buy.jewproxy.tech

7h 11m uptime 12183 prompts 270.00m tokens ($831.45) 10 active prompters auth: user_token

service info·limits·get access·generate images·how to use·agentic coding·check your user token

{
  "uptime": 25900,
  "endpoints": {
    "openai": "https://vip.jewproxy.tech/proxy/openai",
    "openai-image": "https://vip.jewproxy.tech/proxy/openai-image",
    "google-ai": "https://vip.jewproxy.tech/proxy/google-ai",
    "aws-claude": "https://vip.jewproxy.tech/proxy/aws/claude",
    "aws-mistral": "https://vip.jewproxy.tech/proxy/aws/mistral",
    "aws-openai": "https://vip.jewproxy.tech/proxy/aws/openai",
    "gcp": "https://vip.jewproxy.tech/proxy/gcp/claude",
    "azure": "https://vip.jewproxy.tech/proxy/azure/openai",
    "deepseek": "https://vip.jewproxy.tech/proxy/deepseek",
    "xai": "https://vip.jewproxy.tech/proxy/xai",
    "qwen": "https://vip.jewproxy.tech/proxy/qwen",
    "glm": "https://vip.jewproxy.tech/proxy/glm",
    "moonshot": "https://vip.jewproxy.tech/proxy/moonshot",
    "openrouter": "https://vip.jewproxy.tech/proxy/openrouter",
    "groq": "https://vip.jewproxy.tech/proxy/groq",
    "meta": "https://vip.jewproxy.tech/proxy/meta",
    "images": "https://vip.jewproxy.tech/proxy/images",
    "videos": "https://vip.jewproxy.tech/proxy/videos"
  },
  "proompts": 12183,
  "tookens": "270.00m ($831.45)",
  "tokenBreakdown": {
    "total": 270001783,
    "input": 251517405,
    "output": 18484378,
    "cachedInput": 149553315,
    "reasoningOutput": 2314726
  },
  "proomptersNow": 10,
  "openaiKeys": 69,
  "openaiOrgs": 15,
  "google-aiKeys": 21,
  "awsKeys": 2,
  "gcpKeys": 1,
  "azureKeys": 1,
  "deepseekKeys": 464,
  "xaiKeys": 84,
  "qwenKeys": 178,
  "glmKeys": 148,
  "moonshotKeys": 191,
  "openrouterKeys": 1481,
  "groqKeys": 18,
  "metaKeys": 1,
  "turbo": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "revokedKeys": 20,
    "overQuotaKeys": 28,
    "trialKeys": 0,
    "models": {
      "gpt-4o-mini": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo-instruct": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo-instruct-0914": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo-1106": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo-0125": {
        "activeKeys": 4
      },
      "gpt-4o-mini-2024-07-18": {
        "activeKeys": 4
      },
      "gpt-3.5-turbo-16k": {
        "activeKeys": 4
      },
      "text-embedding-ada-002": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt4": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-4": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt4-turbo": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-4-turbo": {
        "activeKeys": 4
      },
      "gpt-4-turbo-2024-04-09": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt4o": {
    "usage": "41.4k (In: 41.4k, Out: 10) ($0.10)",
    "usageBreakdown": {
      "total": 41437,
      "input": 41427,
      "output": 10
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-4o": {
        "activeKeys": 4
      },
      "gpt-4o-2024-05-13": {
        "activeKeys": 4
      },
      "gpt-4o-2024-08-06": {
        "activeKeys": 4
      },
      "gpt-4o-2024-11-20": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt41": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-4.1-2025-04-14": {
        "activeKeys": 4
      },
      "gpt-4.1": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt41-mini": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-4.1-mini-2025-04-14": {
        "activeKeys": 4
      },
      "gpt-4.1-mini": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt41-nano": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-4.1-nano-2025-04-14": {
        "activeKeys": 4
      },
      "gpt-4.1-nano": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt5": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5-2025-08-07": {
        "activeKeys": 4
      },
      "gpt-5": {
        "activeKeys": 4
      },
      "gpt-5-codex": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt51": {
    "usage": "372.3k (In: 368.3k, Out: 4.0k) ($0.50)",
    "usageBreakdown": {
      "total": 372257,
      "input": 368285,
      "output": 3972,
      "cachedInput": 176256
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.1-2025-11-13": {
        "activeKeys": 4
      },
      "gpt-5.1": {
        "activeKeys": 4
      },
      "gpt-5.1-codex": {
        "activeKeys": 4
      },
      "gpt-5.1-codex-mini": {
        "activeKeys": 4
      },
      "gpt-5.1-codex-max": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt52": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.2-2025-12-11": {
        "activeKeys": 4
      },
      "gpt-5.2": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt54": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.4-2026-03-05": {
        "activeKeys": 4
      },
      "gpt-5.4": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt55": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.5": {
        "activeKeys": 4
      },
      "gpt-5.5-2026-04-23": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt56": {
    "usage": "4.79m (In: 4.54m, Out: 254.0k) ($30.30)",
    "usageBreakdown": {
      "total": 4789895,
      "input": 4535905,
      "output": 253990,
      "cachedInput": 5568659,
      "reasoningOutput": 107448
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.6-sol": {
        "activeKeys": 4
      },
      "gpt-5.6": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt56-terra": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.6-terra": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt56-luna": {
    "usage": "3.57m (In: 3.49m, Out: 87.6k) ($0.80)",
    "usageBreakdown": {
      "total": 3573258,
      "input": 3485685,
      "output": 87573,
      "cachedInput": 22112224,
      "reasoningOutput": 35875
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5.6-luna": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt5-mini": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-5-mini-2025-08-07": {
        "activeKeys": 4
      },
      "gpt-5-mini": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt5-nano": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 5,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5-nano": {
        "activeKeys": 5
      },
      "gpt-5-nano-2025-08-07": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt5-chat-latest": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5-chat-latest": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt5-pro": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "gpt-5-pro-2025-10-06": {
        "activeKeys": 4
      },
      "gpt-5-pro": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "o1": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "o1-2024-12-17": {
        "activeKeys": 4
      },
      "o1": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "o3": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "o3-2025-04-16": {
        "activeKeys": 4
      },
      "o3": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "o3-mini": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "o3-mini": {
        "activeKeys": 4
      },
      "o3-mini-2025-01-31": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "o3-pro": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 2,
    "overQuotaKeys": 1,
    "models": {
      "o3-pro": {
        "activeKeys": 2
      },
      "o3-pro-2025-06-10": {
        "activeKeys": 2
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "o4-mini": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 4,
    "overQuotaKeys": 24,
    "models": {
      "o4-mini-2025-04-16": {
        "activeKeys": 4
      },
      "o4-mini": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gpt-image": {
    "usage": "17.8k (In: 8.4k, Out: 9.4k) ($0.00)",
    "usageBreakdown": {
      "total": 17756,
      "input": 8358,
      "output": 9398
    },
    "activeKeys": 4,
    "overQuotaKeys": 25,
    "models": {
      "gpt-image-1": {
        "activeKeys": 4
      },
      "gpt-image-1-mini": {
        "activeKeys": 4
      },
      "gpt-image-1.5": {
        "activeKeys": 4
      },
      "gpt-image-2": {
        "activeKeys": 4
      },
      "gpt-image-2-2026-04-21": {
        "activeKeys": 4
      }
    },
    "modelDiscoveryPending": false,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-turbo": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt51": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt54": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt54-mini": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt54-nano": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt56": {
    "usage": "16.04m (In: 15.46m, Out: 587.5k) ($94.90)",
    "usageBreakdown": {
      "total": 16043378,
      "input": 15455873,
      "output": 587505,
      "cachedInput": 51385724,
      "reasoningOutput": 290413
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt56-terra": {
    "usage": "2.16m (In: 2.09m, Out: 63.2k) ($4.94)",
    "usageBreakdown": {
      "total": 2156548,
      "input": 2093369,
      "output": 63179,
      "cachedInput": 6280249,
      "reasoningOutput": 31081
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "azure-gpt56-luna": {
    "usage": "2.90m (In: 2.89m, Out: 9.0k) ($0.59)",
    "usageBreakdown": {
      "total": 2899769,
      "input": 2890739,
      "output": 9030,
      "cachedInput": 6115140,
      "reasoningOutput": 3462
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-flash": {
    "usage": "1.44m (In: 1.10m, Out: 339.6k) ($1.18)",
    "usageBreakdown": {
      "total": 1442022,
      "input": 1102428,
      "output": 339594
    },
    "activeKeys": 6,
    "revokedKeys": 0,
    "overQuotaKeys": 2,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-35-flash": {
    "usage": "1.14m (In: 1.03m, Out: 105.2k) ($2.50)",
    "usageBreakdown": {
      "total": 1138782,
      "input": 1033551,
      "output": 105231
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-35-flash-lite": {
    "usage": "158.2k (In: 150.0k, Out: 8.2k) ($0.07)",
    "usageBreakdown": {
      "total": 158164,
      "input": 149985,
      "output": 8179
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-31-flash-lite": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-37-flash": {
    "usage": "32.21m (In: 29.94m, Out: 2.27m) ($24.42)",
    "usageBreakdown": {
      "total": 32213333,
      "input": 29939852,
      "output": 2273481
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "models": {
      "gemini-3.7-flash": {
        "activeKeys": 8,
        "unavailable": {
          "disabledOrRevoked": 13
        }
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-36-flash": {
    "usage": "129.1k (In: 112.0k, Out: 17.1k) ($0.14)",
    "usageBreakdown": {
      "total": 129064,
      "input": 111968,
      "output": 17096
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "models": {
      "gemini-3.6-flash": {
        "activeKeys": 8,
        "unavailable": {
          "disabledOrRevoked": 13
        }
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-pro": {
    "usage": "5.98m (In: 5.55m, Out: 431.2k) ($11.24)",
    "usageBreakdown": {
      "total": 5977186,
      "input": 5545994,
      "output": 431192
    },
    "activeKeys": 8,
    "revokedKeys": 8,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gemini-3-pro": {
    "usage": "113.00m (In: 108.33m, Out: 4.67m) ($272.69)",
    "usageBreakdown": {
      "total": 113000510,
      "input": 108331999,
      "output": 4668511
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "enabledVariants": "3.0,3.1",
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "veo": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 8,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "aws-claude": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 0,
    "revokedKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "gcp-claude-opus": {
    "usage": "55.74m (In: 52.33m, Out: 3.41m) ($346.97)",
    "usageBreakdown": {
      "total": 55739771,
      "input": 52326342,
      "output": 3413429
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "models": {
      "claude-opus-5": {
        "activeKeys": 0,
        "unsupportedKeys": 1
      },
      "claude-opus-4-8": {
        "activeKeys": 1
      },
      "claude-opus-4-7": {
        "activeKeys": 1
      },
      "claude-opus-4-6": {
        "activeKeys": 1
      },
      "claude-opus-4-5": {
        "activeKeys": 1
      },
      "claude-sonnet-4-6": {
        "activeKeys": 1
      },
      "claude-fable-5": {
        "activeKeys": 1
      },
      "claude-sonnet-5": {
        "activeKeys": 1
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "openrouter-paid": {
    "usage": "1.07m (In: 175.8k, Out: 890.5k) ($0.38)",
    "usageBreakdown": {
      "total": 1066266,
      "input": 175801,
      "output": 890465
    },
    "activeKeys": 228,
    "revokedKeys": 130,
    "overQuotaKeys": 0,
    "paidKeys": 228,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "openrouter-free": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1351,
    "revokedKeys": 130,
    "overQuotaKeys": 0,
    "freeKeys": 716,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "openrouter-video": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 228,
    "revokedKeys": 130,
    "overQuotaKeys": 0,
    "paidKeys": 228,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "deepseek": {
    "usage": "12.20m (In: 8.49m, Out: 3.71m) ($6.92)",
    "usageBreakdown": {
      "total": 12204249,
      "input": 8489356,
      "output": 3714893,
      "cachedInput": 42801280,
      "reasoningOutput": 1190467
    },
    "activeKeys": 3,
    "revokedKeys": 267,
    "overQuotaKeys": 194,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "xai": {
    "usage": "3.48m (In: 3.05m, Out: 428.6k) ($8.03)",
    "usageBreakdown": {
      "total": 3476223,
      "input": 3047616,
      "output": 428607,
      "cachedInput": 6234048,
      "reasoningOutput": 286134
    },
    "activeKeys": 21,
    "revokedKeys": 63,
    "overQuotaKeys": 0,
    "models": {
      "grok-4.20": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-0309": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-0309-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-0309-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-0309": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-0309-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-0309-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-latest-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-latest-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-beta-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-0304": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-0304-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-0304-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-non-reasoning-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-experimental-beta-reasoning-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-0309": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-beta-0309": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-beta-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-experimental-beta-0304": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-experimental-beta-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-multi-agent-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-non-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-non-reasoning-gv2": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-non-reasoning-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-reasoning": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-reasoning-gv2": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.20-reasoning-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.3": {
        "activeKeys": 6
      },
      "grok-4.3-latest": {
        "activeKeys": 6
      },
      "grok-4.5": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.5-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-4.6": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-build-0.1": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-build-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-code-fast": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-code-fast-1-0825": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image-2.0": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image-2026-03-02": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image-quality": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image-quality-20260403": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-image-quality-latest": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-video": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-video-1.5": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-video-1.5-2026-05-30": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      },
      "grok-imagine-video-1.5-preview": {
        "activeKeys": 4,
        "unsupportedKeys": 2
      }
    },
    "modelDiscoveryPending": true,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "qwen": {
    "usage": "6.93m (In: 6.45m, Out: 479.9k) ($13.39)",
    "usageBreakdown": {
      "total": 6930078,
      "input": 6450168,
      "output": 479910,
      "cachedInput": 4652416,
      "reasoningOutput": 148381
    },
    "activeKeys": 3,
    "revokedKeys": 113,
    "overQuotaKeys": 62,
    "models": {
      "qwen3.8-max": {
        "activeKeys": 3
      },
      "qwen3.7-plus": {
        "activeKeys": 3
      },
      "qwen3.7-flash": {
        "activeKeys": 3
      },
      "deepseek-v4-pro": {
        "activeKeys": 3
      },
      "deepseek-v4-flash": {
        "activeKeys": 3
      },
      "kimi-k2.7-code": {
        "activeKeys": 3
      },
      "glm-5.2": {
        "activeKeys": 3
      },
      "MiniMax-M2.5": {
        "activeKeys": 3
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "16sec"
  },
  "glm": {
    "usage": "6.63m (In: 5.93m, Out: 699.1k) ($11.38)",
    "usageBreakdown": {
      "total": 6631837,
      "input": 5932704,
      "output": 699133,
      "cachedInput": 4227319,
      "reasoningOutput": 221465
    },
    "activeKeys": 2,
    "revokedKeys": 2,
    "overQuotaKeys": 145,
    "models": {
      "glm-5.3": {
        "activeKeys": 0,
        "unsupportedKeys": 2
      },
      "glm-5.2": {
        "activeKeys": 0,
        "unsupportedKeys": 2
      },
      "glm-5.1": {
        "activeKeys": 2
      },
      "glm-5": {
        "activeKeys": 2
      },
      "glm-4.7": {
        "activeKeys": 2
      },
      "glm-4.6": {
        "activeKeys": 2
      },
      "glm-4.5-air": {
        "activeKeys": 2
      },
      "glm-4.5": {
        "activeKeys": 2
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "moonshot": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 6,
    "revokedKeys": 171,
    "overQuotaKeys": 14,
    "modelDiscoveryPending": 0,
    "models": {
      "kimi-k3": {
        "id": "kimi-k3",
        "displayName": "Kimi K3",
        "contextWindow": 1048576,
        "maxOutputTokens": 1048576,
        "defaultOutputTokens": 131072,
        "inputModalities": [
          "text",
          "image",
          "video"
        ],
        "supportsReasoning": true,
        "reasoningControl": "reasoning_effort:max",
        "supportsTools": true,
        "supportsRequiredToolChoice": true,
        "pricingPerMillion": {
          "cachedInput": 0.3,
          "uncachedInput": 3,
          "output": 15
        },
        "featured": true,
        "fallback": true,
        "legacy": false,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "kimi-k2.7-code": {
        "id": "kimi-k2.7-code",
        "displayName": "Kimi K2.7 Code",
        "contextWindow": 262144,
        "inputModalities": [
          "text",
          "image",
          "video"
        ],
        "supportsReasoning": true,
        "reasoningControl": "thinking:enabled",
        "supportsTools": true,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.19,
          "uncachedInput": 0.95,
          "output": 4
        },
        "featured": true,
        "fallback": true,
        "legacy": false,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "kimi-k2.7-code-highspeed": {
        "id": "kimi-k2.7-code-highspeed",
        "displayName": "Kimi K2.7 Code HighSpeed",
        "contextWindow": 262144,
        "inputModalities": [
          "text",
          "image",
          "video"
        ],
        "supportsReasoning": true,
        "reasoningControl": "thinking:enabled",
        "supportsTools": true,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.38,
          "uncachedInput": 1.9,
          "output": 8
        },
        "featured": true,
        "fallback": true,
        "legacy": false,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "kimi-k2.6": {
        "id": "kimi-k2.6",
        "displayName": "Kimi K2.6",
        "contextWindow": 262144,
        "inputModalities": [
          "text",
          "image",
          "video"
        ],
        "supportsReasoning": true,
        "reasoningControl": "thinking:configurable",
        "supportsTools": true,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.16,
          "uncachedInput": 0.95,
          "output": 4
        },
        "featured": true,
        "fallback": true,
        "legacy": false,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "kimi-k2.5": {
        "id": "kimi-k2.5",
        "displayName": "Kimi K2.5",
        "contextWindow": 262144,
        "inputModalities": [
          "text",
          "image",
          "video"
        ],
        "supportsReasoning": true,
        "reasoningControl": "thinking:configurable",
        "supportsTools": true,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.1,
          "uncachedInput": 0.6,
          "output": 3
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-8k": {
        "id": "moonshot-v1-8k",
        "displayName": "Moonshot V1 8K",
        "contextWindow": 8192,
        "inputModalities": [
          "text"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.2,
          "uncachedInput": 0.2,
          "output": 2
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-32k": {
        "id": "moonshot-v1-32k",
        "displayName": "Moonshot V1 32K",
        "contextWindow": 32768,
        "inputModalities": [
          "text"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 1,
          "uncachedInput": 1,
          "output": 3
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-128k": {
        "id": "moonshot-v1-128k",
        "displayName": "Moonshot V1 128K",
        "contextWindow": 131072,
        "inputModalities": [
          "text"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 2,
          "uncachedInput": 2,
          "output": 5
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-8k-vision-preview": {
        "id": "moonshot-v1-8k-vision-preview",
        "displayName": "Moonshot V1 8K Vision Preview",
        "contextWindow": 8192,
        "inputModalities": [
          "text",
          "image"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 0.2,
          "uncachedInput": 0.2,
          "output": 2
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-32k-vision-preview": {
        "id": "moonshot-v1-32k-vision-preview",
        "displayName": "Moonshot V1 32K Vision Preview",
        "contextWindow": 32768,
        "inputModalities": [
          "text",
          "image"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 1,
          "uncachedInput": 1,
          "output": 3
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      },
      "moonshot-v1-128k-vision-preview": {
        "id": "moonshot-v1-128k-vision-preview",
        "displayName": "Moonshot V1 128K Vision Preview",
        "contextWindow": 131072,
        "inputModalities": [
          "text",
          "image"
        ],
        "supportsReasoning": false,
        "reasoningControl": "none",
        "supportsTools": false,
        "supportsRequiredToolChoice": false,
        "pricingPerMillion": {
          "cachedInput": 2,
          "uncachedInput": 2,
          "output": 5
        },
        "featured": false,
        "fallback": false,
        "legacy": true,
        "activeKeys": 6,
        "unsupportedKeys": 0
      }
    },
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "groq": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 16,
    "revokedKeys": 2,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "meta": {
    "usage": "0 tokens ($0.00)",
    "usageBreakdown": {
      "total": 0,
      "input": 0,
      "output": 0
    },
    "activeKeys": 1,
    "revokedKeys": 0,
    "overQuotaKeys": 0,
    "proomptersInQueue": 0,
    "estimatedQueueTime": "no wait"
  },
  "config": {
    "awsBedrockTransport": "auto",
    "awsBedrockSigV4Source": "legacy",
    "awsBedrockMantleAuth": "auto",
    "awsBedrockMantleRegion": "us-east-1",
    "awsBedrockAllowProviderDataShare": "true",
    "awsBedrockMantleExposeDiscoveredModels": "true",
    "awsBedrockMantleExposeOpenAiModels": "true",
    "gatekeeper": "user_token",
    "allowUnmeteredResponsesCompact": "false",
    "maxIpsAutoBan": "true",
    "captchaMode": "none",
    "powTokenHours": "24",
    "powTokenMaxIps": "2",
    "powDifficultyLevel": "low",
    "powChallengeTimeout": "30",
    "usageReporting": "true",
    "usageReportCron": "0 0 * * *",
    "watchdogNoKeysThreshold": "3",
    "watchdogNoKeysWindowSeconds": "60",
    "watchdogNoKeysGraceSeconds": "120",
    "watchdogAlertCooldownSeconds": "600",
    "watchdogPoolMonitorEnabled": "true",
    "watchdogPoolMonitorIntervalSeconds": "60",
    "tokenSharingLegacyScoring": "false",
    "textModelRateLimit": "30",
    "imageModelRateLimit": "4",
    "maxContextTokensOpenAI": "271000",
    "maxContextTokensAnthropic": "300000",
    "maxOutputTokensOpenAI": "65535",
    "maxOutputTokensAnthropic": "65535",
    "useRemoteTokenCounting": "true",
    "allowAwsLogging": "false",
    "promptLogging": "false",
    "tokenQuota": {
      "moonshot": "100000",
      "qwen": "0",
      "glm": "10000000",
      "cohere": "0",
      "xai": "30000000",
      "deepseek": "0",
      "openrouter-paid": "1500000",
      "openrouter-free": "0",
      "openrouter-video": "80000",
      "groq": "0",
      "meta": "0",
      "turbo": "0",
      "gpt4": "0",
      "gpt4-turbo": "0",
      "gpt4o": "0",
      "gpt41": "0",
      "gpt41-mini": "0",
      "gpt41-nano": "0",
      "gpt5": "0",
      "gpt51": "0",
      "gpt52": "0",
      "gpt53-codex": "0",
      "gpt53-chat-latest": "0",
      "gpt54": "0",
      "gpt54-thinking": "0",
      "gpt54-pro": "0",
      "gpt54-mini": "0",
      "gpt54-nano": "0",
      "gpt55": "0",
      "gpt55-pro": "0",
      "gpt56": "0",
      "gpt56-terra": "0",
      "gpt56-luna": "0",
      "gpt5-mini": "0",
      "gpt5-nano": "0",
      "gpt5-chat-latest": "0",
      "gpt5-pro": "0",
      "o1": "0",
      "o1-pro": "0",
      "o3-pro": "0",
      "o3-mini": "0",
      "o3": "0",
      "o4-mini": "0",
      "dall-e": "0",
      "gpt-image": "0",
      "claude": "1000000",
      "claude-sonnet-5": "1000000",
      "claude-opus": "1000000",
      "claude-fable": "1000000",
      "claude-haiku": "1000000",
      "gemini-flash": "0",
      "gemini-35-flash": "0",
      "gemini-35-flash-lite": "0",
      "gemini-31-flash-lite": "0",
      "gemini-36-flash": "0",
      "gemini-37-flash": "0",
      "gemini-pro": "0",
      "gemini-3-pro": "0",
      "gemini-ultra": "0",
      "veo": "0",
      "mistral-tiny": "0",
      "mistral-small": "0",
      "mistral-medium": "0",
      "mistral-large": "0",
      "aws-claude": "0",
      "aws-claude-sonnet-5": "0",
      "aws-claude-opus": "0",
      "aws-claude-fable": "1000000",
      "aws-claude-mythos": "0",
      "aws-claude-haiku": "1000000",
      "aws-mistral-tiny": "0",
      "aws-mistral-small": "0",
      "aws-mistral-medium": "0",
      "aws-mistral-large": "0",
      "aws-openai": "10000000",
      "gcp-claude": "0",
      "gcp-claude-opus": "7000000",
      "gcp-gemini-pro": "0",
      "gcp-gemini-flash": "0",
      "gcp-gemini-3-pro": "0",
      "azure-turbo": "0",
      "azure-gpt4": "0",
      "azure-gpt4-turbo": "0",
      "azure-gpt4o": "0",
      "azure-gpt41": "0",
      "azure-gpt41-mini": "0",
      "azure-gpt41-nano": "0",
      "azure-gpt5": "0",
      "azure-gpt51": "0",
      "azure-gpt52": "0",
      "azure-gpt53-codex": "0",
      "azure-gpt53-chat-latest": "0",
      "azure-gpt54": "0",
      "azure-gpt54-thinking": "0",
      "azure-gpt54-pro": "0",
      "azure-gpt54-mini": "0",
      "azure-gpt54-nano": "0",
      "azure-gpt55": "0",
      "azure-gpt55-pro": "0",
      "azure-gpt56": "0",
      "azure-gpt56-terra": "0",
      "azure-gpt56-luna": "0",
      "azure-gpt5-mini": "0",
      "azure-gpt5-nano": "0",
      "azure-gpt5-chat-latest": "0",
      "azure-gpt5-pro": "0",
      "azure-dall-e": "0",
      "azure-o1": "0",
      "azure-o1-pro": "0",
      "azure-o3-pro": "0",
      "azure-o3-mini": "0",
      "azure-o3": "0",
      "azure-o4-mini": "0",
      "azure-gpt-image": "0",
      "openai": "15000000",
      "google-ai": "0",
      "azure": "40000000",
      "aws": "10000000"
    },
    "openAICachedInputQuotaFactor": "0.5",
    "anthropicCacheReadQuotaFactor": "0.1",
    "anthropicCacheWriteQuotaFactor": "1.25",
    "anthropicCacheWrite1hQuotaFactor": "2",
    "allowAnthropicFastMode": "false",
    "allowXaiLiveSearch": "false",
    "allowMoonshotBuiltinTools": "false",
    "gcpClaudeOpenAiThinkingDefault": "true",
    "gcpClaudeMultiRegionFallback": "true",
    "gcpClaudeRegionDeepProbe": "true",
    "quotaRefreshPeriod": "daily",
    "openAIImageModeration": "low",
    "imageAssetRetentionDays": "30",
    "allowOpenAIToolUsage": "false",
    "allowedVisionServices": "google-ai,openai,groq,xai,qwen,meta,anthropic",
    "tokensPunishmentFactor": "0",
    "serviceInfoAuthMode": "token",
    "serverTitleUrl": "https://buy.jewproxy.tech"
  }
}

context limits

openai max context271,000 tokens

openai max output65,535 tokens

token quotas

moonshot · moonshot100.0k tokens / day

glm · glm10m tokens / day

grok · xai30m tokens / day

openrouter (paid) · openrouter1.5m tokens / day

openrouter video · openrouter80.0k tokens / day

gcp claude (opus) · gcp · also on: aws7m tokens / day

openai · openai15m tokens / day

azure · azure40m tokens / day

aws10m tokens / day

all other models: unlimited.

how to use step by step

jewproxy = api access to many ai models, billed via one token. every app needs the same three values: a base url, an api key, and a model name.

01→ the universal recipe

copy a base url from this page
set your api key to your jewproxy token
set the model (depends on the endpoint and tags shown)

02→ sillytavern, full walkthrough

open the api panel (the plug icon at the top)
choose chat completion
choose source custom (openai-compatible)
paste the base url
paste your jewproxy token as the api key
type the model name, or use the model selector
click connect, then send a 1-line test message

for claude opus 4.8, claude fable 5, or claude sonnet 5 in sillytavern, use the openrouter base url (next tab). that's the route most people miss.

for gemini 3.1, use the google-ai endpoint. same setup, different base url.

03→ same 3 values in other apps

lobe chat, librechat, big-agi, openai libraries for python and js, plus your own discord and telegram bots. all use the same base url + api key + model pattern.

04→ support

access, billing, payment, or anything else: buy.jewproxy.tech

three lines of config. follow them in order.

01→ base url

https://vip.jewproxy.tech/proxy/openrouter/v1

02→ the steps

set the base url above in your app
set the api key to your jewproxy token
set the model to claude opus 4.8, claude fable 5, or claude sonnet 5 (or another paid openrouter model)

03→ why this endpoint

the openai endpoint is for openai-style models. claude opus 4.8, claude fable 5, and claude sonnet 5 (and other openrouter-routed models) need this url instead. the request format stays openai-compatible; only the base url is different.

04→ finding the right model name

on the service page, open the dropdown on the openrouter paid row (show paid openrouter models). it loads the live list, so you can copy the exact name into your app to avoid typos.

base url: https://vip.jewproxy.tech/proxy/openrouter/v1
api key: your jewproxy token
model: claude opus 4.8 · claude fable 5 · claude sonnet 5 · or another from the dropdown
more help: buy.jewproxy.tech

a visual ui for both image and video generation. no api setup required.

01→ the url

https://img.jewproxy.tech

02→ the steps

open the frontend
pick image or video at the top
pick a model or preset
write a clear prompt
adjust options (size, count, duration for video, etc.)
press generate
save, tag, compare, or export the result

one ui covers both image and video models, so you can prototype prompts in one place before you call the api from code.

the image api, taught as a process. run export TOKEN="..." once with your jewproxy token — every command below sends $TOKEN, never a vendor key. then pick the tab whose model id you have: the id format has already chosen the route. four steps per provider — pick, send, read, fail.

01→ pick the model

the id format is the routing cue. a bare gpt-image* id with no vendor prefix means the native openai route — this tab. a vendor/slug id belongs on the openrouter tab instead, and a bare gemini *-image id on the google tab. pick a model below; the command in step 02 rewrites itself.

live list: GET https://vip.jewproxy.tech/proxy/openai-image/v1/models — the selector shows the common ones; the full list is live

02→ send the request

one post, one answer. the url ends in /v1/images/generations. the bearer header carries $TOKEN. the body is just model + prompt — optional size, quality, n, and response_format fields exist, and gpt-image-2 is the default if you omit the model.

curl --request POST \
  --url https://vip.jewproxy.tech/proxy/openai-image/v1/images/generations \
  --header "Authorization: Bearer $TOKEN" \
  --header "Content-Type: application/json" \
  --data '{"model": "gpt-image-2", "prompt": "a lighthouse at dawn, oil painting"}'

03→ read the result

this route is synchronous: http 200 and the image is already in the response. the url sits at data[0].url and is hosted by the proxy — open it or download it. no job id, no polling.

lands at: data[0].url — proxy-hosted

04→ when it fails

403 Model family 'gpt-image' is not enabled on this proxy — an admin must allow-list the family. your request was fine.
402 OpenAI image generation is unavailable or not yet verified on this proxy. — the proxy's upstream key is the problem; report it to the admin.
429 — two flavors. You've exceeded your token quota for this model type. means quota: wait for the reset or top up. otherwise it's the rate bucket (4/min default): slow down and retry.

error.code and error.type are always present on image routes — read them first, they name the failure before you guess.

dead end: /proxy/openai/v1/chat/completions does not generate images, whichever model id you send it.

01→ pick the model

a vendor/slug id — openai/gpt-image-2, black-forest-labs/flux.2-pro — routes to the normalized /images api. the prefix is the cue. this one route speaks for many vendors, so its fields are normalized too (step 02). pick a model below; the command rewrites itself.

live list: GET https://vip.jewproxy.tech/proxy/images/v1/models — the selector shows the common ones; the full list is live

02→ send the request

two phases. phase one submits: one post to /images/v1/generations with normalized fields — prompt, negative_prompt, count, quality, image_size (0.5K–4K), aspect_ratio. size does not exist here; that's the native route's word. the answer is 202 accepted with an imgjob_ id — 202 is not success, it only means queued. phase two polls GET /images/v1/generations/$JOB_ID until the status stops being accepted. the script below does both.

JOB_ID=$(curl --request POST \
  --url https://vip.jewproxy.tech/proxy/images/v1/generations \
  --header "Authorization: Bearer $TOKEN" \
  --header "Content-Type: application/json" \
  --data '{"model": "openai/gpt-image-2", "prompt": "a lighthouse at dawn, oil painting", "count": 1, "aspect_ratio": "1:1", "image_size": "1K", "quality": "auto"}' | jq -r .id)
while :; do
  RESPONSE=$(curl --silent https://vip.jewproxy.tech/proxy/images/v1/generations/$JOB_ID \
    --header "Authorization: Bearer $TOKEN")
  STATUS=$(echo "$RESPONSE" | jq -r .status)
  [ "$STATUS" = "accepted" ] || break
  sleep 2
done
URL=$(echo "$RESPONSE" | jq -r '.images[0].url // empty')
if [ -z "$URL" ]; then echo "$RESPONSE" | jq -r .error.message >&2; exit 1; fi
echo "$URL"

03→ read the result

when the status flips away from accepted, the poll is the verdict. on success the image is at images[0].url, hosted by the proxy, and the script prints it. on failure the script pushes .error.message to stderr and exits 1 — that message tells you which side failed.

lands at: images[0].url — proxy-hosted, after the poll

04→ when it fails

429 quota — You've exceeded your token quota for this model type. means wait for the reset or top up.
429 rate bucket — 4/min default; slow down and retry. the script already sleeps 2s between polls.
404 while polling — the job id is unknown or expired; jobs live 15 minutes. resubmit instead of polling a dead id.

error.code and error.type are always present on image routes — read them first, they name the failure before you guess.

dead end: /proxy/openrouter/v1/chat/completions cannot make images — only this /images route can.

01→ pick the model

a bare gemini id ending in -image — gemini-3.1-flash-image, gemini-3-pro-image — takes the native google-ai route. same rule as the other tabs: the id format chooses the route, and here it chose this one. pick a model below; the command rewrites itself.

live list: GET https://vip.jewproxy.tech/proxy/google-ai/v1/models — the selector shows the common ones; the full list is live

02→ send the request

one post, and the model id travels in the url path, not the body: /v1beta/models/<id>:generateContent. the body is google-shaped: contents[] carries the prompt text, generationConfig.responseModalities asks for IMAGE, and imageConfig sets aspectRatio and imageSize. the bearer header is $TOKEN as always.

curl --request POST \
  --url https://vip.jewproxy.tech/proxy/google-ai/v1beta/models/gemini-3.1-flash-image:generateContent \
  --header "Authorization: Bearer $TOKEN" \
  --header "Content-Type: application/json" \
  --data '{"contents": [{"role": "user", "parts": [{"text": "a lighthouse at dawn, oil painting"}]}], "generationConfig": {"responseModalities": ["IMAGE"], "imageConfig": {"aspectRatio": "1:1", "imageSize": "1K"}}}' \
  | jq -r '.candidates[0].content.parts[] | select(.inlineData) | .inlineData.data' | head -n1 | base64 -d > image.png

03→ read the result

synchronous like the openai route, but with a twist: no hosted url exists here. the image comes back as base64 at candidates[0].content.parts[].inlineData.data. the jq pipe in the command extracts that field and decodes it into image.png — you materialize the file yourself.

lands at: decoded image.png — no hosted url on this route

04→ when it fails

429 quota — You've exceeded your token quota for this model type. means wait for the reset or top up.
429 rate bucket — 4/min default; slow down and retry.
403 — the model family is not allow-listed on this proxy; an admin must enable it. your request was fine.

error.code and error.type are always present on image routes — read them first, they name the failure before you guess.

for local cli agents (claude code, codex, or opencode).

open the agentic coding button on this page (the one to the right of how to use)
pick claude code, codex, or opencode
download the generated config file(s)
place each file at the path the popup shows for your os (mac / linux / windows)
open the cli. it should pick up the config

the config files store your token in clear text. don't commit them to a repo or share screenshots.

not needed for: sillytavern or any chat frontend
questions: buy.jewproxy.tech

more help: buy.jewproxy.tech esc close · enter select