{
	"model_id": "openai/gpt-5.6-sol",
	"provider_id": "openai",
	"name": "GPT-5.6 Sol",
	"description": "GPT-5.6 Sol is OpenAI's frontier GPT-5.6 model for complex professional work, using the Responses API for reasoning and stateful context management.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Coding",
		"Reasoning",
		"Multimodal",
		"Responses API"
	],
	"context_length": 1050000,
	"max_output_tokens": 128000,
	"schema_version": "1.0.0",
	"pricing": {
		"Short-context input (per 1M)": 4,
		"Short-context cached input (per 1M)": 0.4,
		"Short-context cache write (per 1M)": 5,
		"Short-context output (per 1M)": 20,
		"Long-context input (per 1M)": 8,
		"Long-context cached input (per 1M)": 0.8,
		"Long-context cache write (per 1M)": 10,
		"Long-context output (per 1M)": 30
	},
	"examples": [
		{
			"name": "Launch Checklist",
			"description": "Basic Responses API request for complex professional planning",
			"input": {
				"input": "Create a concise launch checklist for migrating a production API to a new region.",
				"instructions": "Use five bullets and focus on risk reduction.",
				"max_output_tokens": 512
			},
			"output": {
				"text": "- **Validate readiness:** Confirm capacity, quotas, security controls, certificates, secrets, dependencies, and compliance requirements in the new region.\n- **Protect data:** Take verified backups; validate replication consistency, encryption, retention, and restore procedures before cutover.\n- **Test end to end:** Run load, latency, failover, integration, and smoke tests using production-like traffic and data.\n- **Control cutover:** Lower DNS TTLs, deploy gradually with canary traffic, freeze risky changes, and monitor errors, latency, saturation, and data integrity.\n- **Prepare rollback:** Define go/no-go thresholds, owners, communication channels, and a rehearsed rollback plan; retain the old region until stability is confirmed."
			},
			"raw_response": {
				"id": "resp_0f038c9de2c94eb6016a4fe97e94f081909f0edfecbfb2abd9",
				"object": "response",
				"created_at": 1783622014,
				"status": "completed",
				"background": false,
				"billing": {
					"payer": "developer"
				},
				"completed_at": 1783622017,
				"error": null,
				"frequency_penalty": 0,
				"incomplete_details": null,
				"instructions": "Use five bullets and focus on risk reduction.",
				"max_output_tokens": 512,
				"max_tool_calls": null,
				"model": "gpt-5.6-sol",
				"moderation": null,
				"output": [
					{
						"id": "rs_0f038c9de2c94eb6016a4fe97f2bac81909bf1c27c448cf46b",
						"type": "reasoning",
						"content": [],
						"summary": []
					},
					{
						"id": "msg_0f038c9de2c94eb6016a4fe97fa0688190a1b4958a6a0aa218",
						"type": "message",
						"status": "completed",
						"content": [
							{
								"type": "output_text",
								"annotations": [],
								"logprobs": [],
								"text": "- **Validate readiness:** Confirm capacity, quotas, security controls, certificates, secrets, dependencies, and compliance requirements in the new region.\n- **Protect data:** Take verified backups; validate replication consistency, encryption, retention, and restore procedures before cutover.\n- **Test end to end:** Run load, latency, failover, integration, and smoke tests using production-like traffic and data.\n- **Control cutover:** Lower DNS TTLs, deploy gradually with canary traffic, freeze risky changes, and monitor errors, latency, saturation, and data integrity.\n- **Prepare rollback:** Define go/no-go thresholds, owners, communication channels, and a rehearsed rollback plan; retain the old region until stability is confirmed."
							}
						],
						"phase": "final_answer",
						"role": "assistant"
					}
				],
				"parallel_tool_calls": true,
				"presence_penalty": 0,
				"previous_response_id": null,
				"prompt_cache_key": null,
				"prompt_cache_retention": "in_memory",
				"reasoning": {
					"context": "all_turns",
					"effort": "medium",
					"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",
				"usage": {
					"input_tokens": 34,
					"input_tokens_details": {
						"cache_write_tokens": 0,
						"cached_tokens": 0
					},
					"output_tokens": 182,
					"output_tokens_details": {
						"reasoning_tokens": 32
					},
					"total_tokens": 216
				},
				"user": null,
				"metadata": {}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-5.6-sol',\n  {\n    input: 'Create a concise launch checklist for migrating a production API to a new region.',\n    instructions: 'Use five bullets and focus on risk reduction.',\n    max_output_tokens: 512,\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-5.6-sol\",\n  \"input\": \"Create a concise launch checklist for migrating a production API to a new region.\",\n  \"instructions\": \"Use five bullets and focus on risk reduction.\",\n  \"max_output_tokens\": 512\n}'"
				}
			]
		},
		{
			"name": "Operational Reasoning",
			"description": "Using reasoning effort for a multi-step 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": "medium"
				}
			},
			"output": {
				"text": "- Total minutes in 30 days: \\(30 \\times 24 \\times 60 = 43{,}200\\)\n- Error budget at 99.9% availability: \\(43{,}200 \\times 0.001 = 43.2\\) minutes\n- Downtime used: 31 minutes\n\n**No**, it has not exceeded the monthly error budget. It has **12.2 minutes remaining**."
			},
			"raw_response": {
				"id": "resp_0fcb12a6aa68f25a016a4fe98205b881978b6ab83321e02e3b",
				"object": "response",
				"created_at": 1783622018,
				"status": "completed",
				"background": false,
				"billing": {
					"payer": "developer"
				},
				"completed_at": 1783622020,
				"error": null,
				"frequency_penalty": 0,
				"incomplete_details": null,
				"instructions": null,
				"max_output_tokens": 512,
				"max_tool_calls": null,
				"model": "gpt-5.6-sol",
				"moderation": null,
				"output": [
					{
						"id": "rs_0fcb12a6aa68f25a016a4fe98293e081979139ff657f9b612b",
						"type": "reasoning",
						"content": [],
						"summary": []
					},
					{
						"id": "msg_0fcb12a6aa68f25a016a4fe98354fc8197a4b488662491fdd8",
						"type": "message",
						"status": "completed",
						"content": [
							{
								"type": "output_text",
								"annotations": [],
								"logprobs": [],
								"text": "- Total minutes in 30 days: \\(30 \\times 24 \\times 60 = 43{,}200\\)\n- Error budget at 99.9% availability: \\(43{,}200 \\times 0.001 = 43.2\\) minutes\n- Downtime used: 31 minutes\n\n**No**, it has not exceeded the monthly error budget. It has **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": "in_memory",
				"reasoning": {
					"context": "all_turns",
					"effort": "medium",
					"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",
				"usage": {
					"input_tokens": 44,
					"input_tokens_details": {
						"cache_write_tokens": 0,
						"cached_tokens": 0
					},
					"output_tokens": 159,
					"output_tokens_details": {
						"reasoning_tokens": 63
					},
					"total_tokens": 203
				},
				"user": null,
				"metadata": {}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'openai/gpt-5.6-sol',\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: 'medium' },\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 $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"openai/gpt-5.6-sol\",\n  \"input\": \"A service has 99.9% monthly availability and just had 31 minutes of downtime. Has it exceeded the monthly error budget for a 30-day month? Show the calculation briefly.\",\n  \"max_output_tokens\": 512,\n  \"reasoning\": {\n    \"effort\": \"medium\"\n  }\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": true,
	"zdr_comment": null,
	"external_info": "https://openai.com/",
	"terms": "https://openai.com/policies/",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/openai/gpt-5.6-sol.png",
	"metadata": {
		"API": "Responses",
		"Architecture": "Transformer",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"responses"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "openai",
			"pricing": {
				"long_context_threshold_tokens": 272000,
				"short_context_input_tokens": 4,
				"short_context_input_cached_tokens": 0.4,
				"short_context_input_cache_creation_tokens": 5,
				"short_context_output_tokens": 20,
				"long_context_input_tokens": 8,
				"long_context_input_cached_tokens": 0.8,
				"long_context_input_cache_creation_tokens": 10,
				"long_context_output_tokens": 30
			}
		}
	],
	"banner": {
		"id": "e2dc316b-8765-407f-8405-058ab5d502c8",
		"text": "GPT-5.6 Sol is 50% off through Sept 18",
		"severity": "info",
		"dismissible": true
	},
	"created_at": "2026-07-10 02:48:18",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"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": {}
		},
		"output": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"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": {}
		}
	}
}