{
	"model_id": "openai/gpt-6-luna",
	"provider_id": "openai",
	"name": "GPT-6 Luna",
	"description": "GPT-6 Luna is OpenAI's most efficient GPT-6 model, built for focused, high-volume tasks.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Coding",
		"Reasoning",
		"Multimodal",
		"Computer Use"
	],
	"context_length": 1050000,
	"max_output_tokens": 128000,
	"schema_version": "1.0.0",
	"pricing": {
		"Short-context input (per 1M)": 0.1,
		"Short-context cached input (per 1M)": 0.01,
		"Short-context cache write (per 1M)": 0.125,
		"Short-context output (per 1M)": 0.5,
		"Long-context input (per 1M)": 0.2,
		"Long-context cached input (per 1M)": 0.02,
		"Long-context cache write (per 1M)": 0.25,
		"Long-context output (per 1M)": 0.75
	},
	"examples": [
		{
			"name": "Operational Reasoning",
			"description": "Use reasoning effort for a complex operational decision",
			"input": {
				"input": "A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.",
				"max_output_tokens": 512,
				"reasoning": {
					"effort": "high"
				}
			},
			"output": {
				"text": "No. A 30-day month has 43,200 minutes, so a 99.9% availability target allows **43.2 minutes** of downtime.\n\n**31 minutes < 43.2 minutes** \u2014 the service is within its error budget, with **12.2 minutes** remaining."
			},
			"raw_response": {
				"id": "resp_0834f111f7f68c6e006ab2cf91391887d1b9ed77f9003d8001",
				"object": "response",
				"created_at": 1790103441,
				"status": "completed",
				"access_programs": {
					"cyber": "daybreak_blue"
				},
				"background": false,
				"billing": {
					"payer": "developer"
				},
				"completed_at": 1790103442,
				"error": null,
				"frequency_penalty": 0,
				"incomplete_details": null,
				"instructions": null,
				"max_output_tokens": 512,
				"max_tool_calls": null,
				"model": "gpt-6-luna",
				"moderation": null,
				"output": [
					{
						"id": "rs_0834f111f7f68c6e006ab2cf91a3dc87d194f310e59b05b545",
						"type": "reasoning",
						"content": [],
						"encrypted_content": "gAAAAABqss-TspJODH9IZcFL8SzWTp9z3qvEH482IoLj1OmrPlxluS5KGNZRrU1yGjrek9eQ7K6QzWND5RagCGsxWPN3ZK7lFfa8HWjztExHY-locYCrFDRWniTGdOmjF0dAUcm_5L5laGAhFa5qiRByPmSSapXvxyhbYx1Qs-_SjUxRF7rvxFIisGHm4XeHSuTMLUaVGk3okdDMWwxJDZrPjOk66JLwvZ_D8n345Iw6WG7L6iS30KsEhOuKVxkdkl0H_T_2fDaGxaJfOIr0WCSFjM62vvZNw6Gi9-zf8tzupmjORta_cLu9YDNSklYSNio-rUS-2RMlfJA1RvFQPKIx8347HtpYUYqHBNFRlNA-Az99fWBdGffyNtYL2vuItF4X0UJ1tDN_KtuFil7qLPJMGHTdXI7_-2YzNw9u-rmeeR9tnp3zbCertjlHMsTAcT0fbuLh_ob-GCDSg0pR8Ac5fsJv75nRqIMVixC_e7sL_5sGDAsJDi-24_nUAtU84zCPinglfdiYNvwBoEOgZQ-bYT8K3DZ-Z6dJaupCz_ncOtsFIvvEehM2JzcVdKkhUv6ilUst-J-RoMEzb3HzpKZE2Y6Ry3R-VDvLOda2HL-DrmbK4zW_o8X5-Yp5I-XXIomnt3yxMRYyH5WI66HkMQAFQtiP7ukmQEpI-_ItySu48cro2tpY3tBnRBJAvAU45yGDm9EhG6F_jThXyEav90yADc4GfJw82gZDzrnmQ0Oki8U0jEfPUipKztlsstiLw06Da5IF6cBxhOMiNq2TbB4j5o3bG48HSxAzwgu8xHHSR00_IWMEFO49l6lWpO9W0FWN9OdeaMKkRFQ8cGNIZCqDgYvkw3x0NlbOtjm_TqIQMRVM7vfsdujWSwb1iidy6BEYde7TVAmEg_D0jk7tq9JPIQIngvbxeWXpE2zmvEGrgDqD9y8d-dF2svsxMegzFpZjVowcWRPhJXcySYsMnPrIYqM8bCmXPhSXoBgmTqvWO8BCBJUPvRLPAkJSUU4JTI3GAsN4XAKVm-NaQghf4t5ofeZkIRx9sc1jkz1KfEZ_hH02_89s_A8u2GaiCREYGisKBd9ZuvtDu2WxzIsqud1YKqn9epw-ZC5zCkS0MfZW5rZGmBmu2K6Zia2swsBgs3mypZPh4ihYkkeuAxs_eX1nFtCW-tdYGFcCKVRBf3tvbA2XRgcfgNr9LH6kmbWSBM53kjxLI5L6hR-CDBJ9lWuWoal1R3GzWL9-uIbU4i4ailowQwcgQ2o8Lnnq_jZTs-yurDDyThIVKeo_ZkrmniqyReoVlwYZYRWKaKsSV6i95J-GosOjqM4BoVZGB0tvebNbEOz4tGzKPmoDFI6ckl4Jede1l3dYWAobbPgGab7pp4QgmerdWhiIyK2-kRrDsocrazxjIv0hEqOZha1jwN_cWqmfPTgfmv7jIHZ9Be0S8xrQdd11Qwwyik1OPyJlYte3Ru1IO6FDcCRNbAE3yFBE9pSU8kOKIg==",
						"summary": []
					},
					{
						"id": "msg_0834f111f7f68c6e006ab2cf925fd487d1b67ccd2ee1e2dfe5",
						"type": "message",
						"status": "completed",
						"content": [
							{
								"type": "output_text",
								"annotations": [],
								"logprobs": [],
								"text": "No. A 30-day month has 43,200 minutes, so a 99.9% availability target allows **43.2 minutes** of downtime.\n\n**31 minutes < 43.2 minutes** \u2014 the service is within its error budget, with **12.2 minutes** remaining."
							}
						],
						"phase": "final_answer",
						"role": "assistant"
					}
				],
				"parallel_tool_calls": true,
				"presence_penalty": 0,
				"previous_response_id": null,
				"prompt_cache_key": null,
				"prompt_cache_retention": "24h",
				"reasoning": {
					"context": "all_turns",
					"effort": "high",
					"mode": "standard",
					"summary": null
				},
				"safety_identifier": null,
				"service_tier": "default",
				"store": true,
				"temperature": 1,
				"text": {
					"format": {
						"type": "text"
					},
					"verbosity": "medium"
				},
				"tool_choice": "auto",
				"tool_usage": {
					"image_gen": {
						"input_tokens": 0,
						"input_tokens_details": {
							"image_tokens": 0,
							"text_tokens": 0
						},
						"output_tokens": 0,
						"output_tokens_details": {
							"image_tokens": 0,
							"text_tokens": 0
						},
						"total_tokens": 0
					},
					"web_search": {
						"num_requests": 0
					}
				},
				"tools": [],
				"top_logprobs": 0,
				"top_p": 0.98,
				"truncation": "disabled",
				"usage": {
					"input_tokens": 44,
					"input_tokens_details": {
						"cache_write_tokens": 0,
						"cached_tokens": 0
					},
					"output_tokens": 151,
					"output_tokens_details": {
						"reasoning_tokens": 84
					},
					"total_tokens": 195
				},
				"user": null,
				"metadata": {}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-6-luna',\n  {\n    input:\n      'A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.',\n    max_output_tokens: 512,\n    reasoning: { effort: 'high' },\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-6-luna\",\n  \"input\": \"A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.\",\n  \"max_output_tokens\": 512,\n  \"reasoning\": {\n    \"effort\": \"high\"\n  }\n}'"
				}
			]
		},
		{
			"name": "Migration Safeguards",
			"description": "Generate a concise answer through Chat Completions",
			"input": {
				"messages": [
					{
						"role": "user",
						"content": "List three practical safeguards for a production API migration."
					}
				],
				"max_completion_tokens": 256
			},
			"output": {
				"text": "1. **Preserve compatibility:** Version the API or support old and new contracts during the transition; document breaking changes and give clients a migration window.\n2. **Roll out gradually:** Test in staging, then use a canary or percentage-based rollout with monitoring for errors, latency, and client failures.\n3. **Plan validation and rollback:** Verify key workflows and data before and after cutover, keep backups or a reversible migration path, and define clear rollback triggers."
			},
			"raw_response": {
				"id": "chatcmpl-EQzy7Or5tZ9ZdoXfjhVAYfwDEj28S",
				"object": "chat.completion",
				"created": 1790103443,
				"model": "gpt-6-luna",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "1. **Preserve compatibility:** Version the API or support old and new contracts during the transition; document breaking changes and give clients a migration window.\n2. **Roll out gradually:** Test in staging, then use a canary or percentage-based rollout with monitoring for errors, latency, and client failures.\n3. **Plan validation and rollback:** Verify key workflows and data before and after cutover, keep backups or a reversible migration path, and define clear rollback triggers.",
							"refusal": null,
							"annotations": []
						},
						"finish_reason": "stop"
					}
				],
				"usage": {
					"prompt_tokens": 16,
					"completion_tokens": 128,
					"total_tokens": 144,
					"prompt_tokens_details": {
						"cached_tokens": 0,
						"cache_write_tokens": 0,
						"audio_tokens": 0
					},
					"completion_tokens_details": {
						"reasoning_tokens": 25,
						"audio_tokens": 0,
						"accepted_prediction_tokens": 0,
						"rejected_prediction_tokens": 0
					}
				},
				"service_tier": "default",
				"system_fingerprint": null
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-6-luna',\n  {\n    messages: [\n      { role: 'user', content: 'List three practical safeguards for a production API migration.' },\n    ],\n    max_completion_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 $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-6-luna\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"List three practical safeguards for a production API migration.\"\n    }\n  ],\n  \"max_completion_tokens\": 256\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": false,
	"zdr_comment": null,
	"external_info": "https://developers.openai.com/api/docs/models/gpt-6-luna",
	"terms": "https://openai.com/policies/",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/openai/gpt-6-luna.png",
	"metadata": {
		"API": "Responses, Chat Completions",
		"Architecture": "Transformer",
		"Input modalities": "Text, image",
		"Knowledge cutoff": "May 18, 2026",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"responses",
		"chat-completions"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "openai",
			"pricing": {
				"long_context_threshold_tokens": 272000,
				"short_context_input_tokens": 0.1,
				"short_context_input_cached_tokens": 0.01,
				"short_context_input_cache_creation_tokens": 0.125,
				"short_context_output_tokens": 0.5,
				"long_context_input_tokens": 0.2,
				"long_context_input_cached_tokens": 0.02,
				"long_context_input_cache_creation_tokens": 0.25,
				"long_context_output_tokens": 0.75
			}
		}
	],
	"banner": null,
	"created_at": "2026-09-23 21:02:44",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"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"
				},
				{
					"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": {
						"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"
				},
				{
					"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"
				}
			]
		}
	}
}