{
  "key": "qwen-turbo",
  "name": "Qwen Turbo",
  "description": "Efficient Qwen model for fast chat, extraction, and high-volume workloads",
  "lab": "alibaba",
  "family": "qwen",
  "release_date": "2024-11-01",
  "knowledge": "2024-04",
  "open_weights": false,
  "has_free_offering": false,
  "published": true,
  "modalities": {
    "input": [
      "text"
    ],
    "output": [
      "text"
    ]
  },
  "capabilities": {
    "reasoning": true,
    "tool_call": true,
    "structured_output": null,
    "attachment": false,
    "reasoning_options": [
      {
        "type": "toggle"
      },
      {
        "type": "budget_tokens"
      }
    ]
  },
  "limit": {
    "context": 1000000,
    "output": 16384
  },
  "offerings": [
    {
      "provider": "alibaba",
      "provider_model_id": "qwen-turbo",
      "name": "Qwen Turbo",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.05,
        "output": 0.2,
        "cache_read": null,
        "cache_write": null,
        "reasoning": 0.5,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1000000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2025-04-28"
    },
    {
      "provider": "alibaba-cn",
      "provider_model_id": "qwen-turbo",
      "name": "Qwen Turbo",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.044,
        "output": 0.087,
        "cache_read": null,
        "cache_write": null,
        "reasoning": 0.431,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1000000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2025-07-15"
    },
    {
      "provider": "nano-gpt",
      "provider_model_id": "qwen/qwen-turbo",
      "name": "Qwen Turbo",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.04998,
        "output": 0.2006,
        "cache_read": 0.02499,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 1000000,
        "output": 8192,
        "input": 1000000
      },
      "status": null,
      "last_updated": "2025-04-28"
    },
    {
      "provider": "ofox",
      "provider_model_id": "bailian/qwen-turbo",
      "name": "Qwen Turbo",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.05,
        "output": 0.09,
        "cache_read": 0.0086,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 16384,
        "input": null
      },
      "status": null,
      "last_updated": "2025-04-28"
    },
    {
      "provider": "ofox",
      "provider_model_id": "qwen/qwen-turbo",
      "name": "Qwen Turbo",
      "variants": [],
      "free": false,
      "priced": true,
      "cost": {
        "input": 0.043,
        "output": 0.09,
        "cache_read": 0.0086,
        "cache_write": null,
        "reasoning": null,
        "context_over_200k": null,
        "tiers": null
      },
      "limit": {
        "context": 128000,
        "output": 16000,
        "input": null
      },
      "status": null,
      "last_updated": "2025-04-28"
    },
    {
      "provider": "qiniu-ai",
      "provider_model_id": "qwen-turbo",
      "name": "Qwen-Turbo",
      "variants": [],
      "free": false,
      "priced": false,
      "cost": null,
      "limit": {
        "context": 1000000,
        "output": 4096,
        "input": null
      },
      "status": null,
      "last_updated": "2025-08-05"
    }
  ]
}