{
	"model_id": "google/gemini-3.5-flash-lite",
	"provider_id": "google",
	"name": "Gemini 3.5 Flash-Lite",
	"description": "Gemini 3.5 Flash-Lite is a low-latency, cost-effective multimodal model optimized for high-throughput, low-cost execution for subagent tasks and document parsing.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Fast",
		"Cost-Efficient",
		"Multimodal",
		"Agentic"
	],
	"context_length": 1048576,
	"max_output_tokens": 65536,
	"schema_version": "1.0.0",
	"pricing": {
		"Input tokens (per 1M)": 0.3,
		"Output tokens (per 1M)": 2.5,
		"Cached input tokens (per 1M)": 0.03,
		"Cache creation tokens (per 1M)": 0.03
	},
	"examples": [
		{
			"name": "Simple Question",
			"description": "Basic generateContent request",
			"input": {
				"contents": [
					{
						"parts": [
							{
								"text": "What are the three laws of thermodynamics?"
							}
						],
						"role": "user"
					}
				]
			},
			"output": {
				"text": "The three laws of thermodynamics are fundamental physical principles that describe how energy behaves in the universe\u2014specifically regarding heat, work, entropy, and the limits of energy transfer. \n\nHere is a summary of the three laws, along with a \"zeroth law\" that was established later but is equally fundamental.\n\n---\n\n### The Zeroth Law of Thermodynamics\n*(Establishes temperature as a measurable property and defines thermal equilibrium.)*\n* **The Law:** If two systems are each in thermal equilibrium with a third system, they are also in thermal equilibrium with each other.\n* **Plain English:** If System A is the same temperature as System C, and System B is also the same temperature as System C, then System A and System B are the same temperature. \n* **Why it matters:** This law forms the scientific basis for thermometers.\n\n---\n\n### The First Law of Thermodynamics\n*(The Law of Conservation of Energy)*\n* **The Law:** Energy cannot be created or destroyed in an isolated system; it can only be changed from one form to another.\n* **Plain English:** You can\u2019t get something for nothing. The total amount of energy in the universe remains constant. If a system gains energy, it must come from somewhere else; if it loses energy, it must go somewhere else.\n* **Example:** When you drive a car, chemical energy stored in the gasoline is converted into thermal energy (heat) and kinetic energy (motion). No energy is lost, just transformed.\n\n---\n\n### The Second Law of Thermodynamics\n*(The Law of Entropy)*\n* **The Law:** The total entropy (disorder or randomness) of an isolated system always increases over time. Heat naturally flows from a hotter object to a cooler object, never the reverse spontaneously.\n* **Plain English:** Things naturally fall apart, cool down, or become disorganized unless you put work into maintaining them. You cannot convert heat energy into work with 100% efficiency; some energy is always \"lost\" as unusable waste heat.\n* **Example:** A cup of hot coffee left on a table will eventually cool down to room temperature. The reverse\u2014a room-temperature cup of coffee spontaneously absorbing heat from the room to become boiling hot\u2014never happens naturally. \n* **Why it matters:** This law explains why perpetual motion machines are impossible and gives our universe a \"direction of time\" (often called the \"arrow of time\").\n\n---\n\n### The Third Law of Thermodynamics\n*(The Behavior at Absolute Zero)*\n* **The Law:** As the temperature of a system approaches absolute zero ($0\\text{ Kelvin}$ or $-273.15^\\circ\\text{C}$), the entropy of a pure, perfect crystalline substance approaches a minimum value (typically zero).\n* **Plain English:** You cannot reach absolute zero. As atoms get colder and colder, they slow down and lose thermal motion, but you can never completely stop molecular motion entirely.\n* **Why it matters:** It sets a fundamental lower limit on temperature and helps scientists calculate the absolute entropy of substances."
			},
			"raw_response": {
				"candidates": [
					{
						"content": {
							"role": "model",
							"parts": [
								{
									"text": "The three laws of thermodynamics are fundamental physical principles that describe how energy behaves in the universe\u2014specifically regarding heat, work, entropy, and the limits of energy transfer. \n\nHere is a summary of the three laws, along with a \"zeroth law\" that was established later but is equally fundamental.\n\n---\n\n### The Zeroth Law of Thermodynamics\n*(Establishes temperature as a measurable property and defines thermal equilibrium.)*\n* **The Law:** If two systems are each in thermal equilibrium with a third system, they are also in thermal equilibrium with each other.\n* **Plain English:** If System A is the same temperature as System C, and System B is also the same temperature as System C, then System A and System B are the same temperature. \n* **Why it matters:** This law forms the scientific basis for thermometers.\n\n---\n\n### The First Law of Thermodynamics\n*(The Law of Conservation of Energy)*\n* **The Law:** Energy cannot be created or destroyed in an isolated system; it can only be changed from one form to another.\n* **Plain English:** You can\u2019t get something for nothing. The total amount of energy in the universe remains constant. If a system gains energy, it must come from somewhere else; if it loses energy, it must go somewhere else.\n* **Example:** When you drive a car, chemical energy stored in the gasoline is converted into thermal energy (heat) and kinetic energy (motion). No energy is lost, just transformed.\n\n---\n\n### The Second Law of Thermodynamics\n*(The Law of Entropy)*\n* **The Law:** The total entropy (disorder or randomness) of an isolated system always increases over time. Heat naturally flows from a hotter object to a cooler object, never the reverse spontaneously.\n* **Plain English:** Things naturally fall apart, cool down, or become disorganized unless you put work into maintaining them. You cannot convert heat energy into work with 100% efficiency; some energy is always \"lost\" as unusable waste heat.\n* **Example:** A cup of hot coffee left on a table will eventually cool down to room temperature. The reverse\u2014a room-temperature cup of coffee spontaneously absorbing heat from the room to become boiling hot\u2014never happens naturally. \n* **Why it matters:** This law explains why perpetual motion machines are impossible and gives our universe a \"direction of time\" (often called the \"arrow of time\").\n\n---\n\n### The Third Law of Thermodynamics\n*(The Behavior at Absolute Zero)*\n* **The Law:** As the temperature of a system approaches absolute zero ($0\\text{ Kelvin}$ or $-273.15^\\circ\\text{C}$), the entropy of a pure, perfect crystalline substance approaches a minimum value (typically zero).\n* **Plain English:** You cannot reach absolute zero. As atoms get colder and colder, they slow down and lose thermal motion, but you can never completely stop molecular motion entirely.\n* **Why it matters:** It sets a fundamental lower limit on temperature and helps scientists calculate the absolute entropy of substances.",
									"thoughtSignature": "AY89a1/ol32QPrMVbKQjdSf9juhARUkac2Z+KPcq5oo84TKrgbEj7WuE+4yuNhidBd0="
								}
							]
						},
						"finishReason": "STOP"
					}
				],
				"usageMetadata": {
					"promptTokenCount": 8,
					"candidatesTokenCount": 634,
					"totalTokenCount": 642,
					"trafficType": "ON_DEMAND",
					"promptTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 8
						}
					],
					"candidatesTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 634
						}
					]
				},
				"modelVersion": "gemini-3.5-flash-lite",
				"createTime": "2026-07-21T16:21:55.338444Z",
				"responseId": "o5xfaozUFK2o8sYPiYHy-Ag"
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'google/gemini-3.5-flash-lite',\n  { contents: [{ parts: [{ text: 'What are the three laws of thermodynamics?' }], role: 'user' }] },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"google/gemini-3.5-flash-lite\",\n  \"input\": {\n    \"contents\": [\n      {\n        \"parts\": [\n          {\n            \"text\": \"What are the three laws of thermodynamics?\"\n          }\n        ],\n        \"role\": \"user\"\n      }\n    ]\n  }\n}'"
				}
			]
		},
		{
			"name": "Data Extraction",
			"description": "Structured data extraction from unstructured text, a common subagent task",
			"input": {
				"contents": [
					{
						"parts": [
							{
								"text": "Extract the name, email, and phone number from this text as JSON: 'Hi, I'm Jordan Blake, reach me at jordan.blake@example.com or 555-2938.'"
							}
						],
						"role": "user"
					}
				],
				"generationConfig": {
					"temperature": 0
				},
				"systemInstruction": {
					"parts": [
						{
							"text": "You are a data extraction assistant. Respond with only valid JSON, no extra commentary."
						}
					]
				}
			},
			"output": {
				"text": "{\n  \"name\": \"Jordan Blake\",\n  \"email\": \"jordan.blake@example.com\",\n  \"phone\": \"555-2938\"\n}"
			},
			"raw_response": {
				"candidates": [
					{
						"content": {
							"role": "model",
							"parts": [
								{
									"text": "{\n  \"name\": \"Jordan Blake\",\n  \"email\": \"jordan.blake@example.com\",\n  \"phone\": \"555-2938\"\n}",
									"thoughtSignature": "AY89a1+AejOv/9okEuBeoArPDSAKd5ZcT4tlNk6itaskjb7ezx7K9fEu5NLFUx4iUig="
								}
							]
						},
						"finishReason": "STOP"
					}
				],
				"usageMetadata": {
					"promptTokenCount": 63,
					"candidatesTokenCount": 43,
					"totalTokenCount": 106,
					"trafficType": "ON_DEMAND",
					"promptTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 63
						}
					],
					"candidatesTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 43
						}
					]
				},
				"modelVersion": "gemini-3.5-flash-lite",
				"createTime": "2026-07-21T16:21:57.867550Z",
				"responseId": "pZxfat75NIvG8sYP3dfakAo"
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'google/gemini-3.5-flash-lite',\n  {\n    contents: [\n      {\n        parts: [\n          {\n            text: \"Extract the name, email, and phone number from this text as JSON: 'Hi, I'm Jordan Blake, reach me at jordan.blake@example.com or 555-2938.'\",\n          },\n        ],\n        role: 'user',\n      },\n    ],\n    generationConfig: { temperature: 0 },\n    systemInstruction: {\n      parts: [\n        {\n          text: 'You are a data extraction assistant. Respond with only valid JSON, no extra commentary.',\n        },\n      ],\n    },\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"google/gemini-3.5-flash-lite\",\n  \"input\": {\n    \"contents\": [\n      {\n        \"parts\": [\n          {\n            \"text\": \"Extract the name, email, and phone number from this text as JSON: '\\''Hi, I'\\''m Jordan Blake, reach me at jordan.blake@example.com or 555-2938.'\\''\"\n          }\n        ],\n        \"role\": \"user\"\n      }\n    ],\n    \"generationConfig\": {\n      \"temperature\": 0\n    },\n    \"systemInstruction\": {\n      \"parts\": [\n        {\n          \"text\": \"You are a data extraction assistant. Respond with only valid JSON, no extra commentary.\"\n        }\n      ]\n    }\n  }\n}'"
				}
			]
		},
		{
			"name": "Multi-turn Conversation",
			"description": "Continuing a short conversation with low-latency, high-throughput responses",
			"input": {
				"contents": [
					{
						"parts": [
							{
								"text": "Summarize this in one sentence: The meeting covered Q3 budget overruns, a proposed hiring freeze, and a plan to renegotiate vendor contracts."
							}
						],
						"role": "user"
					},
					{
						"parts": [
							{
								"text": "The meeting addressed Q3 budget overruns by proposing a hiring freeze and vendor contract renegotiations."
							}
						],
						"role": "model"
					},
					{
						"parts": [
							{
								"text": "Now make it even shorter, under 10 words."
							}
						],
						"role": "user"
					}
				],
				"generationConfig": {
					"maxOutputTokens": 512
				}
			},
			"output": {
				"text": "Addressing Q3 budget overruns, hiring freezes, and vendor contracts."
			},
			"raw_response": {
				"candidates": [
					{
						"content": {
							"role": "model",
							"parts": [
								{
									"text": "Addressing Q3 budget overruns, hiring freezes, and vendor contracts.",
									"thoughtSignature": "AY89a1/dUv1ajorDdpZkOzaeL0fb5CjoZL4SoKtpQeX8AK5jF5vNa/v4F6r7OqdabWs="
								}
							]
						},
						"finishReason": "STOP"
					}
				],
				"usageMetadata": {
					"promptTokenCount": 61,
					"candidatesTokenCount": 14,
					"totalTokenCount": 75,
					"trafficType": "ON_DEMAND",
					"promptTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 61
						}
					],
					"candidatesTokensDetails": [
						{
							"modality": "TEXT",
							"tokenCount": 14
						}
					]
				},
				"modelVersion": "gemini-3.5-flash-lite",
				"createTime": "2026-07-21T16:21:58.695703Z",
				"responseId": "ppxfape7KqSn8sYPpMq_gQ8"
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'google/gemini-3.5-flash-lite',\n  {\n    contents: [\n      {\n        parts: [\n          {\n            text: 'Summarize this in one sentence: The meeting covered Q3 budget overruns, a proposed hiring freeze, and a plan to renegotiate vendor contracts.',\n          },\n        ],\n        role: 'user',\n      },\n      {\n        parts: [\n          {\n            text: 'The meeting addressed Q3 budget overruns by proposing a hiring freeze and vendor contract renegotiations.',\n          },\n        ],\n        role: 'model',\n      },\n      { parts: [{ text: 'Now make it even shorter, under 10 words.' }], role: 'user' },\n    ],\n    generationConfig: { maxOutputTokens: 512 },\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/run \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"google/gemini-3.5-flash-lite\",\n  \"input\": {\n    \"contents\": [\n      {\n        \"parts\": [\n          {\n            \"text\": \"Summarize this in one sentence: The meeting covered Q3 budget overruns, a proposed hiring freeze, and a plan to renegotiate vendor contracts.\"\n          }\n        ],\n        \"role\": \"user\"\n      },\n      {\n        \"parts\": [\n          {\n            \"text\": \"The meeting addressed Q3 budget overruns by proposing a hiring freeze and vendor contract renegotiations.\"\n          }\n        ],\n        \"role\": \"model\"\n      },\n      {\n        \"parts\": [\n          {\n            \"text\": \"Now make it even shorter, under 10 words.\"\n          }\n        ],\n        \"role\": \"user\"\n      }\n    ],\n    \"generationConfig\": {\n      \"maxOutputTokens\": 512\n    }\n  }\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": false,
	"zdr_comment": null,
	"external_info": "https://deepmind.google/technologies/gemini/",
	"terms": "https://ai.google.dev/gemini-api/terms",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/google/gemini-3.5-flash-lite.png",
	"metadata": {
		"Architecture": "Transformer (multimodal)"
	},
	"request_formats": [
		"chat-completions"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "google-vertex-ai",
			"pricing": {
				"input_tokens": 0.3,
				"output_tokens": 2.5,
				"input_cached_tokens": 0.03,
				"input_cache_creation_tokens": 0.03
			}
		}
	],
	"banner": null,
	"created_at": "2026-07-21 21:43:11",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"contents": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"role": {
										"type": "string",
										"enum": [
											"user",
											"model"
										]
									},
									"parts": {
										"type": "array",
										"items": {
											"type": "object",
											"properties": {
												"text": {
													"type": "string"
												}
											},
											"additionalProperties": {}
										}
									}
								},
								"required": [
									"parts"
								],
								"additionalProperties": {}
							}
						},
						"systemInstruction": {
							"type": "object",
							"properties": {
								"parts": {
									"type": "array",
									"items": {
										"type": "object",
										"properties": {
											"text": {
												"type": "string"
											}
										},
										"additionalProperties": {}
									}
								}
							},
							"required": [
								"parts"
							],
							"additionalProperties": {}
						},
						"generationConfig": {
							"type": "object",
							"properties": {
								"temperature": {
									"type": "number"
								},
								"topP": {
									"type": "number"
								},
								"topK": {
									"type": "number"
								},
								"maxOutputTokens": {
									"type": "number"
								},
								"candidateCount": {
									"type": "number"
								},
								"stopSequences": {
									"type": "array",
									"items": {
										"type": "string"
									}
								},
								"responseMimeType": {
									"type": "string"
								}
							},
							"additionalProperties": {}
						},
						"safetySettings": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"category": {
										"type": "string"
									},
									"threshold": {
										"type": "string"
									}
								},
								"required": [
									"category",
									"threshold"
								],
								"additionalProperties": {}
							}
						},
						"tools": {
							"type": "array",
							"items": {}
						},
						"toolConfig": {}
					},
					"required": [
						"contents"
					],
					"additionalProperties": {},
					"title": "Generate Content"
				},
				{
					"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"
				}
			]
		},
		"output": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"candidates": {
							"type": "array",
							"items": {}
						},
						"usageMetadata": {
							"type": "object",
							"properties": {
								"promptTokenCount": {
									"type": "number"
								},
								"candidatesTokenCount": {
									"type": "number"
								},
								"totalTokenCount": {
									"type": "number"
								}
							},
							"additionalProperties": {}
						},
						"modelVersion": {
							"type": "string"
						}
					},
					"additionalProperties": {},
					"title": "Generate Content"
				},
				{
					"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"
				}
			]
		}
	}
}