{
	"model_id": "openai/gpt-6-astra",
	"provider_id": "openai",
	"name": "GPT-6 Astra",
	"description": "GPT-6 Astra is OpenAI's most capable model, built for complex reasoning, coding, computer use, research, and document creation.",
	"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)": 10,
		"Short-context cached input (per 1M)": 1,
		"Short-context cache write (per 1M)": 12,
		"Short-context output (per 1M)": 50,
		"Long-context input (per 1M)": 20,
		"Long-context cached input (per 1M)": 2,
		"Long-context cache write (per 1M)": 25,
		"Long-context output (per 1M)": 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. For a 30-day month:\n\n- Total time: \\(30 \\times 24 \\times 60 = 43{,}200\\) minutes\n- Error budget: \\(43{,}200 \\times (1 - 0.999) = 43.2\\) minutes\n- Remaining budget: \\(43.2 - 31 = 12.2\\) minutes\n\nAssuming 31 minutes is the total downtime this month, it is **within the error budget**."
			},
			"raw_response": {
				"id": "resp_0f4dd4f38f19eb60016a99d9b6aaec87d1ab6bb0c344527fbc",
				"object": "response",
				"created_at": 1788467638,
				"model": "gpt-6-astra",
				"output": [
					{
						"id": "rs_0f4dd4f38f19eb60016a99d9b77c6087d1ab41b79ccdf5a833",
						"type": "reasoning",
						"content": [],
						"encrypted_content": "gAAAAABqmdm5bNo3TE240J65AqELJf45m_Forsch1ik0e0iiz5B-XZsvljWjY5PfmKXyel-6WvdoKmKulsRo3PX0fCqdNQFUaSYufMITZh61KSdsWBeeKRAwczgj8ihQBEbSF95MmTwkoQzsHX5SBitcf0n7CrMhXt8-LcE2tXqY309dnpgzAtjeI8H318LR1JyAWKsbver3s30gE1TRh0GC3YisTLrfACSclHB8_cOPA5QvEwKJNljm8R7eVDJx7LTFoB2Av93eaSD7l4fbAJzR_afL8K_Akj5NsjYaZVrsbPPxTYlYpqRhE0c-3C2U0oJ31-4UVa6_nT94QYtnDJ9YNjEdRC8sMkq6DwLhkbIIJGVNJGqHmWP3vQu3JCq9VDUtC3ss3FCkgWwhIV5tAFTFOtppnHenz1Xi2UYwaBNwaHWYJdrTBidNcpEQwPcIdSRAfOHv2r-ueFywhAZmj8Rx_GcJO_5_RWjvglhuNRBTbC92icwLx6wt4LWYBpLW-0itkHNtdy2cqsiKYSxWyMRzaEwyhW3wQo6jC9w9MRUG35wT3drTsuvnMDV5yhtzCtxq57eTRpIpCM9343ITl5DUwS-d7vouI7QH2MAIkZknxTO-_vVPYVQrQ4Th0g6Cb8CrGd-nHQ39xYKnPG7oUmvRobLSaGpKmQREzp-uoQeVK8dypZCl3Xd1uHSUO7w-HKsob-t5whmpE-ziHFaqciWh9YcssC0YE1ztbq0f9tGRy386ZzkkihD23sGR0khZukCdiGSw3Njakpe4AMWujU-t2BtomDJa6pdtLEuvG7p3MbIbHRoXkyK-9h74NgBY2jO7fk0BgItjpmqhcPHelCtMxIhP_OroanM0rCUjfQdqcSBVxwOd_hJ5wcNHmWdyf3gVvKEO83M4cj-sVljJ1afzFfhFsAQH5Zw-JTeBI1udknm3oy5lDwEzRoZpTcQs2Ix8lyUBtZ4MypqRLTnKLXzyij8G8XdgTIqwUkOHhMrm8Zc0_ndcrwPoVjwTq0NugRGJMDAxPKl-aqg6XvEfCYCUF2WYIu8jGo3KK6An8GJ5HFLyidgUslKGJtN2TJmKBOPwc0fXoiW4qyUQdVi2Hz23KBMOQE77jIF0cccZAWDToq67zPLVw9I4j-VKRpti-tOfcg9tz0wr4zJRi49uOqTw038Xn03VXzTolhb3GwwQkMZxWLjam3buEX6SLuS1A7XXZn3aKeLu6KhUin6_aR3jP0s2_Y50Mjv3x0EouaIKQJEINqYRgi9K2SKAxzRSKjGksdNGNcNRGs6cydkHSJF-f60p9HRBbBsN7duP8qm0K2URSJ1DX30=",
						"summary": []
					},
					{
						"id": "msg_0f4dd4f38f19eb60016a99d9b7d7f087d191f17156c41c2f32",
						"type": "message",
						"status": "completed",
						"content": [
							{
								"type": "output_text",
								"annotations": [],
								"logprobs": [],
								"text": "No. For a 30-day month:\n\n- Total time: \\(30 \\times 24 \\times 60 = 43{,}200\\) minutes\n- Error budget: \\(43{,}200 \\times (1 - 0.999) = 43.2\\) minutes\n- Remaining budget: \\(43.2 - 31 = 12.2\\) minutes\n\nAssuming 31 minutes is the total downtime this month, it is **within the error budget**."
							}
						],
						"phase": "final_answer",
						"role": "assistant"
					}
				],
				"status": "completed",
				"usage": {
					"input_tokens": 44,
					"output_tokens": 151,
					"total_tokens": 195,
					"input_tokens_details": {
						"cache_write_tokens": 0,
						"cached_tokens": 0
					},
					"output_tokens_details": {
						"reasoning_tokens": 41
					}
				},
				"access_programs": {
					"cyber": "standard"
				},
				"background": false,
				"billing": {
					"payer": "developer"
				},
				"completed_at": 1788467641,
				"error": null,
				"frequency_penalty": 0,
				"incomplete_details": null,
				"instructions": null,
				"max_output_tokens": 512,
				"max_tool_calls": null,
				"moderation": null,
				"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": false,
				"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",
				"user": null,
				"metadata": {},
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-6-astra',\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-astra\",\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. **Validate compatibility before rollout.** Run contract and integration tests against real client behaviors. Keep breaking changes behind a new API version, and verify authentication, error formats, and data schemas.\n\n2. **Roll out gradually with monitoring.** Start with internal traffic or a small canary group. Track error rates, latency, and critical business metrics; pause expansion if predefined thresholds are exceeded.\n\n3. **Prepare and test rollback.** Keep the old API available and use a feature flag or traffic switch to revert quickly. Ensure database changes remain backward-compatible, and rehearse the rollback procedure."
			},
			"raw_response": {
				"id": "chatcmpl-EK8QDqH1XsfW6m8nEHXxUkrKGcWG5",
				"object": "chat.completion",
				"created": 1788467641,
				"model": "gpt-6-astra",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "1. **Validate compatibility before rollout.** Run contract and integration tests against real client behaviors. Keep breaking changes behind a new API version, and verify authentication, error formats, and data schemas.\n\n2. **Roll out gradually with monitoring.** Start with internal traffic or a small canary group. Track error rates, latency, and critical business metrics; pause expansion if predefined thresholds are exceeded.\n\n3. **Prepare and test rollback.** Keep the old API available and use a feature flag or traffic switch to revert quickly. Ensure database changes remain backward-compatible, and rehearse the rollback procedure.",
							"refusal": null,
							"annotations": []
						},
						"finish_reason": "stop"
					}
				],
				"usage": {
					"prompt_tokens": 16,
					"completion_tokens": 151,
					"total_tokens": 167,
					"prompt_tokens_details": {
						"cached_tokens": 0,
						"cache_write_tokens": 0,
						"audio_tokens": 0
					},
					"completion_tokens_details": {
						"reasoning_tokens": 23,
						"audio_tokens": 0,
						"accepted_prediction_tokens": 0,
						"rejected_prediction_tokens": 0
					}
				},
				"service_tier": "default",
				"system_fingerprint": null,
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-6-astra',\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 $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-6-astra\",\n  \"messages\": [\n    {\n      \"role\": \"user\",\n      \"content\": \"List three practical safeguards for a production API migration.\"\n    }\n  ],\n  \"max_completion_tokens\": 256\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": false,
	"zdr_comment": null,
	"external_info": "https://developers.openai.com/api/docs/models/gpt-6-astra",
	"terms": "https://openai.com/policies/",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/openai/gpt-6-astra.png",
	"metadata": {
		"API": "Responses, Chat Completions",
		"Architecture": "Transformer",
		"Input modalities": "Text, image",
		"Knowledge cutoff": "April 30, 2026",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"responses",
		"chat-completions"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "openai",
			"pricing": {
				"long_context_threshold_tokens": 272000,
				"short_context_input_tokens": 10,
				"short_context_input_cached_tokens": 1,
				"short_context_input_cache_creation_tokens": 12,
				"short_context_output_tokens": 50,
				"long_context_input_tokens": 20,
				"long_context_input_cached_tokens": 2,
				"long_context_input_cache_creation_tokens": 25,
				"long_context_output_tokens": 75
			}
		}
	],
	"banner": null,
	"created_at": "2026-09-10 20:01:11",
	"schema": {
		"input": {
			"$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"
				}
			]
		}
	}
}