hack/tools/scripts/llm-key-hunter/results/_cache/content/besnikbelegu_litellm-open-webui.json

{"repo": "besnikbelegu/litellm-open-webui", "files": {"docs/my-website/docs/providers/deepseek.md": {"0307a0133bcbba944dfaa15c84c0582d28f19646": {"t": 1785746560.2737408, "n": 3070, "h": "37d67dd35c55120b", "c": "import Tabs from '@theme/Tabs';\nimport TabItem from '@theme/TabItem';\n\n# Deepseek\nhttps://deepseek.com/\n\n**We support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests**\n\n## API Key\n```python\n# env variable\nos.environ['DEEPSEEK_API_KEY']\n```\n\n## Sample Usage\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n)\nprint(response)\n```\n\n## Sample Usage - Streaming\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n    stream=True\n)\n\nfor chunk in response:\n    print(chunk)\n```\n\n\n## Supported Models - ALL Deepseek Models Supported!\nWe support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests\n\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-chat | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n| deepseek-coder | `completion(model=\"deepseek/deepseek-coder\", messages)` | \n\n\n## Reasoning Models\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-reasoner | `completion(model=\"deepseek/deepseek-reasoner\", messages)` | \n\n\n\n<Tabs>\n<TabItem value=\"sdk\" label=\"SDK\">\n\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresp = completion(\n    model=\"deepseek/deepseek-reasoner\",\n    messages=[{\"role\": \"user\", \"content\": \"Tell me a joke.\"}],\n)\n\nprint(\n    resp.choices[0].message.reasoning_content\n)\n```\n\n</TabItem>\n<TabItem value=\"proxy\" label=\"PROXY\">\n\n1. Setup config.yaml\n\n```yaml\nmodel_list:\n  - model_name: deepseek-reasoner\n    litellm_params:\n        model: deepseek/deepseek-reasoner\n        api_key: os.environ/DEEPSEEK_API_KEY\n```\n\n2. Run proxy\n\n```bash\npython litellm/proxy/main.py\n```\n\n3. Test it!\n\n```bash\ncurl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \\\n-H 'Content-Type: application/json' \\\n-H 'Authorization: Bearer sk-1234' \\\n-d '{\n    \"model\": \"deepseek-reasoner\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"text\",\n            \"text\": \"Hi, how are you ?\"\n          }\n        ]\n      }\n    ]\n}'\n```\n\n</TabItem>\n\n</Tabs>"}, "a699000a4b02844349649002f5240d9cc70cca87": {"t": 1785765690.730457, "n": 3070, "h": "37d67dd35c55120b", "c": "import Tabs from '@theme/Tabs';\nimport TabItem from '@theme/TabItem';\n\n# Deepseek\nhttps://deepseek.com/\n\n**We support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests**\n\n## API Key\n```python\n# env variable\nos.environ['DEEPSEEK_API_KEY']\n```\n\n## Sample Usage\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n)\nprint(response)\n```\n\n## Sample Usage - Streaming\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n    stream=True\n)\n\nfor chunk in response:\n    print(chunk)\n```\n\n\n## Supported Models - ALL Deepseek Models Supported!\nWe support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests\n\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-chat | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n| deepseek-coder | `completion(model=\"deepseek/deepseek-coder\", messages)` | \n\n\n## Reasoning Models\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-reasoner | `completion(model=\"deepseek/deepseek-reasoner\", messages)` | \n\n\n\n<Tabs>\n<TabItem value=\"sdk\" label=\"SDK\">\n\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresp = completion(\n    model=\"deepseek/deepseek-reasoner\",\n    messages=[{\"role\": \"user\", \"content\": \"Tell me a joke.\"}],\n)\n\nprint(\n    resp.choices[0].message.reasoning_content\n)\n```\n\n</TabItem>\n<TabItem value=\"proxy\" label=\"PROXY\">\n\n1. Setup config.yaml\n\n```yaml\nmodel_list:\n  - model_name: deepseek-reasoner\n    litellm_params:\n        model: deepseek/deepseek-reasoner\n        api_key: os.environ/DEEPSEEK_API_KEY\n```\n\n2. Run proxy\n\n```bash\npython litellm/proxy/main.py\n```\n\n3. Test it!\n\n```bash\ncurl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \\\n-H 'Content-Type: application/json' \\\n-H 'Authorization: Bearer sk-1234' \\\n-d '{\n    \"model\": \"deepseek-reasoner\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"text\",\n            \"text\": \"Hi, how are you ?\"\n          }\n        ]\n      }\n    ]\n}'\n```\n\n</TabItem>\n\n</Tabs>"}, "76795dba39a60088891306198f06796d4319c36e": {"t": 1785765692.3438694, "n": 3098, "h": "656152e96dbfa80c", "c": "import Tabs from '@theme/Tabs';\nimport TabItem from '@theme/TabItem';\n\n# Deepseek\nhttps://deepseek.com/\n\n**We support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests**\n\n## API Key\n```python\n# env variable\nos.environ['DEEPSEEK_API_KEY']\n```\n\n## Sample Usage\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n)\nprint(response)\n```\n\n## Sample Usage - Streaming\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n    stream=True\n)\n\nfor chunk in response:\n    print(chunk)\n```\n\n\n## Supported Models - ALL Deepseek Models Supported!\nWe support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests\n\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-chat | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n| deepseek-coder | `completion(model=\"deepseek/deepseek-coder\", messages)` | \n\n\n## Reasoning Models\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-reasoner | `completion(model=\"deepseek/deepseek-reasoner\", messages)` | \n\n\n\n<Tabs>\n<TabItem value=\"sdk\" label=\"SDK\">\n\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresp = completion(\n    model=\"deepseek/deepseek-reasoner\",\n    messages=[{\"role\": \"user\", \"content\": \"Tell me a joke.\"}],\n)\n\nprint(\n    resp.choices[0].message.provider_specific_fields[\"reasoning_content\"]\n)\n```\n\n</TabItem>\n<TabItem value=\"proxy\" label=\"PROXY\">\n\n1. Setup config.yaml\n\n```yaml\nmodel_list:\n  - model_name: deepseek-reasoner\n    litellm_params:\n        model: deepseek/deepseek-reasoner\n        api_key: os.environ/DEEPSEEK_API_KEY\n```\n\n2. Run proxy\n\n```bash\npython litellm/proxy/main.py\n```\n\n3. Test it!\n\n```bash\ncurl -L -X POST 'http://0.0.0.0:4000/v1/chat/completions' \\\n-H 'Content-Type: application/json' \\\n-H 'Authorization: Bearer sk-1234' \\\n-d '{\n    \"model\": \"deepseek-reasoner\",\n    \"messages\": [\n      {\n        \"role\": \"user\",\n        \"content\": [\n          {\n            \"type\": \"text\",\n            \"text\": \"Hi, how are you ?\"\n          }\n        ]\n      }\n    ]\n}'\n```\n\n</TabItem>\n\n</Tabs>"}, "504a742622be1006d51cb2edd4023c2345c23ef4": {"t": 1785765693.7882895, "n": 1487, "h": "343e57134c5e2e16", "c": "# Deepseek\nhttps://deepseek.com/\n\n**We support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests**\n\n## API Key\n```python\n# env variable\nos.environ['DEEPSEEK_API_KEY']\n```\n\n## Sample Usage\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n)\nprint(response)\n```\n\n## Sample Usage - Streaming\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n    stream=True\n)\n\nfor chunk in response:\n    print(chunk)\n```\n\n\n## Supported Models - ALL Deepseek Models Supported!\nWe support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests\n\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-chat | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n| deepseek-coder | `completion(model=\"deepseek/deepseek-coder\", messages)` | \n\n\n"}, "90eb0ea022792a95a1d613a8cbc0681c3aa01ce8": {"t": 1785765695.5723948, "n": 1486, "h": "8887e09649b2d09d", "c": "# Deepseek\nhttps://deepseek.com/\n\n**We support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests**\n\n## API Key\n```python\n# env variable\nos.environ['DEEPSEEK_API_KEY']\n```\n\n## Sample Usage\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n)\nprint(response)\n```\n\n## Sample Usage - Streaming\n```python\nfrom litellm import completion\nimport os\n\nos.environ['DEEPSEEK_API_KEY'] = \"\"\nresponse = completion(\n    model=\"deepseek/deepseek-chat\", \n    messages=[\n       {\"role\": \"user\", \"content\": \"hello from litellm\"}\n   ],\n    stream=True\n)\n\nfor chunk in response:\n    print(chunk)\n```\n\n\n## Supported Models - ALL Deepseek Models Supported!\nWe support ALL Deepseek models, just set `deepseek/` as a prefix when sending completion requests\n\n| Model Name               | Function Call                                                                                                                                                      |\n|--------------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| deepseek-chat | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n| deepseek-coder | `completion(model=\"deepseek/deepseek-chat\", messages)` | \n\n\n"}}}}