{
  "object": "list",
  "data": [
    {
      "id": "amazon-nova-2-lite",
      "object": "model",
      "created": 1764633600,
      "owned_by": "Amazon",
      "display_name": "amazon-nova-2-lite",
      "description": "Multimodal reasoning model for visual analysis, planning, and tool use",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.33,
        "completion": 2.75,
        "cache_read": 0.0825,
        "cache_write": 0.33
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5",
      "object": "model",
      "created": 1770854400,
      "owned_by": "zAI",
      "display_name": "glm-5",
      "description": "General GLM flagship for coding, analysis, and tool-heavy engineering workflows",
      "context_window": 202752,
      "context_length": 202752,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1,
        "completion": 3.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen3-coder-next",
      "object": "model",
      "created": 1770076800,
      "owned_by": "Alibaba Cloud",
      "display_name": "qwen3-coder-next",
      "description": "Open-weight Qwen coding model for agents, repository edits, and multi-turn tool use",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.5,
        "completion": 1.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "garda-core",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Neosantara",
      "display_name": "garda-core",
      "description": "Experimental models 1M ctx from Neosantara with high capability of coding",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 300,
        "completion": 1500
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "archipelago-core-70b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Neosantara",
      "display_name": "archipelago-core-70b",
      "description": "Specialized model for Indonesian language content with cultural context awareness",
      "context_window": 24000,
      "context_length": 24000,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 4710,
        "completion": 36543
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "garda-agentic-mini",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Neosantara",
      "display_name": "garda-agentic-mini",
      "description": "DEPRECATED - Use garda-core or gpt-oss-120b instead.",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 2500,
        "completion": 10499
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "web_search",
        "code_execution",
        "structured_output"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "garda-core",
        "gpt-oss-120b"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemma-3-27b-it",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "gemma-3-27b-it",
      "description": "Lightweight, state-of the art, open model built from the same technology that powers Gemini models.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 200,
        "completion": 1500
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.1-pro",
      "object": "model",
      "created": 1781827200,
      "owned_by": "Google",
      "display_name": "gemini-3.1-pro",
      "description": "Google Gemini 3.1 Pro model for complex tasks.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 12,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.5-flash",
      "object": "model",
      "created": 1779235200,
      "owned_by": "Google",
      "display_name": "gemini-3.5-flash",
      "description": "Google Gemini Flash model optimized for fast, cost-efficient general-purpose tasks.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 2400,
      "max_completion_tokens": 2400,
      "pricing": {
        "currency": "USD",
        "prompt": 1.5,
        "completion": 9,
        "cache_read": 0.15,
        "cache_write": 1.5
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.6-flash",
      "object": "model",
      "created": 1784592000,
      "owned_by": "Google",
      "display_name": "gemini-3.6-flash",
      "description": "Google's workhorse model, an addition to the Gemini 3 series of highly-capable, natively multimodal, reasoning models that delivers better coding, knowledge work, and multimodal performance with better token-efficiency.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.5,
        "completion": 7.5,
        "cache_read": 0.15,
        "cache_write": 1.5
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-4-argon",
      "object": "model",
      "created": 1793145600,
      "owned_by": "Google",
      "display_name": "gemini-4-argon",
      "description": "Google Gemini 4 Argon is a frontier reasoning and long-horizon multimodal model with a 1M token context window, built for complex problem-solving, code execution, and agentic workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 10
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-4-hydrogen",
      "object": "model",
      "created": 1794528000,
      "owned_by": "Google",
      "display_name": "Gemini 4 Hydrogen",
      "description": "Google Gemini 4 Hydrogen is a frontier multimodal reasoning model with a 1M token context window, supporting advanced reasoning levels, native web search, and cross-modal understanding.",
      "context_window": 1048576,
      "context_length": 1048576,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.5,
        "completion": 7.5
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning",
        "web_search"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 70,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.8-flash",
      "object": "model",
      "created": 1788393600,
      "owned_by": "Google",
      "display_name": "gemini-3.8-flash",
      "description": "The latest iteration in the Gemini 3 model family, featuring advanced multimodal capabilities and dynamic thinking budget control for coding, analysis, and conversational tasks.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.75,
        "completion": 3.75
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 80,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.7-flash",
      "object": "model",
      "created": 1786579200,
      "owned_by": "Google",
      "display_name": "gemini-3.7-flash",
      "description": "The next iteration in the Gemini 3 model family, featuring algorithmic improvements to its core reasoning foundation and customizable thinking configurations to control the mix of quality, cost, and latency.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.5,
        "completion": 7.5,
        "cache_read": 0.15,
        "cache_write": 1.5
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3.1-flash-lite",
      "object": "model",
      "created": 1781827200,
      "owned_by": "Google",
      "display_name": "gemini-3.1-flash-lite",
      "description": "Google Gemini 3.1 Flash Lite model for fast and efficient tasks.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.25,
        "completion": 1.5,
        "cache_read": 0.025
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-3-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "gemini-3-flash",
      "description": "Google most intelligent model built for speed, combining frontier intelligence with superior search and grounding.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 2400,
      "max_completion_tokens": 2400,
      "pricing": {
        "currency": "USD",
        "prompt": 0.5,
        "completion": 3,
        "cache_read": 0.1,
        "cache_write": 0.03
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-sonnet-4-6",
      "object": "model",
      "created": 1779408000,
      "owned_by": "Anthropic",
      "display_name": "claude-sonnet-4-6",
      "description": "Anthropic Claude Sonnet 4.6 is the most capable Sonnet model, upgraded for coding, computer use, long-context reasoning, agent planning, knowledge work, and design.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15,
        "cache_read": 0.3,
        "cache_write": 3.75,
        "cache_write_5m": 3.75,
        "cache_write_1h": 6
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-opus-4-6",
      "object": "model",
      "created": 1779408000,
      "owned_by": "Anthropic",
      "display_name": "claude-opus-4-6",
      "description": "Anthropic Claude Opus 4.6 is a hybrid reasoning model for frontier coding, AI agents, complex enterprise workflows, and high-stakes reasoning.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 25,
        "cache_read": 0.5,
        "cache_write": 6.25,
        "cache_write_5m": 6.25,
        "cache_write_1h": 10
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-opus-5.5",
      "object": "model",
      "created": 1790035200,
      "owned_by": "Anthropic",
      "display_name": "claude-opus-5.5",
      "description": "Claude Opus 5.5 is Anthropic's flagship model for agentic coding, deep reasoning, and autonomous multi-step operations with always-on adaptive thinking.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 4,
        "completion": 20
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning",
        "computer_use"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-sonnet-5.5",
      "object": "model",
      "created": 1793145600,
      "owned_by": "Anthropic",
      "display_name": "claude-sonnet-5.5",
      "description": "Claude Sonnet 5.5 is Anthropic's advanced model for high-intelligence reasoning, coding, and autonomous tool workflows.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "computer_use",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-6-luna",
      "object": "model",
      "created": 1790035200,
      "owned_by": "OpenAI",
      "display_name": "gpt-6-luna",
      "description": "GPT-6 Luna is OpenAI's lightweight, high-speed reasoning model optimized for low-latency subagent tasks, rapid exploration, and high-throughput operations.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 0.1,
        "completion": 0.5
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.4-mini",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.4-mini",
      "description": "GPT-5.4 Mini model with agentic reasoning and fast responses",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.75,
        "completion": 4.5,
        "cache_read": 0.075,
        "cache_write": 0.75
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5-nano",
      "object": "model",
      "created": 1754524800,
      "owned_by": "OpenAI",
      "display_name": "gpt-5-nano",
      "description": "GPT-5 nano is a high throughput model that excels at simple instruction or classification tasks.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 810,
        "completion": 6485
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning",
        "vision",
        "file_input"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.4-nano",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.4-nano",
      "description": "GPT 5.4 Nano is the smallest and most affordable model in the GPT-5.4 family for high-volume sub-agent workflows.",
      "context_window": 400000,
      "context_length": 400000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 3240,
        "completion": 20250
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning",
        "vision",
        "file_input",
        "web_search"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "text-embedding-3-small",
      "object": "model",
      "created": 1706140800,
      "owned_by": "OpenAI",
      "display_name": "text-embedding-3-small",
      "description": "OpenAI Text Embedding 3 Small. Highly efficient and cost-effective embedding model for search, clustering, and classification tasks.",
      "context_window": 8191,
      "context_length": 8191,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.02,
        "completion": 0
      },
      "capabilities": [
        "embeddings"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 131000,
      "context_length": 131000,
      "max_output_tokens": 128000,
      "max_completion_tokens": 128000,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-4.5-sonnet",
      "object": "model",
      "created": 1759104000,
      "owned_by": "Anthropic",
      "display_name": "claude-4.5-sonnet",
      "description": "DEPRECATED - Claude Sonnet 4.5 is deprecated and legacy. Use claude-sonnet-4-6 instead.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15,
        "cache_read": 0.3,
        "cache_write": 3.75,
        "cache_write_5m": 3.75,
        "cache_write_1h": 6
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-sonnet-4-6"
      ],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-4.5-opus",
      "object": "model",
      "created": 1761955200,
      "owned_by": "Anthropic",
      "display_name": "claude-4.5-opus",
      "description": "Claude 4.5 Opus is Anthropic's most powerful model, designed for highly complex tasks, deep reasoning, and creative endeavors with a massive context window.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 25,
        "cache_read": 0.5,
        "cache_write": 6.25,
        "cache_write_5m": 6.25,
        "cache_write_1h": 10
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "imagen-4.0-fast",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "imagen-4.0-fast",
      "description": "Google Imagen 4 Fast. High-speed, high-quality image generation.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_image": {
          "1024x1024": 0.02
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-code-fast",
      "object": "model",
      "created": 1756166400,
      "owned_by": "xAI",
      "display_name": "grok-code-fast",
      "description": "Deprecated alias for xai/grok-code-fast-1. Migrated to Grok 4.3.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.2,
        "completion": 1.5,
        "cache_read": 0.05,
        "cache_write": 0.13
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "grok-4.3"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-4.1-fast-non-reasoning",
      "object": "model",
      "created": 1763510400,
      "owned_by": "xAI",
      "display_name": "grok-4.1-fast-non-reasoning",
      "description": "Grok 4.1 Fast is a strong tool-calling model designed for agentic tasks with low-latency responses for practical workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 2.5,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-4.1-fast-reasoning",
      "object": "model",
      "created": 1763510400,
      "owned_by": "xAI",
      "display_name": "grok-4.1-fast-reasoning",
      "description": "Grok 4.1 Fast Reasoning variant optimized for tool use with stronger reasoning depth.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 2.5,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-4.20-non-reasoning",
      "object": "model",
      "created": 1773100800,
      "owned_by": "xAI",
      "display_name": "grok-4.20-non-reasoning",
      "description": "Grok 4.20 Non-Reasoning variant for fast tool-calling and low-latency workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 2.5,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "function_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "grok-4.1-fast-non-reasoning"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-4.3",
      "object": "model",
      "created": 1778803200,
      "owned_by": "xAI",
      "display_name": "grok-4.3",
      "description": "Grok 4.3 is a large-context xAI model for reasoning and tool-enabled workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 2.5,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning",
        "vision",
        "file_input",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "grok-imagine-image",
      "object": "model",
      "created": 1772409600,
      "owned_by": "xAI",
      "display_name": "grok-imagine-image",
      "description": "xAI Grok Imagine Image model for high-quality image generation.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_image": {
          "1024x1024": 0.02
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4-flash",
      "object": "model",
      "created": 1785456000,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4-flash",
      "description": "High-speed Mixture-of-Experts (MoE) model with 284B total parameters (13B active) and 1M context window. Built for real-time interactive chats, quick reasoning tasks, web search grounding, and lightweight agentic pipelines.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.22,
        "completion": 0.66,
        "cache_read": 0.007,
        "peak_windows": {
          "multiplier": 2,
          "timezone": "UTC",
          "days": [
            1,
            2,
            3,
            4,
            5
          ],
          "windows": [
            [
              "01:00",
              "04:00"
            ],
            [
              "06:00",
              "10:00"
            ]
          ],
          "applies_to": [
            "input",
            "output",
            "cache_read"
          ]
        }
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning",
        "implicit_caching",
        "web_search"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 0,
      "limitations": {
        "pricing_notes": [
          "Off-peak rate shown (17h/day on weekdays plus all weekend): $0.22 input / $0.66 output / $0.007 cache read per 1M tokens.",
          "Peak rate doubles to $0.44 input / $1.32 output / $0.014 cache read, 01:00-04:00 and 06:00-10:00 UTC, Monday-Friday."
        ]
      },
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4-pro",
      "object": "model",
      "created": 1786579200,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4-pro",
      "description": "Flagship Mixture-of-Experts (MoE) reasoning model with 1.6T total parameters, 49B active parameters, and Engram memory architecture. Excels in complex STEM problem solving, full-repository coding, and multi-agent coordination with 1M context window.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.66,
        "completion": 1.98,
        "cache_read": 0.022,
        "peak_windows": {
          "multiplier": 2,
          "timezone": "UTC",
          "days": [
            1,
            2,
            3,
            4,
            5
          ],
          "windows": [
            [
              "01:00",
              "04:00"
            ],
            [
              "06:00",
              "10:00"
            ]
          ],
          "applies_to": [
            "input",
            "output",
            "cache_read"
          ]
        }
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning",
        "implicit_caching",
        "web_search"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 0,
      "limitations": {
        "pricing_notes": [
          "Off-peak rate shown (17h/day on weekdays plus all weekend): $0.66 input / $1.98 output / $0.022 cache read per 1M tokens.",
          "Peak rate doubles to $1.32 input / $3.96 output / $0.044 cache read, 01:00-04:00 and 06:00-10:00 UTC, Monday-Friday."
        ]
      },
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4-flash-0731",
      "object": "model",
      "created": 1785456000,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4-flash-0731",
      "description": "DeepSeek-V4-Flash-0731 is an ultra-fast 284B MoE (13B active) model engineered for sub-second latency, 1M context processing, structured JSON extraction, and multi-turn function calling in high-volume agentic applications.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.14,
        "completion": 0.28,
        "cache_read": 0.03
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 0,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4-pro-0813",
      "object": "model",
      "created": 1786579200,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4-pro-0813",
      "description": "DeepSeek-V4-Pro-0813 is a 1.65T parameter (49B active) production MoE model featuring integrated DSpark speculative decoding, 1M token context support, native tool use, and configurable reasoning effort levels for complex engineering workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.32,
        "completion": 3.96,
        "cache_read": 0.13
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 0,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.7-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.7-flash",
      "description": "GLM 4.7 Flash, a fast and efficient model with 0 cost (free).",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-3.1-8b-wse",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Meta",
      "display_name": "llama-3.1-8b-wse",
      "description": "Llama 3.1 8B optimized for Wafer-Scale Engine. Provides ultra-high speed inference (2,000+ tokens/s) for real-time applications.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 100,
        "completion": 100
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen3-235b-wse",
      "object": "model",
      "created": 1751328000,
      "owned_by": "Alibaba Cloud",
      "display_name": "qwen3-235b-wse",
      "description": "Qwen 3 235B on Wafer-Scale Engine. High-intelligence model with massive parameter count and hardware-accelerated inference speed.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 1800,
        "completion": 1800
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-image-2",
      "object": "model",
      "created": 1776729600,
      "owned_by": "OpenAI",
      "display_name": "gpt-image-2",
      "description": "GPT Image 2. Advanced image generation and editing model by OpenAI.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_image": {
          "1024x1024": 0.04
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "codestral-2",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Mistral",
      "display_name": "codestral-2",
      "description": "Codestral (2508) model, specialized for code generation.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.3,
        "completion": 0.9
      },
      "capabilities": [
        "text_generation",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-spark-1.1",
      "object": "model",
      "created": 1783555200,
      "owned_by": "Meta",
      "display_name": "muse-spark-1.1",
      "description": "Meta Muse Spark 1.1. Multimodal frontier reasoning model optimized for tool use, computer operations, code generation, and multi-step planning.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 4.25,
        "cache_read": 0.15
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-spark-1.2",
      "object": "model",
      "created": 1786752000,
      "owned_by": "Meta",
      "display_name": "muse-spark-1.2",
      "description": "Meta Muse Spark 1.2. Multimodal frontier reasoning model optimized for code generation and agentic workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 4.25,
        "cache_read": 0.15
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-spark-1.2-contributor",
      "object": "model",
      "created": 1786752000,
      "owned_by": "Meta",
      "display_name": "muse-spark-1.2-contributor",
      "description": "Meta Muse Spark 1.2 Contributor. Cost-optimized option for agentic coding workflows with high throughput.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.1,
        "completion": 0.2,
        "cache_read": 0.002
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-spark-1.3",
      "object": "model",
      "created": 1788220800,
      "owned_by": "Meta",
      "display_name": "muse-spark-1.3",
      "description": "Meta Muse Spark 1.3. Flagship multimodal reasoning model for long-horizon agentic and coding workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.25,
        "completion": 4.25,
        "cache_read": 0.15
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-spark-1.3-contributor",
      "object": "model",
      "created": 1788220800,
      "owned_by": "Meta",
      "display_name": "muse-spark-1.3-contributor",
      "description": "Meta Muse Spark 1.3 Contributor. High efficiency and cost-optimized API option for agentic coding workflows.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.1,
        "completion": 0.2,
        "cache_read": 0.002
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-wonder-1.0",
      "object": "model",
      "created": 1791849600,
      "owned_by": "Meta",
      "display_name": "muse-wonder-1.0",
      "description": "Meta Muse Wonder 1.0. Flagship multimodal frontier reasoning model with 1M context window for complex problem solving, coding, and autonomous agents.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 4,
        "completion": 20,
        "cache_read": 0.2
      },
      "capabilities": [
        "text_generation",
        "vision",
        "audio_input",
        "video_understanding",
        "file_input",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-ember-1.0",
      "object": "model",
      "created": 1794182400,
      "owned_by": "Meta",
      "display_name": "muse-ember-1.0",
      "description": "Meta Muse Ember 1.0. Fast multimodal reasoning model with a 1M token context window, optimized for high-volume agentic pipelines, tool calling, structured extraction, and long-document parsing.",
      "context_window": 1048576,
      "context_length": 1048576,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.1,
        "completion": 0.5,
        "cache_read": 0.004,
        "long_context": {
          "threshold_input_tokens": 200000,
          "multiplier": 3,
          "applies_to": [
            "input",
            "output",
            "cache_read"
          ]
        }
      },
      "capabilities": [
        "text_generation",
        "vision",
        "audio_input",
        "video_understanding",
        "file_input",
        "function_calling",
        "reasoning",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "ling-3.0-flash-fin",
      "object": "model",
      "created": 1773792000,
      "owned_by": "InclusionAI",
      "display_name": "ling-3.0-flash-fin",
      "description": "Ling 3.0 Flash Fin is a finance-enhanced Mixture-of-Experts language model with a 256K context window, engineered for financial research, investment analysis, multi-step planning, coding, and tool use.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "sea-lion-v4-27b-it",
      "object": "model",
      "created": 1700000000,
      "owned_by": "AI Singapore",
      "display_name": "sea-lion-v4-27b-it",
      "description": "SEA-LION v4: State-of-the-art multimodal LLM specialized for Southeast Asian languages including Bahasa Indonesia, with native-level fluency and cultural context understanding",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 350,
        "completion": 560
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mistral-nemotron",
      "object": "model",
      "created": 1700000000,
      "owned_by": "NVIDIA",
      "display_name": "mistral-nemotron",
      "description": "DEPRECATED - Use nemotron-3-nano-30b or llama-3.2-11b-vision instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 4560,
        "completion": 31991
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "nemotron-3-nano-30b",
        "llama-3.2-11b-vision"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "granite-3-8b-instruct",
      "object": "model",
      "created": 1700000000,
      "owned_by": "IBM",
      "display_name": "granite-3-8b-instruct",
      "description": "Granite-3.1-8B-Instruct is an 8B long-context instruction model tuned from Granite-3.1-8B-Base using open instruction datasets and synthetic data designed for long-context tasks.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 2880,
        "completion": 11520
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-3.3-nemotron-super-49b-v1.5",
      "object": "model",
      "created": 1700000000,
      "owned_by": "NVIDIA",
      "display_name": "llama-3.3-nemotron-super-49b-v1.5",
      "description": "DEPRECATED - Use nemotron-3-super-120b or nemotron-3-nano-30b instead.",
      "context_window": 132000,
      "context_length": 132000,
      "max_output_tokens": 128000,
      "max_completion_tokens": 128000,
      "pricing": {
        "currency": "IDR",
        "prompt": 4560,
        "completion": 31991
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "nemotron-3-super-120b",
        "nemotron-3-nano-30b"
      ],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "minimax-m2.5",
      "object": "model",
      "created": 1700000000,
      "owned_by": "MiniMax",
      "display_name": "minimax-m2.5",
      "description": "DEPRECATED - Use llama-3.2-11b-vision instead.",
      "context_window": 204800,
      "context_length": 204800,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 4560,
        "completion": 31991
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "llama-3.2-11b-vision"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "step-3.5-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Other",
      "display_name": "step-3.5-flash",
      "description": "DEPRECATED - Use nemotron-3-nano-30b or nemotron-3.5-lightning-30b instead.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "IDR",
        "prompt": 3000,
        "completion": 9000
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "reasoning",
        "function_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "nemotron-3-nano-30b",
        "nemotron-3.5-lightning-30b"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-3.2-11b-vision",
      "object": "model",
      "created": 1791849600,
      "owned_by": "Meta",
      "display_name": "llama-3.2-11b-vision",
      "description": "Llama 3.2 11B Vision is an efficient multimodal model by Meta supporting high-resolution image analysis, tool calling, and fast multilingual dialogue.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 1500,
        "completion": 4500
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "nemotron-3-nano-30b",
      "object": "model",
      "created": 1791849600,
      "owned_by": "NVIDIA",
      "display_name": "nemotron-3-nano-30b",
      "description": "Nemotron 3 Nano Omni 30B is an advanced reasoning model by NVIDIA featuring native chain-of-thought, tool calling, and high-speed logical inference.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 3000,
        "completion": 9000
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "nemotron-3.5-lightning-30b",
      "object": "model",
      "created": 1791849600,
      "owned_by": "NVIDIA",
      "display_name": "nemotron-3.5-lightning-30b",
      "description": "Nemotron 3.5 Lightning 30B is a high-efficiency MoE reasoning model by NVIDIA optimized for rapid logical deduction and multi-step reasoning.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 3000,
        "completion": 9000
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "nemotron-3-super-120b",
      "object": "model",
      "created": 1791849600,
      "owned_by": "NVIDIA",
      "display_name": "nemotron-3-super-120b",
      "description": "Nemotron 3 Super 120B is a large-scale MoE reasoning model by NVIDIA for complex reasoning, programming, and mathematics.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 4560,
        "completion": 31991
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "hermes-2-pro-mistral-7b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Mistral AI",
      "display_name": "hermes-2-pro-mistral-7b",
      "description": "Flagship 7B model optimized for advanced instruction following, Function Calling, and precise JSON output.",
      "context_window": 24000,
      "context_length": 24000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 450,
        "completion": 1200
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "command-a",
      "object": "model",
      "created": 1772323200,
      "owned_by": "Cohere",
      "display_name": "command-a",
      "description": "Cohere Command A, a state-of-the-art language model optimized for agentic workflows, function calling, structured output, and multilingual tasks.",
      "context_window": 288000,
      "context_length": 288000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "command-a-plus",
      "object": "model",
      "created": 1777593600,
      "owned_by": "Cohere",
      "display_name": "command-a-plus",
      "description": "Cohere Command A Plus (05-2026), a flagship reasoning model featuring deep analytical chain-of-thought, native tool calling, and long-context processing.",
      "context_window": 436000,
      "context_length": 436000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "north-mini-code",
      "object": "model",
      "created": 1788220800,
      "owned_by": "Cohere",
      "display_name": "north-mini-code",
      "description": "North Mini Code (1.0), a 30B total / 3B active parameter MoE model trained specifically for agentic coding, tool calling, and structured outputs.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemma2-9b-it",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "gemma2-9b-it",
      "description": "Gemma is a family of lightweight, state-of-the-art open models from Google, built from the same research and technology used to create the Gemini models.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 200,
        "completion": 1000
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen3.8-27b",
      "object": "model",
      "created": 1791590400,
      "owned_by": "Alibaba Cloud",
      "display_name": "qwen3.8-27b",
      "description": "Qwen 3.8 27B is an advanced multilingual multimodal model with 131K context window, ultra-fast inference speed, and native support for vision understanding, tool calling, and structured outputs.",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 0.8,
        "completion": 4,
        "cache_read": 0.4
      },
      "capabilities": [
        "text_generation",
        "vision",
        "json_mode",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-oss-20b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "gpt-oss-20b",
      "description": "Medium-sized open-weight model for low latency",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 400,
        "completion": 1600
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-oss-120b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "gpt-oss-120b",
      "description": "GPT-OSS-120B — powerful open-source foundation model.",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.15,
        "completion": 0.6,
        "cache_read": 0.075
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-3.2-11b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Meta",
      "display_name": "llama-3.2-11b",
      "description": "Llama 3.2 11B - Efficient lightweight model for general conversation and text generation tasks.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 100,
        "completion": 400
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "minimax-m3",
      "object": "model",
      "created": 1782864000,
      "owned_by": "MiniMax",
      "display_name": "minimax-m3",
      "description": "MiniMax-M3 is a high-performance multimodal model supporting large context windows, json mode, and tool calling.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.6,
        "completion": 1.2,
        "cache_read": 0.12
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "jev",
      "object": "model",
      "created": 1790294400,
      "owned_by": "TypeSafe AI",
      "display_name": "jev",
      "description": "TypeSafe AI Jev evaluation model for fast, structured decisions in software (classification, routing, rubric-based assessment).",
      "context_window": 32000,
      "context_length": 32000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.042,
        "completion": 0
      },
      "capabilities": [
        "evaluation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "minimax-m3-free",
      "object": "model",
      "created": 1787616000,
      "owned_by": "MiniMax",
      "display_name": "minimax-m3-free",
      "description": "MiniMax-M3 (free) is a frontier multimodal model with a 1M-token context window, vision, and tool calling.",
      "context_window": 1048576,
      "context_length": 1048576,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "promotion_exhausted",
        "code": "promotion_exhausted",
        "message": "Promotion for MiniMax-M3 (free) is exhausted. Please use minimax-m3 instead."
      }
    },
    {
      "id": "minimax-m2.7-free",
      "object": "model",
      "created": 1787616000,
      "owned_by": "MiniMax",
      "display_name": "minimax-m2.7-free",
      "description": "MiniMax-M2.7 (free) is a massive 230B reasoning model, optimized for complex software engineering and agentic workflows with native thinking process.",
      "context_window": 196608,
      "context_length": 196608,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "promotion_exhausted",
        "code": "promotion_exhausted",
        "message": "Promotion for MiniMax-M2.7 (free) is exhausted. Please use minimax-m2.7 instead."
      }
    },
    {
      "id": "pixel-canary",
      "object": "model",
      "created": 1787356800,
      "owned_by": "Stealth",
      "display_name": "pixel-canary",
      "description": "Pixel Canary is an anonymous large model with strong coding capabilities and adjustable reasoning effort. It is well suited to web and mobile app development, helping developers build and refine applications across both platforms.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "vision"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "neosantara-gen-2045",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Neosantara",
      "display_name": "neosantara-gen-2045",
      "description": "The flagship image generation model of Neosantara AI, delivering high-quality visual content with optimal speed and artistic precision.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "per_image": {
          "1024x1024": 1500,
          "512x512": 800,
          "256x256": 400
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "sdxl-lightning",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Stability AI",
      "display_name": "sdxl-lightning",
      "description": "SDXL-Lightning is the most affordable image generation model on Neosantara. It generates high-quality 1024px images in just 4 steps.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "per_image": {
          "1024x1024": 200,
          "512x512": 120,
          "256x256": 60
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "stable-diffusion-v1-5-img2img",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Stability AI",
      "display_name": "stable-diffusion-v1-5-img2img",
      "description": "Stable Diffusion v1.5 Image-to-Image. Generate a new image from an input image and a text prompt.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "per_image": {
          "1024x1024": 200,
          "512x512": 120,
          "256x256": 60
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-guard-3-8b",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Meta",
      "display_name": "llama-guard-3-8b",
      "description": "Llama Guard 3 is a safeguards model fine-tuned for content safety classification. It can classify both LLM inputs and responses.",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 256,
      "max_completion_tokens": 256,
      "pricing": {
        "currency": "IDR",
        "prompt": 7680,
        "completion": 480
      },
      "capabilities": [
        "text_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "nv-embed-v1",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Other",
      "display_name": "nv-embed-v1",
      "description": "DEPRECATED - Use nemotron-3-embed-1b instead.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 0
      },
      "capabilities": [
        "embeddings"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "nemotron-3-embed-1b"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "nemotron-3-embed-1b",
      "object": "model",
      "created": 1791849600,
      "owned_by": "NVIDIA",
      "display_name": "nemotron-3-embed-1b",
      "description": "Nemotron 3 Embed 1B is a high-accuracy text embedding model by NVIDIA with 2048-dimensional vector representations.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 0
      },
      "capabilities": [
        "embeddings"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2:latest",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2:latest",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2:search",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2:search",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation",
        "web_search"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2:research",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2:research",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k1",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k1",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2:math",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2:math",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2:silent",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2:silent",
      "description": "DEPRECATED - Use kimi-k2-thinking or kimi-k2.5 instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 16642,
        "completion": 49929
      },
      "capabilities": [
        "text_generation",
        "vision",
        "file_interpretation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k2-thinking",
        "kimi-k2.5"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.6",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.6",
      "description": "GLM-4.6 is the latest reasoning model from Z.ai, achieving SOTA performance on coding and agent benchmarks while offering improved conversational chats.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 10000,
        "completion": 30000
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.6-plus",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.6-plus",
      "description": "GLM-4.6-plus is more powerfull coding context.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 10000,
        "completion": 30000
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.6v-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.6v-flash",
      "description": "A lightweight multimodal model from Z.ai with 128K context and native tool use support.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 250,
        "completion": 750
      },
      "capabilities": [
        "text_generation",
        "vision",
        "video_understanding",
        "file_interpretation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.5-flash",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.5-flash",
      "description": "A lightweight and efficient flash model.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 250,
        "completion": 750
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5v-turbo",
      "object": "model",
      "created": 1775001600,
      "owned_by": "zAI",
      "display_name": "glm-5v-turbo",
      "description": "Z.ai GLM-5V-Turbo multimodal vision and coding foundation model. Supports visual reasoning, coding agent workflows, tool use, and long-horizon planning.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.2,
        "completion": 4,
        "cache_read": 0.24
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "vision",
        "file_input",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-4.7",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-4.7",
      "description": "Latest generation GLM model with improved reasoning and coding.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "IDR",
        "prompt": 10000,
        "completion": 30000
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "whisper-large-v3-turbo",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "whisper-large-v3-turbo",
      "description": "Whisper Large v3 Turbo is OpenAI's fastest speech recognition model optimized for speed while maintaining high accuracy. This model delivers exceptional performance with optimized speed, high accuracy across diverse audio conditions, and multilingual support. Built on OpenAI's optimized transformer architecture, it features streamlined processing for enhanced speed while preserving the core capabilities of the Whisper family. The model incorporates efficiency improvements and optimizations that reduce computational overhead without sacrificing transcription quality, making it perfect for time-sensitive applications.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_second": 0.000012
      },
      "capabilities": [
        "audio_transcription"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "whisper-large-v3",
      "object": "model",
      "created": 1700000000,
      "owned_by": "OpenAI",
      "display_name": "whisper-large-v3",
      "description": "Whisper Large v3 is OpenAI's state-of-the-art speech recognition model, providing high accuracy across diverse audio conditions and multilingual support.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_second": 0.000030833
      },
      "capabilities": [
        "audio_transcription"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mistral-voxtral-mini",
      "object": "model",
      "created": 1751328000,
      "owned_by": "Mistral AI",
      "display_name": "mistral-voxtral-mini",
      "description": "Mistral Voxtral Mini is a multimodal audio model designed for high-efficiency audio understanding, transcription, and reasoning.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.04,
        "completion": 0.04
      },
      "capabilities": [
        "audio_transcription"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen3.6-35b-a3b-mtp",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Alibaba Cloud",
      "display_name": "qwen3.6-35b-a3b-mtp",
      "description": "Qwen 3.6 35B is an advanced Mixture-of-Experts (MoE) model featuring Multi-Token Prediction (MTP) for accelerated generation speed, repository-level reasoning, and highly accurate multilingual responses.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemma-4-e2b-it",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "gemma-4-e2b-it",
      "description": "Gemma 4 E2B-it is an edge-optimized instruction-tuned model from Google DeepMind, offering state-of-the-art efficiency for local and edge execution with multimodal inputs.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 100,
        "completion": 400
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "sahabatai-lion-9b-ties-v1",
      "object": "model",
      "created": 1700000000,
      "owned_by": "GoTo",
      "display_name": "sahabatai-lion-9b-ties-v1",
      "description": "SahabatAI Lion 9B is a high-performance Indonesian language model fine-tuned for high fluency, cultural nuance, and localized context in Indonesian workflows.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen-sea-lion-v4-8b-vl",
      "object": "model",
      "created": 1700000000,
      "owned_by": "AI Singapore",
      "display_name": "qwen-sea-lion-v4-8b-vl",
      "description": "Qwen SEA-LION v4 8B VL is a specialized multimodal Vision-Language model developed by AI Singapore, optimized for Southeast Asian languages and cultural contexts.",
      "context_window": 32768,
      "context_length": 32768,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation",
        "vision"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-sea-lion-v3-8b-it",
      "object": "model",
      "created": 1700000000,
      "owned_by": "AI Singapore",
      "display_name": "llama-sea-lion-v3-8b-it",
      "description": "Llama SEA-LION v3 8B IT is an instruction-tuned Southeast Asian regional model developed by AI Singapore.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama3-8b-cpt-sahabatai-instruct",
      "object": "model",
      "created": 1700000000,
      "owned_by": "GoTo",
      "display_name": "llama3-8b-cpt-sahabatai-instruct",
      "description": "Llama3 8B CPT SahabatAI is an Indonesian-adapted instruction-tuned language model fine-tuned for high Indonesian fluency and localization.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemma2-9b-cpt-sahabatai-instruct",
      "object": "model",
      "created": 1700000000,
      "owned_by": "GoTo",
      "display_name": "gemma2-9b-cpt-sahabatai-instruct",
      "description": "Gemma2 9B CPT SahabatAI is a high-performance regional model optimized for Indonesian cultural nuance and localized instruction-following.",
      "context_window": 8192,
      "context_length": 8192,
      "max_output_tokens": 2048,
      "max_completion_tokens": 2048,
      "pricing": {
        "currency": "IDR",
        "prompt": 150,
        "completion": 600
      },
      "capabilities": [
        "text_generation",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.6-luna",
      "object": "model",
      "created": 1783555200,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.6-luna",
      "description": "DEPRECATED - Use gpt-6-luna instead. GPT 5.6 LUNA served on Kiro and managed by Neosantara. A fast, cost-efficient GPT-5.6 model for text generation, coding, reasoning, and autonomous tool use. Text-only; native JSON mode, forced tool choice, multiple output choices, and advanced OpenAI sampling controls are not supported by the upstream Kiro backend.",
      "context_window": 272000,
      "context_length": 272000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.2,
        "completion": 1.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "gpt-6-luna"
      ],
      "limitations": {
        "supported_parameters": [
          "reasoning_effort"
        ],
        "ignored_parameters": [
          "tool_choice",
          "response_format",
          "top_p",
          "frequency_penalty",
          "presence_penalty",
          "logit_bias",
          "seed"
        ],
        "parameter_notes": {
          "tool_choice": "The model decides autonomously whether to call tools; callers cannot force a tool or disable tool use.",
          "response_format": "Native JSON mode is unavailable. Request JSON explicitly in the prompt and validate the result client-side.",
          "sampling_controls": "top_p, frequency_penalty, presence_penalty, logit_bias, and seed are not forwarded by the upstream Kiro backend."
        },
        "multiple_choices": {
          "parameter": "n",
          "supported_value": 1,
          "behavior": "Values greater than 1 still return only choices[0]."
        },
        "vision": {
          "supported": false,
          "input": "text_only",
          "behavior": "Image and multimodal inputs are ignored by the upstream Kiro backend."
        }
      },
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.5",
      "object": "model",
      "created": 1781740800,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.5",
      "description": "GPT-5.5 — OpenAI latest frontier model for coding and professional work.",
      "context_window": 270000,
      "context_length": 270000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 30,
        "cache_read": 0.5
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.4",
      "object": "model",
      "created": 1778716800,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.4",
      "description": "DEPRECATED - Use gpt-6-luna instead.",
      "context_window": 270000,
      "context_length": 270000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2.5,
        "completion": 15,
        "cache_read": 0.25
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "gpt-6-luna"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "minimax-m2.7",
      "object": "model",
      "created": 1700000000,
      "owned_by": "MiniMax",
      "display_name": "minimax-m2.7",
      "description": "MiniMax-M2.7 is a massive 230B reasoning model, optimized for complex software engineering and agentic workflows with native thinking process.",
      "context_window": 204800,
      "context_length": 204800,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.3,
        "completion": 1.2
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 70,
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k3",
      "object": "model",
      "created": 1784160000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k3",
      "description": "Moonshot AI Kimi K3 is a powerful Mixture of Experts (MoE) model featuring native reasoning capabilities and an advanced thinking mode.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15,
        "cache_read": 0.3
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 0,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2.6",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2.6",
      "description": "DEPRECATED - Moonshot AI Kimi K2.6 is deprecated. Please use kimi-k3 or kimi-k2.5 instead.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.95,
        "completion": 4
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "vision",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "kimi-k3",
        "kimi-k2.5"
      ],
      "discount": 70,
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.6-sol",
      "object": "model",
      "created": 1786838400,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.6-sol",
      "description": "DEPRECATED - Use gpt-6.1-sol or gpt-5.5 instead. GPT-5.6 Sol served on Kiro and managed by Neosantara. A fast, cost-efficient GPT-5.6 variant for text generation, coding, reasoning, and autonomous tool use. Text-only; images are ignored by the upstream Kiro backend.",
      "context_window": 272000,
      "context_length": 272000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 30
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "gpt-6.1-sol",
        "gpt-5.5"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-opus-5",
      "object": "model",
      "created": 1786838400,
      "owned_by": "Anthropic",
      "display_name": "claude-opus-5",
      "description": "DEPRECATED - Use claude-opus-5.5 or claude-sonnet-5.5 instead. Anthropic Claude Opus 5 served on Kiro and managed by Neosantara. A frontier hybrid-reasoning model with vision for complex coding, AI agents, enterprise workflows, and high-stakes reasoning. Reasoning traces are exposed via reasoning_effort.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 25
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-opus-5.5",
        "claude-sonnet-5.5"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-5.6-terra",
      "object": "model",
      "created": 1786838400,
      "owned_by": "OpenAI",
      "display_name": "gpt-5.6-terra",
      "description": "DEPRECATED - Use gpt-6-astra or gpt-5.5 instead. GPT-5.6 Terra served on Kiro and managed by Neosantara. A GPT-5.6 variant with vision for text generation, coding, reasoning, and autonomous tool use.",
      "context_window": 272000,
      "context_length": 272000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 12
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "gpt-6-astra",
        "gpt-5.5"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "bonsai-27b",
      "object": "model",
      "created": 1787270400,
      "owned_by": "Prism ML",
      "display_name": "bonsai-27b",
      "description": "Ternary Bonsai 27B is an ultra-fast high-efficiency ternary-quantized reasoning model with 256K context window, native thinking process, function calling, and multimodal vision capabilities.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "vision",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "muse-glimmer-30b",
      "object": "model",
      "created": 1786320000,
      "owned_by": "Meta",
      "display_name": "muse-glimmer-30b",
      "description": "Meta Muse Glimmer 30B is a 29.6B parameter multimodal reasoning model optimized for agentic workflows, multi-step reasoning, and coding. Includes DFlash speculative decoding.",
      "context_window": 131072,
      "context_length": 131072,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.35,
        "completion": 1.5,
        "cache_read": 0.04
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5.3-flash",
      "object": "model",
      "created": 1787702400,
      "owned_by": "zAI",
      "display_name": "glm-5.3-flash",
      "description": "GLM-5.3-Flash is a lightweight, ultra-fast language model by Z.ai supporting a 1M context window, high-throughput text generation, native reasoning mode, JSON mode, and function calling.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.15,
        "completion": 0.5,
        "cache_read": 0.03
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5.3",
      "object": "model",
      "created": 1786665600,
      "owned_by": "zAI",
      "display_name": "glm-5.3",
      "description": "GLM-5.3 is the flagship reasoning and coding language model by Z.ai supporting a 1M context window, deep analytical logic, function calling, and structured JSON output.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1.4,
        "completion": 4.4,
        "cache_read": 0.26
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-6-astra",
      "object": "model",
      "created": 1788393600,
      "owned_by": "OpenAI",
      "display_name": "gpt-6-astra",
      "description": "GPT-6 Astra is OpenAI's flagship frontier reasoning and autonomous agent model featuring deep analytical planning, advanced coding, and a 1M token context window.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 10,
        "completion": 50,
        "cache_read": 1.25,
        "cache_write": 10
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gpt-6.1-sol",
      "object": "model",
      "created": 1790035200,
      "owned_by": "OpenAI",
      "display_name": "gpt-6.1-sol",
      "description": "GPT-6.1 Sol is OpenAI's high-efficiency frontier reasoning and coding model, optimized for demanding agentic workflows, complex software engineering, and rapid multi-step deduction.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 10,
        "cache_read": 0.2,
        "cache_write": 2.5
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 50,
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "longcat-2.0",
      "object": "model",
      "created": 1785542400,
      "owned_by": "Meituan",
      "display_name": "longcat-2.0",
      "description": "LongCat 2.0 is a frontier-class sparse MoE model by Meituan with a 1M token context window, optimized for agentic coding, deep reasoning, and complex tool execution.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "streaming",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.5",
      "object": "model",
      "created": 1776816000,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.5",
      "description": "MiMo-V2.5 is a native omnimodal model by Xiaomi delivering flagship-level agentic performance at roughly half the inference cost. With a 1M token context window, it handles text, image, and video input for agent workflows that need strong reasoning, rich perception, and cost efficiency.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.14,
        "completion": 0.28,
        "cache_read": 0.0028
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 90,
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.5-pro",
      "object": "model",
      "created": 1776816000,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.5-pro",
      "description": "MiMo-V2.5-Pro is the flagship reasoning model from Xiaomi, built for general agentic capability, complex software engineering, and long-horizon tasks. Its 1M token context window lets it carry out professional work that would otherwise take human experts days or weeks, spanning more than a thousand tool calls.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.435,
        "completion": 0.87,
        "cache_read": 0.0036
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "discount": 90,
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "grok-4.5",
      "object": "model",
      "created": 1783468800,
      "owned_by": "xAI",
      "display_name": "grok-4.5",
      "description": "Grok 4.5 is a frontier reasoning model from xAI built for coding, agentic tasks, and knowledge work. It accepts text, image, and PDF input with selectable low, medium, and high reasoning depth, a 500K token context window, and tool use spanning function calling, structured outputs, and search.",
      "context_window": 500000,
      "context_length": 500000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 6,
        "cache_read": 0.3,
        "long_context": {
          "threshold_input_tokens": 200000,
          "multiplier": 2,
          "applies_to": [
            "input",
            "output",
            "cache_read"
          ]
        }
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning",
        "vision",
        "file_input",
        "json_mode",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "limitations": {
        "pricing_notes": [
          "Prompts of 200,000 input tokens or more are billed at double the listed rate: $4.00 input / $0.60 cached input / $12.00 output per 1M tokens."
        ]
      },
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4.1-flash",
      "object": "model",
      "created": 1788998400,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4.1-flash",
      "description": "DeepSeek V4.1 Flash is a sparse Mixture-of-Experts model from DeepSeek and the first built on its Causal Encoder-Decoder architecture. With a 1M token context window and native image understanding, it is tuned for coding, terminal, and computer-use agents plus long-horizon, long-context analysis at low cost.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.15,
        "completion": 0.6,
        "cache_read": 0.003,
        "peak_windows": {
          "multiplier": 2,
          "timezone": "UTC",
          "days": [
            1,
            2,
            3,
            4,
            5
          ],
          "windows": [
            [
              "01:00",
              "04:00"
            ],
            [
              "06:00",
              "10:00"
            ]
          ],
          "applies_to": [
            "input",
            "output",
            "cache_read"
          ]
        }
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "reasoning",
        "vision",
        "json_mode",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "limitations": {
        "pricing_notes": [
          "Off-peak rate shown (17h/day): $0.15 input / $0.60 output / $0.003 cache read per 1M tokens.",
          "Peak rate $0.30 input / $1.20 output / $0.006 cache read per 1M tokens applies 01:00-04:00 and 06:00-10:00 UTC, Monday-Friday (7h/day)."
        ]
      },
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "laguna-xs-2.1",
      "object": "model",
      "created": 1782777600,
      "owned_by": "Poolside",
      "display_name": "laguna-xs-2.1",
      "description": "Laguna XS 2.1 is an ultra-fast agentic coding model with a 256K context window, engineered for high-speed software development, refactoring, and tool execution.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "laguna-s-2.1",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Poolside",
      "display_name": "laguna-s-2.1",
      "description": "Laguna S 2.1 is a frontier-class agentic MoE coding and reasoning model with a 256K context window, designed for complex software engineering, long-horizon multi-step reasoning, and tool use.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "agnes-3.0-flash",
      "object": "model",
      "created": 1791244800,
      "owned_by": "Agnes AI",
      "display_name": "agnes-3.0-flash",
      "description": "Agnes 3.0 Flash is a next-generation high-speed multimodal reasoning model by Sapiens AI featuring native chain-of-thought, tool calling, and vision understanding.",
      "context_window": 1048576,
      "context_length": 1048576,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "agnes-2.5-flash",
      "object": "model",
      "created": 1788134400,
      "owned_by": "Agnes AI",
      "display_name": "agnes-2.5-flash",
      "description": "Agnes 2.5 Flash is a high-speed multimodal reasoning model by Sapiens AI featuring native chain-of-thought, tool calling, and vision understanding.",
      "context_window": 1048576,
      "context_length": 1048576,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "vision",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "agnes-image-2.5-flash",
      "object": "model",
      "created": 1788134400,
      "owned_by": "Agnes AI",
      "display_name": "agnes-image-2.5-flash",
      "description": "Agnes Image 2.5 Flash is an ultra-fast text-to-image generation model by Sapiens AI supporting high-resolution image synthesis.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD"
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "agnes-image-2.0-flash",
      "object": "model",
      "created": 1788134400,
      "owned_by": "Agnes AI",
      "display_name": "agnes-image-2.0-flash",
      "description": "Agnes Image 2.0 Flash is a high-speed text-to-image synthesis model for fast creative workflows.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD"
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "agnes-image-2.1-flash",
      "object": "model",
      "created": 1788134400,
      "owned_by": "Agnes AI",
      "display_name": "agnes-image-2.1-flash",
      "description": "Agnes Image 2.1 Flash is an upgraded text-to-image synthesis model optimized for high information density visuals.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD"
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "qwen-3.8-27b-nvfp4",
      "object": "model",
      "created": 1789948800,
      "owned_by": "Alibaba Cloud",
      "display_name": "qwen-3.8-27b-nvfp4",
      "description": "DEPRECATED - Qwen 3.8 27B NVFP4 is deprecated. Please use qwen3.5-27b or qwen3-32b instead.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.25,
        "completion": 1.5,
        "cache_read": 0.05
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "vision",
        "function_calling",
        "streaming_tool_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "qwen3.5-27b",
        "qwen3-32b"
      ],
      "discount": 100,
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "hy4-preview",
      "object": "model",
      "created": 1787875200,
      "owned_by": "Tencent",
      "display_name": "hy4-preview",
      "description": "Tencent Hunyuan 4 Preview. Large-scale MoE reasoning model with 1M context window, optimized for complex reasoning, programming, and long-horizon tool execution.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0.85,
        "completion": 2.55,
        "cache_read": 0.05
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "implicit_caching"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "minimal",
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5.3-flash-free",
      "object": "model",
      "created": 1792713600,
      "owned_by": "zAI",
      "display_name": "glm-5.3-flash-free",
      "description": "DEPRECATED - Use glm-5.3-flash or mimo-v2.6-flash-free instead. GLM 5.3 Flash (free) is a high-speed reasoning model trained by Z.ai for conversational tasks, instruction following, and agent workflows via OpenCode free access.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "glm-5.3-flash",
        "mimo-v2.6-flash-free"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-5.3-flashx-free",
      "object": "model",
      "created": 1790380800,
      "owned_by": "zAI",
      "display_name": "glm-5.3-flashx-free",
      "description": "DEPRECATED - Use glm-5.3-flash instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "glm-5.3-flash"
      ],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.6-flash-free",
      "object": "model",
      "created": 1790380800,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.6-flash-free",
      "description": "MiMo 2.6 Flash (free) is a lightweight frontier reasoning model developed by Xiaomi LLM Core Team for fast logical deduction.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.6-pro-free",
      "object": "model",
      "created": 1790380800,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.6-pro-free",
      "description": "DEPRECATED - Use mimo-v2.6-flash-free instead.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "mimo-v2.6-flash-free"
      ],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.5-free",
      "object": "model",
      "created": 1790380800,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.5-free",
      "description": "DEPRECATED - Use mimo-v2.6-flash-free instead.",
      "context_window": 262144,
      "context_length": 262144,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "mimo-v2.6-flash-free"
      ],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mimo-v2.5-pro-free",
      "object": "model",
      "created": 1790380800,
      "owned_by": "Xiaomi",
      "display_name": "mimo-v2.5-pro-free",
      "description": "DEPRECATED - Use mimo-v2.6-flash-free instead.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "mimo-v2.6-flash-free"
      ],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4-flash-0731-free",
      "object": "model",
      "created": 1785456000,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4-flash-0731-free",
      "description": "DEPRECATED - Use deepseek-v4.1-flash instead.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "function_calling",
        "json_mode",
        "reasoning"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "deepseek-v4.1-flash"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-v4.1-flash-free",
      "object": "model",
      "created": 1792281600,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-v4.1-flash-free",
      "description": "DEPRECATED - Use deepseek-v4.1-flash or mimo-v2.6-flash-free instead. DeepSeek V4.1 Flash (free) is a fast sparse Mixture-of-Experts reasoning model tuned for coding, tool execution, and long-horizon tasks.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "deepseek-v4.1-flash",
        "mimo-v2.6-flash-free"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "high",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "minimax-m3.1-flash-free",
      "object": "model",
      "created": 1792540800,
      "owned_by": "MiniMax",
      "display_name": "minimax-m3.1-flash-free",
      "description": "DEPRECATED - Use mimo-v2.6-flash-free or deepseek-v4.1-flash instead.",
      "context_window": 1000000,
      "context_length": 1000000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "mimo-v2.6-flash-free",
        "deepseek-v4.1-flash"
      ],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "ernie-5.5-flash-preview-free",
      "object": "model",
      "created": 1794268800,
      "owned_by": "Baidu",
      "display_name": "ERNIE 5.5 Flash Preview (Free)",
      "description": "ERNIE 5.5 Flash Preview (free) is a 280B foundation reasoning model by Baidu with a 1M token context window, optimized for coding, agentic workflows, knowledge work, and deep research.",
      "context_window": 1024000,
      "context_length": 1024000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "high"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-3-haiku",
      "object": "model",
      "created": 1709769600,
      "owned_by": "Anthropic",
      "display_name": "claude-3-haiku",
      "description": "DEPRECATED - Claude 3 Haiku reached end of life on Amazon Bedrock. Use claude-4-5-haiku or amazon-nova-micro instead.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.25,
        "completion": 1.25
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-4-5-haiku",
        "amazon-nova-micro"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "amazon-nova-micro",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Amazon",
      "display_name": "amazon-nova-micro",
      "description": "Amazon Nova Micro is the most affordable model with 300K context. Great for text generation and function calling.",
      "context_window": 300000,
      "context_length": 300000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.035,
        "completion": 0.14
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mistral-small-latest",
      "object": "model",
      "created": 1706745600,
      "owned_by": "Mistral AI",
      "display_name": "mistral-small-latest",
      "description": "Mistral Small is a fast, cost-effective model for text generation and function calling. Ideal for simple chat and code assistance.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.15,
        "completion": 0.6
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "mistral-large-latest",
      "object": "model",
      "created": 1706745600,
      "owned_by": "Mistral AI",
      "display_name": "mistral-large-latest",
      "description": "Mistral Large is a powerful model for complex reasoning, coding, and content generation. Best performance among Mistral family.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 2,
        "completion": 6
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-3-5-sonnet",
      "object": "model",
      "created": 1718841600,
      "owned_by": "Anthropic",
      "display_name": "claude-3-5-sonnet",
      "description": "DEPRECATED - Claude 3.5 Sonnet (v1) has been superseded. Use claude-4-5-haiku instead.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-4-5-haiku"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-3-5-haiku",
      "object": "model",
      "created": 1729555200,
      "owned_by": "Anthropic",
      "display_name": "claude-3-5-haiku",
      "description": "DEPRECATED - Claude 3.5 Haiku has been superseded by Claude Haiku 4.5.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1,
        "completion": 5
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-4-5-haiku"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-4-5-haiku",
      "object": "model",
      "created": 1759276800,
      "owned_by": "Anthropic",
      "display_name": "claude-4-5-haiku",
      "description": "Claude 4.5 Haiku. Fast, cost-efficient model for agentic workloads with strong coding and reasoning performance.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 1,
        "completion": 5,
        "cache_read": 0.1,
        "cache_write": 1.25,
        "cache_write_5m": 1.25,
        "cache_write_1h": 2
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-3-5-sonnet-v2",
      "object": "model",
      "created": 1729555200,
      "owned_by": "Anthropic",
      "display_name": "claude-3-5-sonnet-v2",
      "description": "DEPRECATED - Claude 3.5 Sonnet v2 has been superseded. Use claude-4-5-haiku instead.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "computer_use",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-4-5-haiku"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-3-7-sonnet",
      "object": "model",
      "created": 1739923200,
      "owned_by": "Anthropic",
      "display_name": "claude-3-7-sonnet",
      "description": "DEPRECATED - Claude 3.7 Sonnet has been superseded. Use claude-4-5-haiku instead.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "computer_use",
        "reasoning",
        "streaming_tool_calling"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "claude-4-5-haiku"
      ],
      "reasoning": {
        "mode": "unknown",
        "supported_efforts": null
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "amazon-nova-lite",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Amazon",
      "display_name": "amazon-nova-lite",
      "description": "Amazon Nova Lite is a very fast, low-cost multimodal model that is ideal for processing images, videos, and text with a 300,000-token context window.",
      "context_window": 300000,
      "context_length": 300000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.06,
        "completion": 0.24
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "amazon-nova-pro",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Amazon",
      "display_name": "amazon-nova-pro",
      "description": "Amazon Nova Pro is a high-capability multimodal model with the best balance of speed and intelligence for complex reasoning, vision, and video analysis.",
      "context_window": 300000,
      "context_length": 300000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.8,
        "completion": 3.2
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "llama-3-2-11b-vision",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Meta",
      "display_name": "llama-3-2-11b-vision",
      "description": "DEPRECATED - Llama 3.2 11B reached end of life on Amazon Bedrock. Use amazon-nova-lite or claude-4-5-haiku instead.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.16,
        "completion": 0.16
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "vision"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "amazon-nova-lite",
        "claude-4-5-haiku"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "titan-image-g1",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Amazon",
      "display_name": "titan-image-g1",
      "description": "DEPRECATED - Amazon Titan Image Generator G1 v2 reached end of life on Amazon Bedrock. Use imagen-4.0-fast or gpt-image-2 instead.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_image": {
          "256x256": 0.008,
          "384x384": 0.008,
          "512x512": 0.008,
          "512x384": 0.008,
          "384x512": 0.008,
          "768x768": 0.01,
          "1024x1024": 0.01,
          "1408x1408": 0.01,
          "768x1024": 0.01,
          "1024x768": 0.01,
          "1152x1152": 0.01,
          "1280x1280": 0.01
        }
      },
      "capabilities": [
        "image_generation"
      ],
      "deprecated": true,
      "deprecation_alternatives": [
        "imagen-4.0-fast",
        "gpt-image-2"
      ],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "luma-ray2-720p",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Luma AI",
      "display_name": "luma-ray2-720p",
      "description": "Luma Ray2 (720p, 24fps) - High-quality video generation.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_second": 1.5
      },
      "capabilities": [
        "video_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "luma-ray2-540p",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Luma AI",
      "display_name": "luma-ray2-540p",
      "description": "Luma Ray2 (540p, 24fps) - Efficient video generation.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "per_second": 0.75
      },
      "capabilities": [
        "video_generation"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-r1",
      "object": "model",
      "created": 1700000000,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-r1",
      "description": "DeepSeek-R1 is a state-of-the-art reasoning model, providing high-quality intelligence with excellent cost-efficiency.",
      "context_window": 128000,
      "context_length": 128000,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 1.35,
        "completion": 5.4
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "json_mode"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2-thinking",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2-thinking",
      "description": "Kimi K2 Thinking is Moonshot AI's reasoning model with chain-of-thought capabilities for complex problem solving in math, coding, and logic.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 0.6,
        "completion": 2.5
      },
      "capabilities": [
        "text_generation",
        "reasoning",
        "function_calling",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "always_on",
        "supported_efforts": [],
        "can_disable": false
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "kimi-k2.5",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Moonshot",
      "display_name": "kimi-k2.5",
      "description": "Kimi K2.5 is Moonshot AI's native multimodal model with vision, reasoning, and agentic capabilities.",
      "context_window": 256000,
      "context_length": 256000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 0.6,
        "completion": 3
      },
      "capabilities": [
        "text_generation",
        "vision",
        "reasoning",
        "function_calling",
        "streaming_tool_calling"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "toggle",
        "supported_efforts": [],
        "can_disable": true
      },
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "claude-fable-5",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Anthropic",
      "display_name": "claude-fable-5",
      "description": "Claude Fable 5 is Anthropic's first Mythos-class model, optimized for complex and long-running autonomous agentic workflows.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 10,
        "completion": 50,
        "cache_read": 1,
        "cache_write": 12.5,
        "cache_write_5m": 12.5,
        "cache_write_1h": 20
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "claude-sonnet-5",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Anthropic",
      "display_name": "claude-sonnet-5",
      "description": "Claude Sonnet 5 represents the latest in agentic and high-intelligence reasoning from Anthropic.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 3,
        "completion": 15,
        "cache_read": 0.3,
        "cache_write": 3.75,
        "cache_write_5m": 3.75,
        "cache_write_1h": 6
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "computer_use",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": true
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "claude-opus-4-7",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Anthropic",
      "display_name": "claude-opus-4-7",
      "description": "Claude Opus 4.7 is Anthropic's model for complex reasoning and advanced analysis.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 25,
        "cache_read": 0.5,
        "cache_write": 6.25,
        "cache_write_5m": 6.25,
        "cache_write_1h": 10
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "claude-opus-4-8",
      "object": "model",
      "created": 1783296000,
      "owned_by": "Anthropic",
      "display_name": "claude-opus-4-8",
      "description": "Claude Opus 4.8 is Anthropic's model for complex reasoning and advanced analysis.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 8192,
      "max_completion_tokens": 8192,
      "pricing": {
        "currency": "USD",
        "prompt": 5,
        "completion": 25,
        "cache_read": 0.5,
        "cache_write": 6.25,
        "cache_write_5m": 6.25,
        "cache_write_1h": 10
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "claude-fable-5.1",
      "object": "model",
      "created": 1788220800,
      "owned_by": "Anthropic",
      "display_name": "claude-fable-5.1",
      "description": "Claude Fable 5.1 is Anthropic's frontier model for complex research, advanced coding, and autonomous multi-step operations.",
      "context_window": 200000,
      "context_length": 200000,
      "max_output_tokens": 16384,
      "max_completion_tokens": 16384,
      "pricing": {
        "currency": "USD",
        "prompt": 10,
        "completion": 50,
        "cache_read": 1,
        "cache_write": 12.5,
        "cache_write_5m": 12.5,
        "cache_write_1h": 20
      },
      "capabilities": [
        "text_generation",
        "json_mode",
        "function_calling",
        "streaming_tool_calling",
        "vision",
        "reasoning"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "reasoning": {
        "mode": "graded",
        "supported_efforts": [
          "low",
          "medium",
          "high",
          "xhigh",
          "max"
        ],
        "can_disable": false
      },
      "availability": {
        "status": "unavailable",
        "code": "model_unavailable",
        "message": "This model is temporarily unavailable. Please use another model."
      }
    },
    {
      "id": "nusa-embedding-0001",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Neosantara",
      "display_name": "nusa-embedding-0001",
      "description": "Text embedding model for search and recommendation systems",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0,
        "completion": 0
      },
      "capabilities": [
        "embeddings"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "gemini-embedding-001",
      "object": "model",
      "created": 1700000000,
      "owned_by": "Google",
      "display_name": "gemini-embedding-001",
      "description": "Google Gemini Text Embedding 001. Extremely cost-effective ($0.15/1M).",
      "context_window": 2048,
      "context_length": 2048,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "USD",
        "prompt": 0.15,
        "completion": 0
      },
      "capabilities": [
        "embeddings"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "deepseek-ocr",
      "object": "model",
      "created": 1700000000,
      "owned_by": "DeepSeek",
      "display_name": "deepseek-ocr",
      "description": "DeepSeek OCR model for extracting text from images with high accuracy. Supports URLs and base64 images.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "per_image": 100
      },
      "capabilities": [
        "ocr",
        "vision"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    },
    {
      "id": "glm-ocr",
      "object": "model",
      "created": 1700000000,
      "owned_by": "zAI",
      "display_name": "glm-ocr",
      "description": "GLM-OCR model by Z.ai, specialized in high-accuracy text extraction, table recognition (HTML), and formula recognition (LaTeX). Note: Does not support visual grounding output.",
      "context_window": 0,
      "context_length": 0,
      "max_output_tokens": 4096,
      "max_completion_tokens": 4096,
      "pricing": {
        "currency": "IDR",
        "per_image": 100
      },
      "capabilities": [
        "ocr"
      ],
      "deprecated": false,
      "deprecation_alternatives": [],
      "availability": {
        "status": "available"
      }
    }
  ]
}