{
	"model_id": "anthropic/claude-sonnet-5.5",
	"provider_id": "anthropic",
	"name": "Claude Sonnet 5.5",
	"description": "Claude Sonnet 5.5 offers the best combination of speed and intelligence, with adaptive thinking for coding, tool use, reasoning, and long-horizon work.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Coding",
		"Reasoning",
		"Agentic"
	],
	"context_length": 1000000,
	"max_output_tokens": 128000,
	"schema_version": "1.0.0",
	"pricing": {
		"Input tokens (per 1M)": 2,
		"Cached input tokens (per 1M)": 0.1,
		"Cache creation tokens (per 1M)": 2.5,
		"Output tokens (per 1M)": 10
	},
	"examples": [
		{
			"name": "System-Guided Explanation",
			"description": "Use a system message to set a concise technical response style.",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "Explain why database indexes improve lookup performance.",
						"role": "user"
					}
				],
				"system": "You are a concise database engineering tutor. Include one concrete example."
			},
			"output": {
				"text": "**Core idea:** An index is a separate, sorted data structure (usually a B-tree) that lets the database find rows without scanning the entire table.\n\n**Without an index:** To find a row, the database does a *full table scan*, checking every row. Cost grows linearly: O(n).\n\n**With an index:** The database navigates a balanced tree. Each step eliminates a large fraction of the remaining data, so lookup cost is O(log n). Because B-tree nodes hold hundreds of keys, even huge tables are typically only 3\u20134 levels deep, meaning just a few disk/page reads.\n\n**Analogy:** It's like a book's index. Instead of reading every page to find \"photosynthesis,\" you look it up alphabetically and jump straight to the page.\n\n**Concrete example**\n\n```sql\nCREATE TABLE users (\n  id INT PRIMARY KEY,\n  email VARCHAR(255),\n  name VARCHAR(100)\n);\n-- Assume 10 million rows\n\nSELECT * FROM users WHERE email = 'ana@example.com';\n```\n\n- **No index on `email`:** The database reads all 10,000,000 rows to find matches. This may take seconds.\n- **After indexing:**\n  ```sql\n  CREATE INDEX idx_users_email ON users(email);\n  ```\n  The database traverses the B-tree on `email` (~3\u20134 page reads), finds a pointer to the matching row, and fetches it directly. This typically takes milliseconds.\n\nYou can verify this with `EXPLAIN`: you'll see a `Seq Scan` / `type: ALL` before, and an `Index Scan` / `type: ref` after.\n\n**Why it works, in short**\n1. Keys are stored **sorted**, enabling binary-search-like navigation.\n2. The tree is **shallow and wide**, minimizing expensive disk I/O.\n3. Leaf entries **point directly** to the row location.\n\n**Tradeoffs:** Indexes consume extra storage and slow down `INSERT`/`UPDATE`/`DELETE`, since the index must be kept in sync. Index columns you frequently filter, join, or sort on, not everything."
			},
			"raw_response": {
				"model": "claude-sonnet-5-5",
				"id": "msg_011CfWPzXNFbhjzHxLnrjPAs",
				"type": "message",
				"role": "assistant",
				"content": [
					{
						"type": "text",
						"text": "**Core idea:** An index is a separate, sorted data structure (usually a B-tree) that lets the database find rows without scanning the entire table.\n\n**Without an index:** To find a row, the database does a *full table scan*, checking every row. Cost grows linearly: O(n).\n\n**With an index:** The database navigates a balanced tree. Each step eliminates a large fraction of the remaining data, so lookup cost is O(log n). Because B-tree nodes hold hundreds of keys, even huge tables are typically only 3\u20134 levels deep, meaning just a few disk/page reads.\n\n**Analogy:** It's like a book's index. Instead of reading every page to find \"photosynthesis,\" you look it up alphabetically and jump straight to the page.\n\n**Concrete example**\n\n```sql\nCREATE TABLE users (\n  id INT PRIMARY KEY,\n  email VARCHAR(255),\n  name VARCHAR(100)\n);\n-- Assume 10 million rows\n\nSELECT * FROM users WHERE email = 'ana@example.com';\n```\n\n- **No index on `email`:** The database reads all 10,000,000 rows to find matches. This may take seconds.\n- **After indexing:**\n  ```sql\n  CREATE INDEX idx_users_email ON users(email);\n  ```\n  The database traverses the B-tree on `email` (~3\u20134 page reads), finds a pointer to the matching row, and fetches it directly. This typically takes milliseconds.\n\nYou can verify this with `EXPLAIN`: you'll see a `Seq Scan` / `type: ALL` before, and an `Index Scan` / `type: ref` after.\n\n**Why it works, in short**\n1. Keys are stored **sorted**, enabling binary-search-like navigation.\n2. The tree is **shallow and wide**, minimizing expensive disk I/O.\n3. Leaf entries **point directly** to the row location.\n\n**Tradeoffs:** Indexes consume extra storage and slow down `INSERT`/`UPDATE`/`DELETE`, since the index must be kept in sync. Index columns you frequently filter, join, or sort on, not everything."
					}
				],
				"container": null,
				"stop_reason": "end_turn",
				"stop_sequence": null,
				"stop_details": null,
				"usage": {
					"input_tokens": 46,
					"cache_creation_input_tokens": 0,
					"cache_read_input_tokens": 0,
					"cache_creation": {
						"ephemeral_5m_input_tokens": 0,
						"ephemeral_1h_input_tokens": 0
					},
					"output_tokens": 705,
					"output_tokens_details": {
						"thinking_tokens": 0
					},
					"service_tier": "standard",
					"inference_geo": "global"
				},
				"diagnostics": null
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-sonnet-5.5',\n  {\n    max_tokens: 1024,\n    messages: [{ content: 'Explain why database indexes improve lookup performance.', role: 'user' }],\n    system: 'You are a concise database engineering tutor. Include one concrete example.',\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-sonnet-5.5\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"Explain why database indexes improve lookup performance.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"system\": \"You are a concise database engineering tutor. Include one concrete example.\"\n}'"
				}
			]
		},
		{
			"name": "Adaptive Reasoning",
			"description": "Use adaptive thinking with high effort for a multi-step reasoning task.",
			"input": {
				"max_tokens": 2048,
				"messages": [
					{
						"content": "A service processes 120 jobs per minute. Each retry adds 15% more work, and 8% of jobs retry once. What is the expected number of jobs processed per minute including retries? Show the calculation.",
						"role": "user"
					}
				],
				"output_config": {
					"effort": "high"
				},
				"thinking": {
					"type": "adaptive"
				}
			},
			"output": {
				"text": "**Assumptions:** 120 jobs/min is the base load. 8% of jobs are retried exactly once. Each retry costs 15% more work than the original run, so it counts as 1.15 job-equivalents.\n\n**Calculation**\n\n1. Jobs retried per minute: 120 \u00d7 0.08 = 9.6\n2. Work from retries: 9.6 \u00d7 1.15 = 11.04 job-equivalents\n3. Total: 120 + 11.04 = **131.04 job-equivalents per minute**\n\nThat is about 9.2% more load than the base 120.\n\n**Alternative reading:** If you only want the number of executions and each retry counts as one ordinary job, the total is 120 + 9.6 = **129.6 jobs per minute**. The 15% extra work then doesn't enter the count.\n\nThe first figure (131.04) is the better estimate of capacity needed, since it reflects the heavier cost of retries."
			},
			"raw_response": {
				"model": "claude-sonnet-5-5",
				"id": "msg_011CfWPzyhH6mWkQYYXi8zC5",
				"type": "message",
				"role": "assistant",
				"content": [
					{
						"type": "thinking",
						"thinking": "",
						"signature": "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"
					},
					{
						"type": "text",
						"text": "**Assumptions:** 120 jobs/min is the base load. 8% of jobs are retried exactly once. Each retry costs 15% more work than the original run, so it counts as 1.15 job-equivalents.\n\n**Calculation**\n\n1. Jobs retried per minute: 120 \u00d7 0.08 = 9.6\n2. Work from retries: 9.6 \u00d7 1.15 = 11.04 job-equivalents\n3. Total: 120 + 11.04 = **131.04 job-equivalents per minute**\n\nThat is about 9.2% more load than the base 120.\n\n**Alternative reading:** If you only want the number of executions and each retry counts as one ordinary job, the total is 120 + 9.6 = **129.6 jobs per minute**. The 15% extra work then doesn't enter the count.\n\nThe first figure (131.04) is the better estimate of capacity needed, since it reflects the heavier cost of retries."
					}
				],
				"container": null,
				"stop_reason": "end_turn",
				"stop_sequence": null,
				"stop_details": null,
				"usage": {
					"input_tokens": 72,
					"cache_creation_input_tokens": 0,
					"cache_read_input_tokens": 0,
					"cache_creation": {
						"ephemeral_5m_input_tokens": 0,
						"ephemeral_1h_input_tokens": 0
					},
					"output_tokens": 667,
					"output_tokens_details": {
						"thinking_tokens": 368
					},
					"service_tier": "standard",
					"inference_geo": "global"
				},
				"diagnostics": null
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-sonnet-5.5',\n  {\n    max_tokens: 2048,\n    messages: [\n      {\n        content:\n          'A service processes 120 jobs per minute. Each retry adds 15% more work, and 8% of jobs retry once. What is the expected number of jobs processed per minute including retries? Show the calculation.',\n        role: 'user',\n      },\n    ],\n    output_config: { effort: 'high' },\n    thinking: { type: 'adaptive' },\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-sonnet-5.5\",\n  \"max_tokens\": 2048,\n  \"messages\": [\n    {\n      \"content\": \"A service processes 120 jobs per minute. Each retry adds 15% more work, and 8% of jobs retry once. What is the expected number of jobs processed per minute including retries? Show the calculation.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"output_config\": {\n    \"effort\": \"high\"\n  },\n  \"thinking\": {\n    \"type\": \"adaptive\"\n  }\n}'"
				}
			]
		},
		{
			"name": "Tool Use",
			"description": "Ask the model to select and call a tool when it needs structured external information.",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "What is the weather in San Francisco right now?",
						"role": "user"
					}
				],
				"tools": [
					{
						"description": "Get the current weather for a city.",
						"input_schema": {
							"properties": {
								"city": {
									"type": "string"
								}
							},
							"required": [
								"city"
							],
							"type": "object"
						},
						"name": "get_weather"
					}
				]
			},
			"error": {
				"kind": "runner-failure",
				"message": "normalizer returned empty output \u2014 check modality vs response shape, or recapture",
				"timestamp": "2026-09-28T19:34:24.420Z"
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-sonnet-5.5',\n  {\n    max_tokens: 1024,\n    messages: [{ content: 'What is the weather in San Francisco right now?', role: 'user' }],\n    tools: [\n      {\n        description: 'Get the current weather for a city.',\n        input_schema: {\n          properties: { city: { type: 'string' } },\n          required: ['city'],\n          type: 'object',\n        },\n        name: 'get_weather',\n      },\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-sonnet-5.5\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"What is the weather in San Francisco right now?\",\n      \"role\": \"user\"\n    }\n  ],\n  \"tools\": [\n    {\n      \"description\": \"Get the current weather for a city.\",\n      \"input_schema\": {\n        \"properties\": {\n          \"city\": {\n            \"type\": \"string\"\n          }\n        },\n        \"required\": [\n          \"city\"\n        ],\n        \"type\": \"object\"\n      },\n      \"name\": \"get_weather\"\n    }\n  ]\n}'"
				}
			]
		},
		{
			"name": "Streaming Checklist",
			"description": "Enable streaming for incremental response delivery.",
			"input": {
				"max_tokens": 1024,
				"messages": [
					{
						"content": "Write a short three-step checklist for reviewing a pull request.",
						"role": "user"
					}
				],
				"stream": true
			},
			"output": {
				"text": [
					"# Pull Request Review",
					" Checklist\n\n1. **",
					"Understand the int",
					"ent**\n   - Read the",
					" PR description and lin",
					"ked issue.\n   -",
					" Confirm the change sol",
					"ves the st",
					"ated problem and st",
					"ays within scope.\n\n2.",
					" **Review the code**\n   ",
					"- Check for correctness,",
					" ed",
					"ge cases, and pot",
					"ential bugs.\n   -",
					" Look",
					" for cl",
					"arity, cons",
					"istency",
					" with existing con",
					"ventions, and un",
					"necessary complexity.",
					"\n   - Wat",
					"ch for security,",
					" performance, or back",
					"ward",
					"-compatibility conc",
					"erns.\n\n3. **",
					"Verify qu",
					"ality and give",
					" feedback**\n   -",
					" Confirm tests ex",
					"ist,",
					" are",
					" me",
					"aningful, and pass in",
					" CI.\n   - Check",
					" that doc",
					"s or",
					" com",
					"ments are updated where",
					" needed.\n   - Le",
					"ave cl",
					"ear, constructive com",
					"ments, dist",
					"inguishing bloc",
					"king issues from opt",
					"ional su",
					"ggestions, then approve or",
					" request changes."
				]
			},
			"raw_response": [
				{
					"type": "message_start",
					"message": {
						"model": "claude-sonnet-5-5",
						"id": "msg_011CfWQ1TEzRFYuStMzD8Fi7",
						"type": "message",
						"role": "assistant",
						"content": [],
						"container": null,
						"stop_reason": null,
						"stop_sequence": null,
						"stop_details": null,
						"usage": {
							"input_tokens": 28,
							"cache_creation_input_tokens": 0,
							"cache_read_input_tokens": 0,
							"cache_creation": {
								"ephemeral_5m_input_tokens": 0,
								"ephemeral_1h_input_tokens": 0
							},
							"output_tokens": 8,
							"service_tier": "standard",
							"inference_geo": "global"
						},
						"diagnostics": null
					}
				},
				{
					"type": "content_block_start",
					"index": 0,
					"content_block": {
						"type": "text",
						"text": ""
					}
				},
				{
					"type": "ping"
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "# Pull Request Review"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " Checklist\n\n1. **"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "Understand the int"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ent**\n   - Read the"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " PR description and lin"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ked issue.\n   -"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " Confirm the change sol"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ves the st"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ated problem and st"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ays within scope.\n\n2."
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " **Review the code**\n   "
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "- Check for correctness,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " ed"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ge cases, and pot"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ential bugs.\n   -"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " Look"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " for cl"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "arity, cons"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "istency"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " with existing con"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ventions, and un"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "necessary complexity."
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "\n   - Wat"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ch for security,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " performance, or back"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ward"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "-compatibility conc"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "erns.\n\n3. **"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "Verify qu"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ality and give"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " feedback**\n   -"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " Confirm tests ex"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ist,"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " are"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " me"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "aningful, and pass in"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " CI.\n   - Check"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " that doc"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "s or"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " com"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ments are updated where"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " needed.\n   - Le"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ave cl"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ear, constructive com"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ments, dist"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "inguishing bloc"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "king issues from opt"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ional su"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": "ggestions, then approve or"
					}
				},
				{
					"type": "content_block_delta",
					"index": 0,
					"delta": {
						"type": "text_delta",
						"text": " request changes."
					}
				},
				{
					"type": "content_block_stop",
					"index": 0
				},
				{
					"type": "message_delta",
					"delta": {
						"stop_reason": "end_turn",
						"stop_sequence": null,
						"stop_details": null,
						"container": null
					},
					"usage": {
						"input_tokens": 28,
						"cache_creation_input_tokens": 0,
						"cache_read_input_tokens": 0,
						"output_tokens": 247,
						"output_tokens_details": {
							"thinking_tokens": 0
						}
					}
				},
				{
					"type": "message_stop"
				}
			],
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'anthropic/claude-sonnet-5.5',\n  {\n    max_tokens: 1024,\n    messages: [\n      { content: 'Write a short three-step checklist for reviewing a pull request.', role: 'user' },\n    ],\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-sonnet-5.5\",\n  \"max_tokens\": 1024,\n  \"messages\": [\n    {\n      \"content\": \"Write a short three-step checklist for reviewing a pull request.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"stream\": true\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": false,
	"zdr_comment": null,
	"external_info": "https://platform.claude.com/docs/en/models/sonnet-5-5/overview",
	"terms": "https://www.anthropic.com/legal/commercial-terms",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/anthropic/claude-sonnet-5.5.png",
	"metadata": {
		"Adaptive Thinking": "Yes",
		"Architecture": "Transformer",
		"Input Price": "$2 / MTok",
		"Output Price": "$10 / MTok",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"anthropic-messages"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "anthropic",
			"pricing": {
				"input_tokens": 2,
				"input_cached_tokens": 0.1,
				"input_cache_creation_tokens": 2.5,
				"output_tokens": 10
			}
		}
	],
	"banner": null,
	"created_at": "2026-10-06 18:42:20",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"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": {}
							}
						}
					]
				},
				"stream": {
					"type": "boolean"
				},
				"metadata": {
					"type": "object",
					"propertyNames": {
						"type": "string"
					},
					"additionalProperties": {}
				}
			},
			"required": [
				"messages",
				"max_tokens"
			],
			"additionalProperties": {}
		},
		"output": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"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": {}
		}
	}
}