gemma-sea-lion-v4-27b-it

a

gemma-sea-lion-v4-27b-it

Text Generation • aisingapore

@cf/aisingapore/gemma-sea-lion-v4-27b-it

SEA-LION stands for Southeast Asian Languages In One Network, which is a collection of Large Language Models (LLMs) which have been pretrained and instruct-tuned for the Southeast Asia (SEA) region.

Model Info
Context Window ↗	128,000 tokens
Unit Pricing	$0.35 per M input tokens, $0.56 per M output tokens

Playground

Try out this model with Workers AI LLM Playground. It does not require any setup or authentication and an instant way to preview and test a model directly in the browser.

Launch the LLM Playground

Usage

Worker - Streaming

TypeScript

export interface Env {
  AI: Ai;
}

export default {
  async fetch(request, env): Promise<Response> {

    const messages = [
      { role: "system", content: "You are a friendly assistant" },
      {
        role: "user",
        content: "What is the origin of the phrase Hello, World",
      },
    ];

    const stream = await env.AI.run("@cf/aisingapore/gemma-sea-lion-v4-27b-it", {
      messages,
      stream: true,
    });

    return new Response(stream, {
      headers: { "content-type": "text/event-stream" },
    });
  },
} satisfies ExportedHandler<Env>;

Worker

TypeScript

export interface Env {
  AI: Ai;
}

export default {
  async fetch(request, env): Promise<Response> {

    const messages = [
      { role: "system", content: "You are a friendly assistant" },
      {
        role: "user",
        content: "What is the origin of the phrase Hello, World",
      },
    ];
    const response = await env.AI.run("@cf/aisingapore/gemma-sea-lion-v4-27b-it", { messages });

    return Response.json(response);
  },
} satisfies ExportedHandler<Env>;

Python

Python

import os
import requests

ACCOUNT_ID = "your-account-id"
AUTH_TOKEN = os.environ.get("CLOUDFLARE_AUTH_TOKEN")

prompt = "Tell me all about PEP-8"
response = requests.post(
  f"https://api.cloudflare.com/client/v4/accounts/{ACCOUNT_ID}/ai/run/@cf/aisingapore/gemma-sea-lion-v4-27b-it",
    headers={"Authorization": f"Bearer {AUTH_TOKEN}"},
    json={
      "messages": [
        {"role": "system", "content": "You are a friendly assistant"},
        {"role": "user", "content": prompt}
      ]
    }
)
result = response.json()
print(result)

curl

curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run/@cf/aisingapore/gemma-sea-lion-v4-27b-it \
  -X POST \
  -H "Authorization: Bearer $CLOUDFLARE_AUTH_TOKEN" \
  -d '{ "messages": [{ "role": "system", "content": "You are a friendly assistant" }, { "role": "user", "content": "Why is pizza so good" }]}'

OpenAI compatible endpoints

Workers AI also supports OpenAI compatible API endpoints for /v1/chat/completions and /v1/embeddings. For more details, refer to Configurations .

Parameters

* indicates a required field

Input

• 0 object
  • $merge

• 1 object
  • $merge

• 2 object
  • requests array required
    • items one of
      • 0 object
        • $merge

      • 1 object
        • $merge

Output

• 0 object
  • id string

    Unique identifier for the completion

  • object string

    Object type identifier

  • created number

    Unix timestamp of when the completion was created

  • model string

    Model used for the completion

  • choices array

    List of completion choices

    • items object
      • index number

        Index of the choice in the list

      • message object

        The message generated by the model

        • role string required

          Role of the message author

        • content string required

          The content of the message

        • reasoning_content string

          Internal reasoning content (if available)

        • tool_calls array

          Tool calls made by the assistant

          • items object
            • id string required

              Unique identifier for the tool call

            • type string required

              Type of tool call

            • function object required
              • name string required

                Name of the function to call

              • arguments string required

                JSON string of arguments for the function

      • finish_reason string

        Reason why the model stopped generating

      • stop_reason string

        Stop reason (may be null)

      • logprobs object

        Log probabilities (if requested)

  • usage

  • prompt_logprobs object

    Log probabilities for the prompt (if requested)

• 1 object
  • id string

    Unique identifier for the completion

  • object string

    Object type identifier

  • created number

    Unix timestamp of when the completion was created

  • model string

    Model used for the completion

  • choices array

    List of completion choices

    • items object
      • index number required

        Index of the choice in the list

      • text string required

        The generated text completion

      • finish_reason string required

        Reason why the model stopped generating

      • stop_reason string

        Stop reason (may be null)

      • logprobs object

        Log probabilities (if requested)

      • prompt_logprobs object

        Log probabilities for the prompt (if requested)

  • usage

• 2 string

• 3 object
  • request_id string

    The async request id that can be used to obtain the results.

API Schemas

The following schemas are based on JSON Schema

Input

{
    "$id": "http://ai.cloudflare.com/schemas/textGenerationInput",
    "type": "object",
    "oneOf": [
        {
            "title": "Prompt",
            "properties": {
                "$merge": {
                    "source": {
                        "prompt": {
                            "$ref": "textGenerationPrompts#/prompt"
                        },
                        "lora": {
                            "$ref": "textGenerationFinetune#/lora"
                        },
                        "response_format": {
                            "$ref": "jsonMode#/response_format"
                        }
                    },
                    "with": {
                        "raw": {
                            "type": "boolean",
                            "default": false,
                            "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
                        },
                        "stream": {
                            "type": "boolean",
                            "default": false,
                            "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events."
                        },
                        "max_tokens": {
                            "type": "integer",
                            "default": 2000,
                            "description": "The maximum number of tokens to generate in the response."
                        },
                        "temperature": {
                            "type": "number",
                            "default": 0.6,
                            "minimum": 0,
                            "maximum": 5,
                            "description": "Controls the randomness of the output; higher values produce more random results."
                        },
                        "top_p": {
                            "type": "number",
                            "minimum": 0.001,
                            "maximum": 1,
                            "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
                        },
                        "top_k": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 50,
                            "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."
                        },
                        "seed": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 9999999999,
                            "description": "Random seed for reproducibility of the generation."
                        },
                        "repetition_penalty": {
                            "type": "number",
                            "minimum": 0,
                            "maximum": 2,
                            "description": "Penalty for repeated tokens; higher values discourage repetition."
                        },
                        "frequency_penalty": {
                            "type": "number",
                            "minimum": -2,
                            "maximum": 2,
                            "description": "Decreases the likelihood of the model repeating the same lines verbatim."
                        },
                        "presence_penalty": {
                            "type": "number",
                            "minimum": -2,
                            "maximum": 2,
                            "description": "Increases the likelihood of the model introducing new topics."
                        }
                    }
                }
            },
            "required": [
                "prompt"
            ]
        },
        {
            "title": "Messages",
            "properties": {
                "$merge": {
                    "source": {
                        "messages": {
                            "$ref": "textGenerationPrompts#/messages"
                        },
                        "functions": {
                            "$ref": "textGenerationTools#/functions"
                        },
                        "tools": {
                            "$ref": "textGenerationTools#/tools"
                        },
                        "response_format": {
                            "$ref": "jsonMode#/response_format"
                        }
                    },
                    "with": {
                        "raw": {
                            "type": "boolean",
                            "default": false,
                            "description": "If true, a chat template is not applied and you must adhere to the specific model's expected formatting."
                        },
                        "stream": {
                            "type": "boolean",
                            "default": false,
                            "description": "If true, the response will be streamed back incrementally using SSE, Server Sent Events."
                        },
                        "max_tokens": {
                            "type": "integer",
                            "default": 2000,
                            "description": "The maximum number of tokens to generate in the response."
                        },
                        "temperature": {
                            "type": "number",
                            "default": 0.6,
                            "minimum": 0,
                            "maximum": 5,
                            "description": "Controls the randomness of the output; higher values produce more random results."
                        },
                        "top_p": {
                            "type": "number",
                            "minimum": 0.001,
                            "maximum": 1,
                            "description": "Adjusts the creativity of the AI's responses by controlling how many possible words it considers. Lower values make outputs more predictable; higher values allow for more varied and creative responses."
                        },
                        "top_k": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 50,
                            "description": "Limits the AI to choose from the top 'k' most probable words. Lower values make responses more focused; higher values introduce more variety and potential surprises."
                        },
                        "seed": {
                            "type": "integer",
                            "minimum": 1,
                            "maximum": 9999999999,
                            "description": "Random seed for reproducibility of the generation."
                        },
                        "repetition_penalty": {
                            "type": "number",
                            "minimum": 0,
                            "maximum": 2,
                            "description": "Penalty for repeated tokens; higher values discourage repetition."
                        },
                        "frequency_penalty": {
                            "type": "number",
                            "minimum": -2,
                            "maximum": 2,
                            "description": "Decreases the likelihood of the model repeating the same lines verbatim."
                        },
                        "presence_penalty": {
                            "type": "number",
                            "minimum": -2,
                            "maximum": 2,
                            "description": "Increases the likelihood of the model introducing new topics."
                        }
                    }
                }
            },
            "required": [
                "messages"
            ]
        },
        {
            "title": "Async Batch",
            "type": "object",
            "properties": {
                "requests": {
                    "type": "array",
                    "items": {
                        "type": "object",
                        "oneOf": [
                            {
                                "title": "Prompt",
                                "properties": {
                                    "$merge": {
                                        "source": {
                                            "prompt": {
                                                "$ref": "textGenerationPrompts#/prompt"
                                            },
                                            "lora": {
                                                "$ref": "textGenerationFinetune#/lora"
                                            },
                                            "response_format": {
                                                "$ref": "jsonMode#/response_format"
                                            }
                                        },
                                        "with": {
                                            "$ref": "textGenerationOptions#/common"
                                        }
                                    }
                                },
                                "required": [
                                    "prompt"
                                ]
                            },
                            {
                                "title": "Messages",
                                "properties": {
                                    "$merge": {
                                        "source": {
                                            "messages": {
                                                "$ref": "textGenerationPrompts#/messages"
                                            },
                                            "functions": {
                                                "$ref": "textGenerationTools#/functions"
                                            },
                                            "tools": {
                                                "$ref": "textGenerationTools#/tools"
                                            },
                                            "response_format": {
                                                "$ref": "jsonMode#/response_format"
                                            }
                                        },
                                        "with": {
                                            "$ref": "textGenerationOptions#/common"
                                        }
                                    }
                                },
                                "required": [
                                    "messages"
                                ]
                            }
                        ]
                    }
                }
            },
            "required": [
                "requests"
            ]
        }
    ]
}

Output

{
    "oneOf": [
        {
            "type": "object",
            "contentType": "application/json",
            "title": "Chat Completion Response",
            "properties": {
                "id": {
                    "type": "string",
                    "description": "Unique identifier for the completion"
                },
                "object": {
                    "type": "string",
                    "enum": [
                        "chat.completion"
                    ],
                    "description": "Object type identifier"
                },
                "created": {
                    "type": "number",
                    "description": "Unix timestamp of when the completion was created"
                },
                "model": {
                    "type": "string",
                    "description": "Model used for the completion"
                },
                "choices": {
                    "type": "array",
                    "description": "List of completion choices",
                    "items": {
                        "type": "object",
                        "properties": {
                            "index": {
                                "type": "number",
                                "description": "Index of the choice in the list"
                            },
                            "message": {
                                "type": "object",
                                "description": "The message generated by the model",
                                "properties": {
                                    "role": {
                                        "type": "string",
                                        "description": "Role of the message author"
                                    },
                                    "content": {
                                        "type": "string",
                                        "description": "The content of the message"
                                    },
                                    "reasoning_content": {
                                        "type": "string",
                                        "description": "Internal reasoning content (if available)"
                                    },
                                    "tool_calls": {
                                        "type": "array",
                                        "description": "Tool calls made by the assistant",
                                        "items": {
                                            "type": "object",
                                            "properties": {
                                                "id": {
                                                    "type": "string",
                                                    "description": "Unique identifier for the tool call"
                                                },
                                                "type": {
                                                    "type": "string",
                                                    "enum": [
                                                        "function"
                                                    ],
                                                    "description": "Type of tool call"
                                                },
                                                "function": {
                                                    "type": "object",
                                                    "properties": {
                                                        "name": {
                                                            "type": "string",
                                                            "description": "Name of the function to call"
                                                        },
                                                        "arguments": {
                                                            "type": "string",
                                                            "description": "JSON string of arguments for the function"
                                                        }
                                                    },
                                                    "required": [
                                                        "name",
                                                        "arguments"
                                                    ]
                                                }
                                            },
                                            "required": [
                                                "id",
                                                "type",
                                                "function"
                                            ]
                                        }
                                    }
                                },
                                "required": [
                                    "role",
                                    "content"
                                ]
                            },
                            "finish_reason": {
                                "type": "string",
                                "description": "Reason why the model stopped generating"
                            },
                            "stop_reason": {
                                "type": [
                                    "string",
                                    "null"
                                ],
                                "description": "Stop reason (may be null)"
                            },
                            "logprobs": {
                                "type": [
                                    "object",
                                    "null"
                                ],
                                "description": "Log probabilities (if requested)"
                            }
                        }
                    }
                },
                "usage": {
                    "$ref": "usage#/usage"
                },
                "prompt_logprobs": {
                    "type": [
                        "object",
                        "null"
                    ],
                    "description": "Log probabilities for the prompt (if requested)"
                }
            }
        },
        {
            "type": "object",
            "contentType": "application/json",
            "title": "Text Completion Response",
            "properties": {
                "id": {
                    "type": "string",
                    "description": "Unique identifier for the completion"
                },
                "object": {
                    "type": "string",
                    "enum": [
                        "text_completion"
                    ],
                    "description": "Object type identifier"
                },
                "created": {
                    "type": "number",
                    "description": "Unix timestamp of when the completion was created"
                },
                "model": {
                    "type": "string",
                    "description": "Model used for the completion"
                },
                "choices": {
                    "type": "array",
                    "description": "List of completion choices",
                    "items": {
                        "type": "object",
                        "properties": {
                            "index": {
                                "type": "number",
                                "description": "Index of the choice in the list"
                            },
                            "text": {
                                "type": "string",
                                "description": "The generated text completion"
                            },
                            "finish_reason": {
                                "type": "string",
                                "description": "Reason why the model stopped generating"
                            },
                            "stop_reason": {
                                "type": [
                                    "string",
                                    "null"
                                ],
                                "description": "Stop reason (may be null)"
                            },
                            "logprobs": {
                                "type": [
                                    "object",
                                    "null"
                                ],
                                "description": "Log probabilities (if requested)"
                            },
                            "prompt_logprobs": {
                                "type": [
                                    "object",
                                    "null"
                                ],
                                "description": "Log probabilities for the prompt (if requested)"
                            }
                        },
                        "required": [
                            "index",
                            "text",
                            "finish_reason"
                        ]
                    }
                },
                "usage": {
                    "$ref": "usage#/usage"
                }
            }
        },
        {
            "type": "string",
            "contentType": "text/event-stream",
            "format": "binary"
        },
        {
            "type": "object",
            "contentType": "application/json",
            "title": "Async response",
            "properties": {
                "request_id": {
                    "type": "string",
                    "description": "The async request id that can be used to obtain the results."
                }
            }
        }
    ]
}