokens": 65536,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "video",
+        "audio",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "video",
+      "tool_choice",
+      "transcription",
+      "batch",
+      "caching"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.25,
+          "output_per_million": 1.5,
+          "cache_read_input_per_million": 0.025
+        }
+      },
+      "audio_tokens": {
+        "standard": {
+          "input_per_million": 0.5
+        }
+      }
+    },
+    "metadata": {
+      "version": "3.1-flash-lite-05-2026",
+      "description": "Gemini 3.1 Flash Lite",
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent",
+        "batchGenerateContent"
+      ],
+      "source": "models.dev",
+      "provider_id": "google",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-05-07",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "minimal",
+            "low",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.25,
+        "output": 1.5,
+        "cache_read": 0.025,
+        "input_audio": 0.5
+      },
+      "limit": {
+        "context": 1048576,
+        "output": 65536
+      },
+      "knowledge": "2025-01"
+    }
+  },
+  {
+    "id": "google/gemini-3.8-flash",
+    "name": "Gemini 3.8 Flash",
+    "provider": "qiniu",
+    "family": "gemini-flash",
+    "created_at": "2026-09-02 00:00:00 UTC",
+    "context_window": 1048576,
+    "max_output_tokens": 65536,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "video",
+        "audio",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "video",
+      "tool_choice",
+      "transcription",
+      "batch",
+      "caching"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.75,
+          "output_per_million": 3.75,
+          "cache_read_input_per_million": 0.075
+        }
+      },
+      "audio_tokens": {
+        "standard": {
+          "input_per_million": 0.75
+        }
+      }
+    },
+    "metadata": {
+      "version": "3.0",
+      "description": "Gemini 3.8 Flash",
+      "supported_generation_methods": [
+        "generateContent",
+        "countTokens",
+        "createCachedContent",
+        "batchGenerateContent"
+      ],
+      "source": "models.dev",
+      "provider_id": "google",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-09-02",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "medium",
+            "high"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.75,
+        "output": 3.75,
+        "cache_read": 0.075,
+        "input_audio": 0.75
+      },
+      "limit": {
+        "context": 1048576,
+        "output": 65536
+      }
+    }
+  },
+  {
+    "id": "openai/gpt-6-luna",
+    "name": "GPT-6 Luna",
+    "provider": "qiniu",
+    "family": "gpt-luna",
+    "created_at": "2026-09-22 00:00:00 UTC",
+    "context_window": 1050000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2026-05-18",
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.1,
+          "output_per_million": 0.5,
+          "cache_read_input_per_million": 0.01,
+          "cache_write_input_per_million": 0.125
+        },
+        "long_context": {
+          "input_per_million": 0.2,
+          "output_per_million": 0.75,
+          "cache_read_input_per_million": 0.02,
+          "cache_write_input_per_million": 0.25
+        },
+        "long_context_threshold": 272000
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": false,
+      "last_updated": "2026-09-22",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.1,
+        "output": 0.5,
+        "cache_read": 0.01,
+        "cache_write": 0.125,
+        "tiers": [
+          {
+            "input": 0.2,
+            "output": 0.75,
+            "cache_read": 0.02,
+            "cache_write": 0.25,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.2,
+          "output": 0.75,
+          "cache_read": 0.02,
+          "cache_write": 0.25
+        }
+      },
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "knowledge": "2026-05-18"
+    }
+  },
+  {
+    "id": "openai/gpt-5.6-luna",
+    "name": "GPT-5.6 Luna",
+    "provider": "qiniu",
+    "family": "gpt-luna",
+    "created_at": "2026-07-09 00:00:00 UTC",
+    "context_window": 1050000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2026-02-16",
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.2,
+          "output_per_million": 1.2,
+          "cache_read_input_per_million": 0.02,
+          "cache_write_input_per_million": 0.25
+        },
+        "long_context": {
+          "input_per_million": 0.4,
+          "output_per_million": 1.8,
+          "cache_read_input_per_million": 0.04,
+          "cache_write_input_per_million": 0.5
+        },
+        "long_context_threshold": 272000
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": false,
+      "last_updated": "2026-07-09",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh",
+            "max"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.2,
+        "output": 1.2,
+        "cache_read": 0.02,
+        "cache_write": 0.25,
+        "tiers": [
+          {
+            "input": 0.4,
+            "output": 1.8,
+            "cache_read": 0.04,
+            "cache_write": 0.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 0.4,
+          "output": 1.8,
+          "cache_read": 0.04,
+          "cache_write": 0.5
+        }
+      },
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "knowledge": "2026-02-16"
+    }
+  },
+  {
+    "id": "openai/gpt-5.4",
+    "name": "GPT-5.4",
+    "provider": "qiniu",
+    "family": "gpt",
+    "created_at": "2026-03-05 00:00:00 UTC",
+    "context_window": 1050000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2025-08-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image",
+        "pdf"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 2.5,
+          "output_per_million": 15,
+          "cache_read_input_per_million": 0.25
+        },
+        "long_context": {
+          "input_per_million": 5,
+          "output_per_million": 22.5,
+          "cache_read_input_per_million": 0.5
+        },
+        "long_context_threshold": 272000
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-03-05",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 2.5,
+        "output": 15,
+        "cache_read": 0.25,
+        "tiers": [
+          {
+            "input": 5,
+            "output": 22.5,
+            "cache_read": 0.5,
+            "tier": {
+              "type": "context",
+              "size": 272000
+            }
+          }
+        ],
+        "context_over_200k": {
+          "input": 5,
+          "output": 22.5,
+          "cache_read": 0.5
+        }
+      },
+      "limit": {
+        "context": 1050000,
+        "input": 922000,
+        "output": 128000
+      },
+      "knowledge": "2025-08-31"
+    }
+  },
+  {
+    "id": "openai/gpt-5.4-mini",
+    "name": "GPT-5.4 mini",
+    "provider": "qiniu",
+    "family": "gpt-mini",
+    "created_at": "2026-03-17 00:00:00 UTC",
+    "context_window": 400000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2025-08-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.75,
+          "output_per_million": 4.5,
+          "cache_read_input_per_million": 0.075
+        }
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-03-17",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.75,
+        "output": 4.5,
+        "cache_read": 0.075
+      },
+      "limit": {
+        "context": 400000,
+        "input": 272000,
+        "output": 128000
+      },
+      "knowledge": "2025-08-31"
+    }
+  },
+  {
+    "id": "openai/gpt-5.2",
+    "name": "GPT-5.2",
+    "provider": "qiniu",
+    "family": "gpt",
+    "created_at": "2025-12-11 00:00:00 UTC",
+    "context_window": 400000,
+    "max_output_tokens": 128000,
+    "knowledge_cutoff": "2025-08-31",
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice",
+      "parallel_tool_calls"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 1.75,
+          "output_per_million": 14,
+          "cache_read_input_per_million": 0.175
+        }
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "system",
+      "source": "models.dev",
+      "provider_id": "openai",
+      "open_weights": false,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2025-12-11",
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "effort",
+          "values": [
+            "none",
+            "low",
+            "medium",
+            "high",
+            "xhigh"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 1.75,
+        "output": 14,
+        "cache_read": 0.175
+      },
+      "limit": {
+        "context": 400000,
+        "input": 272000,
+        "output": 128000
+      },
+      "knowledge": "2025-08-31"
+    }
+  },
+  {
+    "id": "deepseek/deepseek-v4.1-flash",
+    "name": "DeepSeek V4.1 Flash",
+    "provider": "qiniu",
+    "family": "deepseek-flash",
+    "created_at": "2026-09-10 00:00:00 UTC",
+    "context_window": 1000000,
+    "max_output_tokens": 393216,
+    "knowledge_cutoff": null,
+    "modalities": {
+      "input": [
+        "text",
+        "image"
+      ],
+      "output": [
+        "text"
+      ]
+    },
+    "capabilities": [
+      "function_calling",
+      "structured_output",
+      "reasoning",
+      "vision",
+      "tool_choice"
+    ],
+    "pricing": {
+      "text_tokens": {
+        "standard": {
+          "input_per_million": 0.15,
+          "output_per_million": 0.6,
+          "cache_read_input_per_million": 0.003,
+          "reasoning_output_per_million": 0.6
+        }
+      }
+    },
+    "metadata": {
+      "object": "model",
+      "owned_by": "deepseek",
+      "source": "models.dev",
+      "provider_id": "deepseek",
+      "open_weights": true,
+      "attachment": true,
+      "temperature": true,
+      "last_updated": "2026-09-10",
+      "interleaved": {
+        "field": "reasoning_content"
+      },
+      "tool_call": true,
+      "structured_output": true,
+      "reasoning": true,
+      "reasoning_options": [
+        {
+          "type": "toggle"
+        },
+        {
+          "type": "effort",
+          "values": [
+            "low",
+            "high",
+            "max"
+          ]
+        }
+      ],
+      "cost": {
+        "input": 0.15,
+        "output": 0.6,
+        "reasoning": 0.6,
+        "cache_read": 0.003
+      },
+      "limit": {
+        "context": 1000000,
+        "output": 393216
+      },
+      "knowledge": "2025-05"
+    }
+  }
+]