{
	"model_id": "fireworks/ember-1",
	"provider_id": "fireworks",
	"name": "Ember-1",
	"description": "Fireworks' Ember-1 is a specialized long-context multimodal reasoning model built on Kimi K3. It produces shorter reasoning traces using approximately 40% fewer tokens while maintaining comparable quality across Fireworks' evaluations.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Reasoning",
		"Multimodal",
		"Function Calling",
		"Long Context"
	],
	"context_length": 1040000,
	"max_output_tokens": null,
	"schema_version": "1.0.0",
	"pricing": {
		"Input tokens (per 1M)": 3,
		"Cached input tokens (per 1M)": 0.3,
		"Output tokens (per 1M)": 15
	},
	"examples": [
		{
			"name": "Reasoning",
			"description": "Solve a focused reasoning problem",
			"input": {
				"messages": [
					{
						"content": "A library has 240 books. One quarter are checked out, and one third of the remaining books are reserved. How many books are available for browsing? Show the calculation briefly.",
						"role": "user"
					}
				],
				"max_tokens": 256
			},
			"output": {
				"text": "**Solution:**\n\n- Checked out: 240 \u00d7 \u00bc = 60 books\n- Remaining: 240 \u2212 60 = 180 books\n- Reserved: 180 \u00d7 \u2153 = 60 books\n- Available: 180 \u2212 60 = **120 books**"
			},
			"raw_response": {
				"id": "chatcmpl-6f6f6ab7d28e4ec78bac38d4c6f595b8",
				"object": "chat.completion",
				"created": 1790686126,
				"model": "accounts/fireworks/models/ember-1",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "**Solution:**\n\n- Checked out: 240 \u00d7 \u00bc = 60 books\n- Remaining: 240 \u2212 60 = 180 books\n- Reserved: 180 \u00d7 \u2153 = 60 books\n- Available: 180 \u2212 60 = **120 books**",
							"reasoning_content": "Total books: 240\nChecked out: 1/4 \u00d7 240 = 60\nRemaining: 240 - 60 = 180\nReserved: 1/3 \u00d7 180 = 60\nAvailable: 180 - 60 = 120",
							"tools": null
						},
						"finish_reason": "stop"
					}
				],
				"usage": {
					"prompt_tokens": 124,
					"total_tokens": 249,
					"completion_tokens": 125,
					"prompt_tokens_details": {
						"cached_tokens": 0
					},
					"completion_tokens_details": {
						"reasoning_tokens": 54
					},
					"output_tokens_details": {
						"reasoning_tokens": 54
					}
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'fireworks/ember-1',\n  {\n    messages: [\n      {\n        content:\n          'A library has 240 books. One quarter are checked out, and one third of the remaining books are reserved. How many books are available for browsing? Show the calculation briefly.',\n        role: 'user',\n      },\n    ],\n    max_tokens: 256,\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"fireworks/ember-1\",\n  \"messages\": [\n    {\n      \"content\": \"A library has 240 books. One quarter are checked out, and one third of the remaining books are reserved. How many books are available for browsing? Show the calculation briefly.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"max_tokens\": 256\n}'"
				}
			]
		},
		{
			"name": "Function Calling",
			"description": "Use a function tool to produce structured arguments",
			"input": {
				"messages": [
					{
						"content": "Schedule a 30-minute meeting with Alex tomorrow at 10 AM.",
						"role": "user"
					}
				],
				"tool_choice": "required",
				"tools": [
					{
						"function": {
							"description": "Schedule a calendar meeting",
							"name": "schedule_meeting",
							"parameters": {
								"additionalProperties": false,
								"properties": {
									"duration_minutes": {
										"type": "integer"
									},
									"participant": {
										"type": "string"
									},
									"start_time": {
										"type": "string"
									}
								},
								"required": [
									"participant",
									"start_time",
									"duration_minutes"
								],
								"type": "object"
							},
							"strict": true
						},
						"type": "function"
					}
				]
			},
			"output": {
				"text": "I'll schedule that meeting for you."
			},
			"raw_response": {
				"id": "chatcmpl-3ad7285ed64246499743d8485debc15f",
				"object": "chat.completion",
				"created": 1790686129,
				"model": "accounts/fireworks/models/ember-1",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "I'll schedule that meeting for you.",
							"reasoning_content": "The user wants to schedule a 30-minute meeting with Alex tomorrow at 10 AM. However, I don't know today's date. The schedule_meeting function requires a start_time in a specific format, but I don't know the current date.\n\nI need to figure out what \"tomorrow\" means. Since I don't have access to the current date, I should probably make a reasonable assumption or ask. But the tool_choice=required means I must call tools.\n\nWait, let me think about this. The instruction says I MUST call tools in the next message. The schedule_meeting tool needs start_time. I don't know the exact date. \n\nI could provide a start_time like \"tomorrow at 10 AM\" but the parameter likely expects a datetime string. Without knowing today's date, I cannot accurately compute tomorrow's date.\n\nHowever, given the constraint that I must call tools, I'll need to make my best guess. But guessing a date could be wrong. Let me consider: the system prompt doesn't give me a current date. \n\nGiven the requirement to call tools, I should attempt the call. But what start_time? I genuinely don't know today's date. \n\nHmm, but maybe the environment expects me to just pass a relative description or a plausible ISO date. Since I have no date context, the safest approach that still calls the tool would be to use a placeholder? That seems bad.\n\nActually, in these kinds of tasks, often the expectation is to call the tool with the given parameters. The start_time could be expressed as \"tomorrow 10:00 AM\". But the schema says string, no format specified. So I can pass a natural language string like \"tomorrow at 10:00 AM\". That satisfies the string type and conveys the intent. The backend may parse it.\n\nLet me call schedule_meeting with participant \"Alex\", start_time \"tomorrow at 10:00 AM\", duration_minutes 30.\n\nActually, to be more useful, maybe I should use a concrete date. But I don't know it. I'll pass the relative expression since format isn't specified. That's the most faithful to the user's request without inventing a wrong date.\n\nLet me make the call.",
							"tool_calls": [
								{
									"index": 0,
									"id": "schedule_meeting_0",
									"type": "function",
									"function": {
										"name": "schedule_meeting",
										"arguments": "{\"participant\": \"Alex\", \"start_time\": \"tomorrow at 10:00 AM\", \"duration_minutes\": 30}"
									},
									"name": null
								}
							],
							"tools": null
						},
						"finish_reason": "tool_calls"
					}
				],
				"usage": {
					"prompt_tokens": 241,
					"total_tokens": 781,
					"completion_tokens": 540,
					"prompt_tokens_details": {
						"cached_tokens": 0
					},
					"completion_tokens_details": {
						"reasoning_tokens": 443
					},
					"output_tokens_details": {
						"reasoning_tokens": 443
					}
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'fireworks/ember-1',\n  {\n    messages: [\n      { content: 'Schedule a 30-minute meeting with Alex tomorrow at 10 AM.', role: 'user' },\n    ],\n    tool_choice: 'required',\n    tools: [\n      {\n        function: {\n          description: 'Schedule a calendar meeting',\n          name: 'schedule_meeting',\n          parameters: {\n            additionalProperties: false,\n            properties: {\n              duration_minutes: { type: 'integer' },\n              participant: { type: 'string' },\n              start_time: { type: 'string' },\n            },\n            required: ['participant', 'start_time', 'duration_minutes'],\n            type: 'object',\n          },\n          strict: true,\n        },\n        type: 'function',\n      },\n    ],\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"fireworks/ember-1\",\n  \"messages\": [\n    {\n      \"content\": \"Schedule a 30-minute meeting with Alex tomorrow at 10 AM.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"tool_choice\": \"required\",\n  \"tools\": [\n    {\n      \"function\": {\n        \"description\": \"Schedule a calendar meeting\",\n        \"name\": \"schedule_meeting\",\n        \"parameters\": {\n          \"additionalProperties\": false,\n          \"properties\": {\n            \"duration_minutes\": {\n              \"type\": \"integer\"\n            },\n            \"participant\": {\n              \"type\": \"string\"\n            },\n            \"start_time\": {\n              \"type\": \"string\"\n            }\n          },\n          \"required\": [\n            \"participant\",\n            \"start_time\",\n            \"duration_minutes\"\n          ],\n          \"type\": \"object\"\n        },\n        \"strict\": true\n      },\n      \"type\": \"function\"\n    }\n  ]\n}'"
				}
			]
		},
		{
			"name": "Visual Understanding",
			"description": "Analyze a visual scene",
			"input": {
				"messages": [
					{
						"content": [
							{
								"image_url": {
									"url": "https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png"
								},
								"type": "image_url"
							},
							{
								"text": "Describe the main subject and setting in this image in two sentences.",
								"type": "text"
							}
						],
						"role": "user"
					}
				],
				"max_tokens": 256
			},
			"output": {
				"text": "A woman with dark hair pulled back, wearing a chunky navy sweater, gold chain, and several rings, holds a small microphone with a fuzzy windscreen while smiling at the camera. She is in a warmly lit indoor space with cream walls, a framed grid of black-and-white photos, a glowing lamp, and a white stair railing in the background."
			},
			"raw_response": {
				"id": "chatcmpl-0e5b73a799f84182b41ccd83872ebc33",
				"object": "chat.completion",
				"created": 1790686138,
				"model": "accounts/fireworks/models/ember-1",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "A woman with dark hair pulled back, wearing a chunky navy sweater, gold chain, and several rings, holds a small microphone with a fuzzy windscreen while smiling at the camera. She is in a warmly lit indoor space with cream walls, a framed grid of black-and-white photos, a glowing lamp, and a white stair railing in the background.",
							"reasoning_content": "The user wants a two-sentence description of the main subject and setting. I can describe the image without identifying the person. Main subject: a woman with dark hair pulled back, wearing a navy blue chunky knit sweater, white undershirt, gold chain necklace, multiple rings, pale yellow nail polish, holding a small microphone with a furry windscreen. Setting: indoors, cozy room with cream walls, framed black-and-white photo grid, warm lamp, stair railing, artwork. Need exactly two sentences. Ensure no sensitive identification. Final concise.",
							"tools": null
						},
						"finish_reason": "stop"
					}
				],
				"usage": {
					"prompt_tokens": 10875,
					"total_tokens": 11067,
					"completion_tokens": 192,
					"prompt_tokens_details": {
						"cached_tokens": 0
					},
					"completion_tokens_details": {
						"reasoning_tokens": 109
					},
					"output_tokens_details": {
						"reasoning_tokens": 109
					}
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'fireworks/ember-1',\n  {\n    messages: [\n      {\n        content: [\n          {\n            image_url: { url: 'https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png' },\n            type: 'image_url',\n          },\n          {\n            text: 'Describe the main subject and setting in this image in two sentences.',\n            type: 'text',\n          },\n        ],\n        role: 'user',\n      },\n    ],\n    max_tokens: 256,\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"fireworks/ember-1\",\n  \"messages\": [\n    {\n      \"content\": [\n        {\n          \"image_url\": {\n            \"url\": \"https://v3.fal.media/files/koala/NLVPfOI4XL1cWT2PmmqT3_Hope.png\"\n          },\n          \"type\": \"image_url\"\n        },\n        {\n          \"text\": \"Describe the main subject and setting in this image in two sentences.\",\n          \"type\": \"text\"\n        }\n      ],\n      \"role\": \"user\"\n    }\n  ],\n  \"max_tokens\": 256\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": true,
	"zdr_comment": null,
	"external_info": "https://fireworks.ai/models/fireworks/ember-1",
	"terms": "https://fireworks.ai/terms",
	"cover_image_url": null,
	"metadata": {
		"Architecture": "Mixture of Experts",
		"Parameters": "2.78T",
		"Specification": "Calibrated: No",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"chat-completions",
		"responses"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "fireworks",
			"pricing": {
				"input_tokens": 3,
				"input_cached_tokens": 0.3,
				"output_tokens": 15
			}
		}
	],
	"banner": null,
	"created_at": "2026-10-15 23:29:53",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"messages": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"role": {
										"type": "string",
										"enum": [
											"system",
											"developer",
											"user",
											"assistant",
											"tool"
										]
									},
									"content": {
										"anyOf": [
											{
												"type": "string"
											},
											{
												"type": "null"
											},
											{
												"type": "array",
												"items": {}
											}
										]
									}
								},
								"required": [
									"role"
								],
								"additionalProperties": {}
							}
						},
						"temperature": {
							"type": "number",
							"minimum": 0,
							"maximum": 2
						},
						"max_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"max_completion_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"top_p": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"frequency_penalty": {
							"type": "number",
							"minimum": -2,
							"maximum": 2
						},
						"presence_penalty": {
							"type": "number",
							"minimum": -2,
							"maximum": 2
						},
						"stream": {
							"type": "boolean"
						},
						"stream_options": {
							"type": "object",
							"properties": {
								"include_usage": {
									"type": "boolean"
								}
							},
							"additionalProperties": false
						},
						"tools": {
							"type": "array",
							"items": {}
						},
						"tool_choice": {},
						"response_format": {},
						"modalities": {
							"type": "array",
							"items": {
								"type": "string",
								"enum": [
									"text",
									"audio"
								]
							}
						},
						"audio": {
							"type": "object",
							"properties": {
								"voice": {
									"type": "string",
									"enum": [
										"alloy",
										"ash",
										"ballad",
										"coral",
										"echo",
										"sage",
										"shimmer",
										"verse"
									]
								},
								"format": {
									"type": "string",
									"enum": [
										"wav",
										"mp3",
										"flac",
										"opus",
										"pcm16"
									]
								}
							},
							"additionalProperties": false
						},
						"reasoning_effort": {
							"description": "Optional reasoning control; availability and accepted values are model-dependent.",
							"type": [
								"string",
								"null"
							]
						}
					},
					"required": [
						"messages"
					],
					"additionalProperties": {},
					"title": "Chat Completions"
				},
				{
					"type": "object",
					"properties": {
						"input": {
							"anyOf": [
								{
									"type": "string"
								},
								{
									"type": "array",
									"items": {}
								}
							]
						},
						"instructions": {
							"type": "string"
						},
						"temperature": {
							"type": "number",
							"minimum": 0,
							"maximum": 2
						},
						"max_output_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"top_p": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"stream": {
							"type": "boolean"
						},
						"tools": {
							"type": "array",
							"items": {}
						},
						"tool_choice": {},
						"text": {
							"type": "object",
							"properties": {
								"format": {}
							},
							"additionalProperties": {}
						},
						"reasoning": {
							"type": "object",
							"properties": {
								"effort": {
									"description": "Reasoning effort; availability and accepted values are model-dependent.",
									"type": "string",
									"enum": [
										"none",
										"low",
										"medium",
										"high",
										"xhigh",
										"max"
									]
								}
							},
							"additionalProperties": {}
						}
					},
					"required": [
						"input"
					],
					"additionalProperties": {},
					"title": "Responses"
				}
			]
		},
		"output": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"id": {
							"type": "string"
						},
						"object": {
							"type": "string"
						},
						"created": {
							"type": "number"
						},
						"model": {
							"type": "string"
						},
						"choices": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"index": {
										"type": "number"
									},
									"message": {
										"type": "object",
										"properties": {
											"role": {
												"type": "string"
											},
											"content": {
												"type": [
													"string",
													"null"
												]
											},
											"tool_calls": {
												"anyOf": [
													{
														"type": "array",
														"items": {}
													},
													{
														"type": "null"
													}
												]
											},
											"audio": {
												"anyOf": [
													{
														"type": "object",
														"properties": {
															"id": {
																"type": "string"
															},
															"data": {
																"type": "string"
															},
															"expires_at": {
																"type": "number"
															},
															"transcript": {
																"type": "string"
															}
														},
														"additionalProperties": {}
													},
													{
														"type": "null"
													}
												]
											}
										},
										"required": [
											"role"
										],
										"additionalProperties": {}
									},
									"finish_reason": {
										"type": [
											"string",
											"null"
										]
									}
								},
								"required": [
									"index",
									"message",
									"finish_reason"
								],
								"additionalProperties": {}
							}
						},
						"usage": {
							"type": "object",
							"properties": {
								"prompt_tokens": {
									"type": "number"
								},
								"completion_tokens": {
									"type": "number"
								},
								"total_tokens": {
									"type": "number"
								}
							},
							"required": [
								"prompt_tokens",
								"completion_tokens",
								"total_tokens"
							],
							"additionalProperties": {}
						}
					},
					"required": [
						"id",
						"object",
						"created",
						"model",
						"choices"
					],
					"additionalProperties": {},
					"title": "Chat Completions"
				},
				{
					"type": "object",
					"properties": {
						"id": {
							"type": "string"
						},
						"object": {
							"type": "string",
							"const": "response"
						},
						"created_at": {
							"type": "number"
						},
						"model": {
							"type": "string"
						},
						"output": {
							"type": "array",
							"items": {}
						},
						"output_text": {
							"type": "string"
						},
						"status": {
							"type": "string",
							"enum": [
								"in_progress",
								"completed",
								"failed",
								"incomplete"
							]
						},
						"usage": {
							"type": "object",
							"properties": {
								"input_tokens": {
									"type": "number"
								},
								"output_tokens": {
									"type": "number"
								},
								"total_tokens": {
									"type": "number"
								}
							},
							"required": [
								"input_tokens",
								"output_tokens",
								"total_tokens"
							],
							"additionalProperties": {}
						}
					},
					"required": [
						"id",
						"object",
						"created_at",
						"model",
						"output"
					],
					"additionalProperties": {},
					"title": "Responses"
				}
			]
		}
	}
}