{
	"model_id": "anthropic/claude-fable-5.2",
	"provider_id": "anthropic",
	"name": "Claude Fable 5.2",
	"description": "Claude Fable 5.2 is built for demanding reasoning and long-horizon agentic work, with adaptive thinking, a 1M token context window, and up to 128K output tokens.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Coding",
		"Reasoning",
		"Enterprise",
		"Agentic"
	],
	"context_length": 1000000,
	"max_output_tokens": 128000,
	"schema_version": "1.0.0",
	"pricing": {
		"Input tokens (per 1M)": 8,
		"Cached input tokens (per 1M)": 0.2,
		"Cache creation tokens (per 1M)": 10,
		"Output tokens (per 1M)": 40
	},
	"examples": [
		{
			"name": "With System Message",
			"description": "Set context with a system message",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "How do I read a JSON file in Python?",
						"role": "user"
					}
				],
				"system": "You are a helpful coding assistant specializing in Python."
			},
			"output": {
				"text": "Use the built-in `json` module:\n\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n    data = json.load(f)\n\nprint(data)\n```\n\n`json.load()` parses the file into Python objects: JSON objects become `dict`s, arrays become `list`s, and strings, numbers, booleans, and `null` become `str`, `int`/`float`, `bool`, and `None`.\n\n**Accessing the data**\n\n```python\n# Given: {\"name\": \"Alice\", \"skills\": [\"Python\", \"SQL\"]}\nprint(data[\"name\"])        # Alice\nprint(data[\"skills\"][0])   # Python\n```\n\n**Handling common errors**\n\n```python\nimport json\n\ntry:\n    with open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n        data = json.load(f)\nexcept FileNotFoundError:\n    print(\"File not found.\")\nexcept json.JSONDecodeError as e:\n    print(f\"Invalid JSON: {e}\")\n```\n\n**Tips**\n\n- Use `json.load(f)` for a file object and `json.loads(s)` for a string.\n- To write JSON back to a file, use `json.dump(data, f, indent=2)`.\n- If your file has one JSON object per line (JSON Lines, `.jsonl`), parse it line by line:\n\n  ```python\n  with open(\"data.jsonl\", encoding=\"utf-8\") as f:\n      records = [json.loads(line) for line in f]\n  ```"
			},
			"raw_response": {
				"model": "claude-fable-5-2",
				"id": "msg_011CgsuBy7YD3SdLFBeFswvH",
				"type": "message",
				"role": "assistant",
				"content": [
					{
						"type": "thinking",
						"thinking": "",
						"signature": "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"
					},
					{
						"type": "text",
						"text": "Use the built-in `json` module:\n\n```python\nimport json\n\nwith open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n    data = json.load(f)\n\nprint(data)\n```\n\n`json.load()` parses the file into Python objects: JSON objects become `dict`s, arrays become `list`s, and strings, numbers, booleans, and `null` become `str`, `int`/`float`, `bool`, and `None`.\n\n**Accessing the data**\n\n```python\n# Given: {\"name\": \"Alice\", \"skills\": [\"Python\", \"SQL\"]}\nprint(data[\"name\"])        # Alice\nprint(data[\"skills\"][0])   # Python\n```\n\n**Handling common errors**\n\n```python\nimport json\n\ntry:\n    with open(\"data.json\", \"r\", encoding=\"utf-8\") as f:\n        data = json.load(f)\nexcept FileNotFoundError:\n    print(\"File not found.\")\nexcept json.JSONDecodeError as e:\n    print(f\"Invalid JSON: {e}\")\n```\n\n**Tips**\n\n- Use `json.load(f)` for a file object and `json.loads(s)` for a string.\n- To write JSON back to a file, use `json.dump(data, f, indent=2)`.\n- If your file has one JSON object per line (JSON Lines, `.jsonl`), parse it line by line:\n\n  ```python\n  with open(\"data.jsonl\", encoding=\"utf-8\") as f:\n      records = [json.loads(line) for line in f]\n  ```"
					}
				],
				"container": null,
				"stop_reason": "end_turn",
				"stop_sequence": null,
				"stop_details": null,
				"usage": {
					"input_tokens": 40,
					"cache_creation_input_tokens": 0,
					"cache_read_input_tokens": 0,
					"cache_creation": {
						"ephemeral_5m_input_tokens": 0,
						"ephemeral_1h_input_tokens": 0
					},
					"output_tokens": 491,
					"output_tokens_details": {
						"thinking_tokens": 24
					},
					"service_tier": "standard",
					"inference_geo": "global",
					"speed": "standard"
				},
				"diagnostics": null
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-fable-5.2',\n  {\n    max_tokens: 1024,\n    messages: [{ content: 'How do I read a JSON file in Python?', role: 'user' }],\n    system: 'You are a helpful coding assistant specializing in Python.',\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"anthropic/claude-fable-5.2\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"How do I read a JSON file in Python?\",\n      \"role\": \"user\"\n    }\n  ],\n  \"system\": \"You are a helpful coding assistant specializing in Python.\"\n}'"
				}
			]
		},
		{
			"name": "Multi-turn Conversation",
			"description": "Continue a conversation with prior assistant context",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "I need help planning a road trip from San Francisco to Los Angeles.",
						"role": "user"
					},
					{
						"content": "I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?",
						"role": "assistant"
					},
					{
						"content": "Yes, what are some good places to stop?",
						"role": "user"
					}
				]
			},
			"output": {
				"text": "The best stops depend on which route you take.\n\n**Highway 1 along the coast (9-10 hours of driving, best split over two days)**\n\nThis is the scenic route. From north to south:\n\n- **Santa Cruz**: a classic beach boardwalk and a good first coffee stop.\n- **Monterey and Carmel**: the Monterey Bay Aquarium, Cannery Row, and Carmel's walkable village and beach.\n- **Big Sur**: the highlight of the drive, with Bixby Bridge, McWay Falls, and Pfeiffer Beach.\n- **San Simeon**: Hearst Castle tours (book ahead) and the elephant seal rookery, which is free and right off the highway.\n- **Morro Bay and San Luis Obispo**: good places to stay overnight, with solid food in downtown SLO.\n- **Santa Barbara**: the Spanish mission, State Street, and the waterfront.\n- **Malibu**: a last beach stop before LA, such as El Matador or Zuma.\n\nCheck Caltrans road conditions before you go, because the Big Sur stretch of Highway 1 sometimes closes for landslides.\n\n**US-101 (about 7 hours)**\n\nThis is a middle ground. It skips Big Sur but still passes through San Luis"
			},
			"raw_response": {
				"model": "claude-fable-5-2",
				"id": "msg_011CgsuCQmtMxj7JPEhCLZZq",
				"type": "message",
				"role": "assistant",
				"content": [
					{
						"type": "thinking",
						"thinking": "",
						"signature": "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"
					},
					{
						"type": "text",
						"text": "The best stops depend on which route you take.\n\n**Highway 1 along the coast (9-10 hours of driving, best split over two days)**\n\nThis is the scenic route. From north to south:\n\n- **Santa Cruz**: a classic beach boardwalk and a good first coffee stop.\n- **Monterey and Carmel**: the Monterey Bay Aquarium, Cannery Row, and Carmel's walkable village and beach.\n- **Big Sur**: the highlight of the drive, with Bixby Bridge, McWay Falls, and Pfeiffer Beach.\n- **San Simeon**: Hearst Castle tours (book ahead) and the elephant seal rookery, which is free and right off the highway.\n- **Morro Bay and San Luis Obispo**: good places to stay overnight, with solid food in downtown SLO.\n- **Santa Barbara**: the Spanish mission, State Street, and the waterfront.\n- **Malibu**: a last beach stop before LA, such as El Matador or Zuma.\n\nCheck Caltrans road conditions before you go, because the Big Sur stretch of Highway 1 sometimes closes for landslides.\n\n**US-101 (about 7 hours)**\n\nThis is a middle ground. It skips Big Sur but still passes through San Luis"
					}
				],
				"container": null,
				"stop_reason": "max_tokens",
				"stop_sequence": null,
				"stop_details": null,
				"usage": {
					"input_tokens": 105,
					"cache_creation_input_tokens": 0,
					"cache_read_input_tokens": 0,
					"cache_creation": {
						"ephemeral_5m_input_tokens": 0,
						"ephemeral_1h_input_tokens": 0
					},
					"output_tokens": 1024,
					"output_tokens_details": {
						"thinking_tokens": 604
					},
					"service_tier": "standard",
					"inference_geo": "global",
					"speed": "standard"
				},
				"diagnostics": null
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-fable-5.2',\n  {\n    max_tokens: 1024,\n    messages: [\n      {\n        content: 'I need help planning a road trip from San Francisco to Los Angeles.',\n        role: 'user',\n      },\n      {\n        content:\n          \"I'd be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?\",\n        role: 'assistant',\n      },\n      { content: 'Yes, what are some good places to stop?', role: 'user' },\n    ],\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"anthropic/claude-fable-5.2\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"I need help planning a road trip from San Francisco to Los Angeles.\",\n      \"role\": \"user\"\n    },\n    {\n      \"content\": \"I'\\''d be happy to help! The drive is about 380 miles and takes roughly 5-6 hours. Would you like suggestions for scenic routes or interesting stops along the way?\",\n      \"role\": \"assistant\"\n    },\n    {\n      \"content\": \"Yes, what are some good places to stop?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"
				}
			]
		},
		{
			"name": "Streaming Response",
			"description": "Stream a response for real-time output",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "Explain the concept of recursion with a simple example.",
						"role": "user"
					}
				],
				"stream": true
			},
			"output": {
				"text": [
					"Recursion is when",
					" a function sol",
					"ves a problem by calling it",
					"self on a smaller version of",
					" the same problem, until the",
					" problem is small",
					" enough to answ",
					"er directly.\n\nEvery rec",
					"ursive function need",
					"s two parts:\n\n1",
					". **Base case:",
					"** a simple input",
					" that it",
					" answers directly, without",
					" calling itself. This",
					" stops the recursion.",
					"\n2. **Recursive case",
					":** the function calls itself",
					" with an",
					" input that",
					" moves closer to the base case",
					".\n\n## Example: factor",
					"ial\n\nThe factorial of a",
					" number `",
					"n` (written `n!`",
					") is the product of all",
					" wh",
					"ole numbers from 1 ",
					"to `n`. For example,",
					" `4! = 4",
					" \u00d7 3 \u00d7 2",
					" \u00d7 1 = 24",
					"`.",
					"\n\nNotice that `4! = ",
					"4 \u00d7 3!`,",
					" and `3! = 3 ",
					"\u00d7 2!`, and so",
					" on. The problem cont",
					"ains a",
					" smaller cop",
					"y of itself, which makes",
					" it a nat",
					"ural fit for recursion:",
					"\n\n```python\ndef factorial",
					"(n):\n    if n <",
					"= 1:          # base case",
					"\n        return 1\n    return",
					" n * factorial(n -",
					" 1)   # recursive",
					" case\n```\n\n## What happens",
					" when you call `factorial(",
					"4)`\n\nEach call wa",
					"its for the one",
					" below it to finish:\n\n```",
					"\nfactorial(4)",
					"\n=",
					" 4 *",
					" factorial(3)\n=",
					" 4 * (3 *",
					" factorial(2))\n=",
					" 4 * (3 *",
					" (2 * factorial(",
					"1)))\n= 4 ",
					"* (3 * (2 ",
					"* 1))     ",
					"\u2190 base case re",
					"ached,",
					" now the results",
					" multiply back up\n= ",
					"4 * (3 * ",
					"2)\n= 4 *",
					" 6\n= 24\n```",
					"\n\nWithout the base case, the",
					" function would call itself forever (",
					"in",
					" practice, until",
					" the program crashes with a st",
					"ack overflow error)."
				]
			},
			"raw_response": [
				{
					"type": "message_start",
					"message": {
						"model": "claude-fable-5-2",
						"id": "msg_011CgsuDKd7HCjnpqvQic3mi",
						"type": "message",
						"role": "assistant",
						"content": [],
						"container": null,
						"stop_reason": null,
						"stop_sequence": null,
						"stop_details": null,
						"usage": {
							"input_tokens": 24,
							"cache_creation_input_tokens": 0,
							"cache_read_input_tokens": 0,
							"cache_creation": {
								"ephemeral_5m_input_tokens": 0,
								"ephemeral_1h_input_tokens": 0
							},
							"output_tokens": 6,
							"service_tier": "standard",
							"inference_geo": "global",
							"speed": "standard"
						},
						"diagnostics": null
					}
				},
				{
					"type": "content_block_start",
					"index": 0,
					"content_block": {
						"type": "thinking",
						"thinking": "",
						"signature": ""
					}
				},
				{
					"type": "ping"
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "thinking_delta",
						"thinking": ""
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "signature_delta",
						"signature": "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"
					}
				},
				{
					"type": "content_block_stop",
					"index": 0
				},
				{
					"type": "content_block_start",
					"index": 1,
					"content_block": {
						"type": "text",
						"text": ""
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "Recursion is when"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " a function sol"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ves a problem by calling it"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "self on a smaller version of"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " the same problem, until the"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " problem is small"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " enough to answ"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "er directly.\n\nEvery rec"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ursive function need"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "s two parts:\n\n1"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": ". **Base case:"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "** a simple input"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " that it"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " answers directly, without"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " calling itself. This"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " stops the recursion."
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n2. **Recursive case"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": ":** the function calls itself"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " with an"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " input that"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " moves closer to the base case"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": ".\n\n## Example: factor"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ial\n\nThe factorial of a"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " number `"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "n` (written `n!`"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": ") is the product of all"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " wh"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ole numbers from 1 "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "to `n`. For example,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " `4! = 4"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " \u00d7 3 \u00d7 2"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " \u00d7 1 = 24"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "`."
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n\nNotice that `4! = "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "4 \u00d7 3!`,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " and `3! = 3 "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\u00d7 2!`, and so"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " on. The problem cont"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ains a"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " smaller cop"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "y of itself, which makes"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " it a nat"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ural fit for recursion:"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n\n```python\ndef factorial"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "(n):\n    if n <"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "= 1:          # base case"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n        return 1\n    return"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " n * factorial(n -"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " 1)   # recursive"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " case\n```\n\n## What happens"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " when you call `factorial("
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "4)`\n\nEach call wa"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "its for the one"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " below it to finish:\n\n```"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\nfactorial(4)"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n="
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " 4 *"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " factorial(3)\n="
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " 4 * (3 *"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " factorial(2))\n="
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " 4 * (3 *"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " (2 * factorial("
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "1)))\n= 4 "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "* (3 * (2 "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "* 1))     "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\u2190 base case re"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ached,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " now the results"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " multiply back up\n= "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "4 * (3 * "
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "2)\n= 4 *"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " 6\n= 24\n```"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "\n\nWithout the base case, the"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " function would call itself forever ("
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "in"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " practice, until"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": " the program crashes with a st"
					}
				},
				{
					"type": "content_block_delta",
					"index": 1,
					"delta": {
						"type": "text_delta",
						"text": "ack overflow error)."
					}
				},
				{
					"type": "content_block_stop",
					"index": 1
				},
				{
					"type": "message_delta",
					"delta": {
						"stop_reason": "end_turn",
						"stop_sequence": null,
						"stop_details": null,
						"container": null
					},
					"usage": {
						"input_tokens": 24,
						"cache_creation_input_tokens": 0,
						"cache_read_input_tokens": 0,
						"output_tokens": 555,
						"output_tokens_details": {
							"thinking_tokens": 60
						}
					}
				},
				{
					"type": "message_stop"
				}
			],
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-fable-5.2',\n  {\n    max_tokens: 1024,\n    messages: [{ content: 'Explain the concept of recursion with a simple example.', role: 'user' }],\n    stream: true,\n  },\n)\nconsole.log(response)"
				},
				{
					"label": "curl",
					"language": "bash",
					"code": "curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/messages \\\n  --header \"Authorization: Bearer $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"anthropic/claude-fable-5.2\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"Explain the concept of recursion with a simple example.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"stream\": true\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": true,
	"zdr_comment": null,
	"external_info": "https://platform.claude.com/docs/en/models/fable-5-2/overview",
	"terms": "https://www.anthropic.com/legal/commercial-terms",
	"cover_image_url": null,
	"metadata": {
		"Adaptive Thinking": "Yes",
		"Architecture": "Transformer"
	},
	"request_formats": [
		"anthropic-messages"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "anthropic",
			"pricing": {
				"input_tokens": 8,
				"input_cached_tokens": 0.2,
				"input_cache_creation_tokens": 10,
				"output_tokens": 40
			}
		}
	],
	"banner": null,
	"created_at": "2026-11-10 19:22:16",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"messages": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"role": {
										"type": "string",
										"enum": [
											"user",
											"assistant",
											"system"
										]
									},
									"content": {
										"anyOf": [
											{
												"type": "string"
											},
											{
												"type": "array",
												"items": {
													"type": "object",
													"properties": {
														"type": {
															"type": "string"
														},
														"text": {
															"type": "string"
														},
														"source": {},
														"cache_control": {
															"type": "object",
															"properties": {
																"type": {
																	"type": "string",
																	"const": "ephemeral"
																},
																"ttl": {
																	"type": "string",
																	"enum": [
																		"5m",
																		"1h"
																	]
																}
															},
															"required": [
																"type"
															],
															"additionalProperties": false
														}
													},
													"required": [
														"type"
													],
													"additionalProperties": {}
												}
											}
										]
									}
								},
								"required": [
									"role",
									"content"
								],
								"additionalProperties": false
							}
						},
						"max_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"system": {
							"anyOf": [
								{
									"type": "string"
								},
								{
									"type": "array",
									"items": {
										"type": "object",
										"properties": {
											"type": {
												"type": "string",
												"const": "text"
											},
											"text": {
												"type": "string"
											},
											"cache_control": {
												"type": "object",
												"properties": {
													"type": {
														"type": "string",
														"const": "ephemeral"
													},
													"ttl": {
														"type": "string",
														"enum": [
															"5m",
															"1h"
														]
													}
												},
												"required": [
													"type"
												],
												"additionalProperties": false
											}
										},
										"required": [
											"type",
											"text"
										],
										"additionalProperties": {}
									}
								}
							]
						},
						"temperature": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"top_p": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"top_k": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"stream": {
							"type": "boolean"
						},
						"metadata": {
							"type": "object",
							"propertyNames": {
								"type": "string"
							},
							"additionalProperties": {}
						}
					},
					"required": [
						"messages",
						"max_tokens"
					],
					"additionalProperties": {},
					"title": "Messages"
				},
				{
					"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"
						},
						"type": {
							"type": "string",
							"const": "message"
						},
						"role": {
							"type": "string",
							"const": "assistant"
						},
						"content": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"type": {
										"type": "string"
									},
									"text": {
										"type": "string"
									}
								},
								"required": [
									"type"
								],
								"additionalProperties": {}
							}
						},
						"model": {
							"type": "string"
						},
						"stop_reason": {
							"type": [
								"string",
								"null"
							]
						},
						"usage": {
							"type": "object",
							"properties": {
								"input_tokens": {
									"type": "number"
								},
								"output_tokens": {
									"type": "number"
								},
								"cache_creation_input_tokens": {
									"type": [
										"number",
										"null"
									]
								},
								"cache_read_input_tokens": {
									"type": [
										"number",
										"null"
									]
								},
								"speed": {
									"type": [
										"string",
										"null"
									]
								}
							},
							"required": [
								"input_tokens",
								"output_tokens"
							],
							"additionalProperties": {}
						}
					},
					"required": [
						"id",
						"type",
						"role",
						"content",
						"model",
						"stop_reason",
						"usage"
					],
					"additionalProperties": {},
					"title": "Messages"
				},
				{
					"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"
				}
			]
		}
	}
}