{
	"model_id": "minimax/m3",
	"provider_id": "minimax",
	"name": "MiniMax M3",
	"description": "MiniMax's M3 language model with frontier coding and agentic capabilities, a 1M token context window, and multilingual support.",
	"task": "Text Generation",
	"tags": [
		"LLM",
		"Multilingual"
	],
	"context_length": 1000000,
	"max_output_tokens": 4096,
	"schema_version": "1.0.0",
	"pricing": {
		"Input <=512k (per 1M)": 0.3,
		"Output <=512k (per 1M)": 1.2,
		"Cached input <=512k (per 1M)": 0.06,
		"Input >512k (per 1M)": 0.6,
		"Output >512k (per 1M)": 2.4,
		"Cached input >512k (per 1M)": 0.12
	},
	"examples": [
		{
			"name": "Simple Conversation",
			"description": "Basic chat completion request",
			"input": {
				"max_tokens": 2048,
				"messages": [
					{
						"content": "What is the capital of France?",
						"role": "user"
					}
				]
			},
			"output": {
				"text": "The capital of France is **Paris**."
			},
			"raw_response": {
				"id": "066cf8a95614a7ebfcaa6ffd7f2cd663",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "The capital of France is **Paris**.",
							"name": "MiniMax AI",
							"audio_content": "",
							"reasoning_content": "The user is asking a simple factual question: \"What is the capital of France?\" This is straightforward - the capital of France is Paris.",
							"reasoning_details": [
								{
									"type": "reasoning.text",
									"id": "reasoning-text-1",
									"format": "MiniMax-response-v1",
									"index": 0,
									"text": "The user is asking a simple factual question: \"What is the capital of France?\" This is straightforward - the capital of France is Paris."
								}
							]
						},
						"finish_reason": "stop"
					}
				],
				"created": 1780336041,
				"model": "MiniMax-M3",
				"object": "chat.completion",
				"usage": {
					"total_tokens": 221,
					"prompt_tokens": 183,
					"completion_tokens": 38,
					"total_characters": 0,
					"prompt_tokens_details": {
						"cached_tokens": 114
					}
				},
				"input_sensitive": false,
				"output_sensitive": false,
				"base_resp": {
					"status_code": 0,
					"status_msg": ""
				},
				"input_sensitive_type": 0,
				"output_sensitive_type": 0,
				"output_sensitive_int": 0,
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'minimax/m3',\n  { max_tokens: 2048, messages: [{ content: 'What is the capital of France?', role: 'user' }] },\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\": \"minimax/m3\",\n  \"max_tokens\": 2048,\n  \"messages\": [\n    {\n      \"content\": \"What is the capital of France?\",\n      \"role\": \"user\"\n    }\n  ]\n}'"
				}
			]
		},
		{
			"name": "With System Prompt",
			"description": "Using a system prompt to guide behavior",
			"input": {
				"max_tokens": 2048,
				"messages": [
					{
						"content": "You are a helpful cooking assistant. Give concise recipes with metric measurements.",
						"role": "system"
					},
					{
						"content": "How do I make a simple pasta aglio e olio?",
						"role": "user"
					}
				],
				"temperature": 0.7
			},
			"output": {
				"text": "# Pasta Aglio e Olio\n\nA classic Italian dish that comes together in minutes with just a few ingredients.\n\n**Serves:** 2 | **Prep:** 5 min | **Cook:** 15 min\n\n## Ingredients\n- 200 g spaghetti or linguine\n- 80 ml extra virgin olive oil\n- 4 garlic cloves, thinly sliced\n- 1\u20132 small dried red chilies, crushed (or \u00bc tsp chili flakes)\n- Salt, for pasta water\n- 15 g fresh flat-leaf parsley, chopped\n- Grated Parmesan or Pecorino (optional, traditionalists skip it)\n\n## Method\n1. **Boil pasta:** Bring a large pot of well-salted water to a rolling boil. Cook the pasta until al dente (about 1 minute less than package instructions). Reserve 1 cup of pasta water before draining.\n2. **Infuse oil:** While the pasta cooks, gently heat the olive oil in a wide pan over low-medium heat. Add the garlic and chilies, and cook slowly for 2\u20133 minutes until the garlic turns pale golden. **Don't let it brown** \u2014 it will turn bitter.\n3. **Combine:** Add the drained pasta to the pan with a splash of reserved pasta water. Toss vigorously over medium heat for about 1 minute so the pasta absorbs the oil.\n4. **Finish:** Add more pasta water as needed to create a light, silky sauce that coats the noodles. Stir in the parsley and season with salt.\n5. **Serve** immediately, topped with cheese if using.\n\n## Tips\n- Cold olive oil + slow heat = better flavor extraction.\n- The starch in the pasta water is key to a glossy, emulsified sauce.\n\nBuon appetito! \ud83c\udf5d"
			},
			"raw_response": {
				"id": "066cf8abfaba58c357c660ebfad38073",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "# Pasta Aglio e Olio\n\nA classic Italian dish that comes together in minutes with just a few ingredients.\n\n**Serves:** 2 | **Prep:** 5 min | **Cook:** 15 min\n\n## Ingredients\n- 200 g spaghetti or linguine\n- 80 ml extra virgin olive oil\n- 4 garlic cloves, thinly sliced\n- 1\u20132 small dried red chilies, crushed (or \u00bc tsp chili flakes)\n- Salt, for pasta water\n- 15 g fresh flat-leaf parsley, chopped\n- Grated Parmesan or Pecorino (optional, traditionalists skip it)\n\n## Method\n1. **Boil pasta:** Bring a large pot of well-salted water to a rolling boil. Cook the pasta until al dente (about 1 minute less than package instructions). Reserve 1 cup of pasta water before draining.\n2. **Infuse oil:** While the pasta cooks, gently heat the olive oil in a wide pan over low-medium heat. Add the garlic and chilies, and cook slowly for 2\u20133 minutes until the garlic turns pale golden. **Don't let it brown** \u2014 it will turn bitter.\n3. **Combine:** Add the drained pasta to the pan with a splash of reserved pasta water. Toss vigorously over medium heat for about 1 minute so the pasta absorbs the oil.\n4. **Finish:** Add more pasta water as needed to create a light, silky sauce that coats the noodles. Stir in the parsley and season with salt.\n5. **Serve** immediately, topped with cheese if using.\n\n## Tips\n- Cold olive oil + slow heat = better flavor extraction.\n- The starch in the pasta water is key to a glossy, emulsified sauce.\n\nBuon appetito! \ud83c\udf5d",
							"name": "MiniMax AI",
							"audio_content": "",
							"reasoning_content": "The user is asking for a simple pasta aglio e olio recipe. The system prompt says I should give concise recipes with metric measurements. Let me provide a classic, simple recipe.",
							"reasoning_details": [
								{
									"type": "reasoning.text",
									"id": "reasoning-text-1",
									"format": "MiniMax-response-v1",
									"index": 0,
									"text": "The user is asking for a simple pasta aglio e olio recipe. The system prompt says I should give concise recipes with metric measurements. Let me provide a classic, simple recipe."
								}
							]
						},
						"finish_reason": "stop"
					}
				],
				"created": 1780336043,
				"model": "MiniMax-M3",
				"object": "chat.completion",
				"usage": {
					"total_tokens": 595,
					"prompt_tokens": 197,
					"completion_tokens": 398,
					"total_characters": 0,
					"prompt_tokens_details": {
						"cached_tokens": 114
					}
				},
				"input_sensitive": false,
				"output_sensitive": false,
				"base_resp": {
					"status_code": 0,
					"status_msg": ""
				},
				"input_sensitive_type": 0,
				"output_sensitive_type": 0,
				"output_sensitive_int": 0,
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'minimax/m3',\n  {\n    max_tokens: 2048,\n    messages: [\n      {\n        content:\n          'You are a helpful cooking assistant. Give concise recipes with metric measurements.',\n        role: 'system',\n      },\n      { content: 'How do I make a simple pasta aglio e olio?', role: 'user' },\n    ],\n    temperature: 0.7,\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\": \"minimax/m3\",\n  \"max_tokens\": 2048,\n  \"messages\": [\n    {\n      \"content\": \"You are a helpful cooking assistant. Give concise recipes with metric measurements.\",\n      \"role\": \"system\"\n    },\n    {\n      \"content\": \"How do I make a simple pasta aglio e olio?\",\n      \"role\": \"user\"\n    }\n  ],\n  \"temperature\": 0.7\n}'"
				}
			]
		},
		{
			"name": "Multi-turn Conversation",
			"description": "Continuing a conversation with context",
			"input": {
				"max_tokens": 2048,
				"messages": [
					{
						"content": "What are the main differences between TCP and UDP?",
						"role": "user"
					},
					{
						"content": "TCP is connection-oriented and guarantees delivery, while UDP is connectionless and faster but without delivery guarantees.",
						"role": "assistant"
					},
					{
						"content": "When would I choose UDP over TCP?",
						"role": "user"
					}
				],
				"temperature": 0.5
			},
			"output": {
				"text": "Use UDP for time-sensitive applications like video streaming, online gaming, or VoIP where speed matters more than perfect reliability."
			},
			"raw_response": {
				"id": "066cf8bb1c666fc68c6810518100c7ba",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "Use UDP for time-sensitive applications like video streaming, online gaming, or VoIP where speed matters more than perfect reliability.",
							"name": "MiniMax AI",
							"audio_content": "",
							"reasoning_content": ""
						},
						"finish_reason": "stop"
					}
				],
				"created": 1780336059,
				"model": "MiniMax-M3",
				"object": "chat.completion",
				"usage": {
					"total_tokens": 250,
					"prompt_tokens": 225,
					"completion_tokens": 25,
					"total_characters": 0,
					"prompt_tokens_details": {
						"cached_tokens": 114
					}
				},
				"input_sensitive": false,
				"output_sensitive": false,
				"base_resp": {
					"status_code": 0,
					"status_msg": ""
				},
				"input_sensitive_type": 0,
				"output_sensitive_type": 0,
				"output_sensitive_int": 0,
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'minimax/m3',\n  {\n    max_tokens: 2048,\n    messages: [\n      { content: 'What are the main differences between TCP and UDP?', role: 'user' },\n      {\n        content:\n          'TCP is connection-oriented and guarantees delivery, while UDP is connectionless and faster but without delivery guarantees.',\n        role: 'assistant',\n      },\n      { content: 'When would I choose UDP over TCP?', role: 'user' },\n    ],\n    temperature: 0.5,\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\": \"minimax/m3\",\n  \"max_tokens\": 2048,\n  \"messages\": [\n    {\n      \"content\": \"What are the main differences between TCP and UDP?\",\n      \"role\": \"user\"\n    },\n    {\n      \"content\": \"TCP is connection-oriented and guarantees delivery, while UDP is connectionless and faster but without delivery guarantees.\",\n      \"role\": \"assistant\"\n    },\n    {\n      \"content\": \"When would I choose UDP over TCP?\",\n      \"role\": \"user\"\n    }\n  ],\n  \"temperature\": 0.5\n}'"
				}
			]
		},
		{
			"name": "Creative Writing",
			"description": "Higher temperature for creative output",
			"input": {
				"max_tokens": 2048,
				"messages": [
					{
						"content": "Write a haiku about programming.",
						"role": "user"
					}
				],
				"temperature": 0.9
			},
			"output": {
				"text": "Fingers on the keys,\nBuilding worlds from empty void\u2014\nCode becomes the light."
			},
			"raw_response": {
				"id": "066cf8be5675980f2ff647974879fb77",
				"choices": [
					{
						"index": 0,
						"message": {
							"role": "assistant",
							"content": "Fingers on the keys,\nBuilding worlds from empty void\u2014\nCode becomes the light.",
							"name": "MiniMax AI",
							"audio_content": "",
							"reasoning_content": "The user wants a haiku about programming. A haiku is a traditional Japanese poem with three lines following a 5-7-5 syllable pattern. I should create one that captures something meaningful about programming.\n\nLet me think of a few options:\n\n1. About debugging:\nLines (5-7-5):\n- \"Bugs hide in the code\" (4) - need 5\n- \"Silent errors whisper\" (6) - need 7\n- \"Find them, fix, deploy\" (5) \u2713\n\nLet me recount:\n- \"Bugs hide in the code\" - Bugs(1) hide(2) in(3) the(4) code(5) = 5 \u2713\n- \"Silent errors whisper\" - Si-lent(2) er-rors(4) whis-per(6) = 6, need 7\n- Try: \"Silent errors always whisper\" - 7 \u2713\n- \"Find them, fix, deploy\" - Find(1) them(2) fix(3) de-ploy(5) = 5 \u2713\n\n2. About code in general:\n- \"Logic flows like streams\" (5) - Lo-gic(2) flows(3) like(4) streams(5) = 5 \u2713\n- \"Through brackets and curved braces\" (7) - Through(1) brack-ets(3) and(4) curved(5) bra-ces(7) = 7 \u2713\n- \"Dreams made into life\" (5) - Dreams(1) made(2) in-to(4) life(5) = 5 \u2713\n\n3. Another option:\n- \"Fingers on the keys\" (5) - Fin-gers(2) on(3) the(4) keys(5) = 5 \u2713\n- \"Building worlds from nothing\" (7) - Build-ing(2) worlds(3) from(4) no-thing(6) = 6, need 7\n- Try: \"Building worlds from empty void\" - Build-ing(2) worlds(3) from(4) emp-ty(6) void(7) = 7 \u2713\n- \"Code becomes the light\" (5) - Code(1) be-comes(3) the(4) light(5) = 5 \u2713\n\nLet me go with option 2 or 3, both are nice. I'll provide one clean haiku and maybe offer an alternative.\n\nActually, let me just give one good one. Option 3 feels more poetic and evocative.\n\nLet me verify option 3 once more:\n- \"Fingers on the keys\" - Fin-gers(2) on(3) the(4) keys(5) = 5 \u2713\n- \"Building worlds from empty void\" - Build-ing(2) worlds(3) from(4) emp-ty(6) void(7) = 7 \u2713\n- \"Code becomes the light\" - Code(1) be-comes(3) the(4) light(5) = 5 \u2713\n\nThat works well. I could also provide a simpler one focused on a different aspect of programming.\n\nI'll give a haiku with a clean delivery. Let me also think about a second option to make it more useful, or just stick with one well-crafted one.\n\nI'll provide one haiku and keep it concise.",
							"reasoning_details": [
								{
									"type": "reasoning.text",
									"id": "reasoning-text-1",
									"format": "MiniMax-response-v1",
									"index": 0,
									"text": "The user wants a haiku about programming. A haiku is a traditional Japanese poem with three lines following a 5-7-5 syllable pattern. I should create one that captures something meaningful about programming.\n\nLet me think of a few options:\n\n1. About debugging:\nLines (5-7-5):\n- \"Bugs hide in the code\" (4) - need 5\n- \"Silent errors whisper\" (6) - need 7\n- \"Find them, fix, deploy\" (5) \u2713\n\nLet me recount:\n- \"Bugs hide in the code\" - Bugs(1) hide(2) in(3) the(4) code(5) = 5 \u2713\n- \"Silent errors whisper\" - Si-lent(2) er-rors(4) whis-per(6) = 6, need 7\n- Try: \"Silent errors always whisper\" - 7 \u2713\n- \"Find them, fix, deploy\" - Find(1) them(2) fix(3) de-ploy(5) = 5 \u2713\n\n2. About code in general:\n- \"Logic flows like streams\" (5) - Lo-gic(2) flows(3) like(4) streams(5) = 5 \u2713\n- \"Through brackets and curved braces\" (7) - Through(1) brack-ets(3) and(4) curved(5) bra-ces(7) = 7 \u2713\n- \"Dreams made into life\" (5) - Dreams(1) made(2) in-to(4) life(5) = 5 \u2713\n\n3. Another option:\n- \"Fingers on the keys\" (5) - Fin-gers(2) on(3) the(4) keys(5) = 5 \u2713\n- \"Building worlds from nothing\" (7) - Build-ing(2) worlds(3) from(4) no-thing(6) = 6, need 7\n- Try: \"Building worlds from empty void\" - Build-ing(2) worlds(3) from(4) emp-ty(6) void(7) = 7 \u2713\n- \"Code becomes the light\" (5) - Code(1) be-comes(3) the(4) light(5) = 5 \u2713\n\nLet me go with option 2 or 3, both are nice. I'll provide one clean haiku and maybe offer an alternative.\n\nActually, let me just give one good one. Option 3 feels more poetic and evocative.\n\nLet me verify option 3 once more:\n- \"Fingers on the keys\" - Fin-gers(2) on(3) the(4) keys(5) = 5 \u2713\n- \"Building worlds from empty void\" - Build-ing(2) worlds(3) from(4) emp-ty(6) void(7) = 7 \u2713\n- \"Code becomes the light\" - Code(1) be-comes(3) the(4) light(5) = 5 \u2713\n\nThat works well. I could also provide a simpler one focused on a different aspect of programming.\n\nI'll give a haiku with a clean delivery. Let me also think about a second option to make it more useful, or just stick with one well-crafted one.\n\nI'll provide one haiku and keep it concise."
								}
							]
						},
						"finish_reason": "stop"
					}
				],
				"created": 1780336062,
				"model": "MiniMax-M3",
				"object": "chat.completion",
				"usage": {
					"total_tokens": 912,
					"prompt_tokens": 183,
					"completion_tokens": 729,
					"total_characters": 0,
					"prompt_tokens_details": {
						"cached_tokens": 114
					}
				},
				"input_sensitive": false,
				"output_sensitive": false,
				"base_resp": {
					"status_code": 0,
					"status_msg": ""
				},
				"input_sensitive_type": 0,
				"output_sensitive_type": 0,
				"output_sensitive_int": 0,
				"gatewayMetadata": {
					"keySource": "Unified"
				}
			},
			"code_snippets": [
				{
					"label": "typescript",
					"language": "typescript",
					"code": "const response = await env.AI.run(\n  'minimax/m3',\n  {\n    max_tokens: 2048,\n    messages: [{ content: 'Write a haiku about programming.', role: 'user' }],\n    temperature: 0.9,\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 $CLOUDFLARE_API_TOKEN\" \\\n  --header \"Content-Type: application/json\" \\\n  --data '{\n  \"model\": \"minimax/m3\",\n  \"max_tokens\": 2048,\n  \"messages\": [\n    {\n      \"content\": \"Write a haiku about programming.\",\n      \"role\": \"user\"\n    }\n  ],\n  \"temperature\": 0.9\n}'"
				}
			]
		}
	],
	"default_example": null,
	"code_snippets": [],
	"supports_async": false,
	"zdr": true,
	"zdr_comment": null,
	"external_info": "https://www.minimax.io/blog/minimax-m3",
	"terms": "https://www.minimaxi.com/terms",
	"cover_image_url": "https://pub-26f1392c1b674324be6786695bd72257.r2.dev/minimax/m3.png",
	"metadata": {
		"Architecture": "Transformer",
		"fedrampAvailable": "true"
	},
	"request_formats": [
		"chat-completions",
		"anthropic-messages"
	],
	"providers": null,
	"provider_details": [
		{
			"id": "minimax",
			"pricing": {
				"under_512k_per_1m_input_tokens": 0.3,
				"under_512k_per_1m_output_tokens": 1.2,
				"under_512k_per_1m_input_cached_tokens": 0.06,
				"over_512k_per_1m_input_tokens": 0.6,
				"over_512k_per_1m_output_tokens": 2.4,
				"over_512k_per_1m_input_cached_tokens": 0.12
			}
		}
	],
	"banner": null,
	"created_at": "2026-06-01 20:11:36",
	"schema": {
		"input": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"messages": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"role": {
										"type": "string",
										"enum": [
											"system",
											"user",
											"assistant",
											"tool"
										]
									},
									"name": {
										"type": "string"
									},
									"content": {
										"anyOf": [
											{
												"type": "string"
											},
											{
												"type": "array",
												"items": {
													"anyOf": [
														{
															"type": "object",
															"properties": {
																"type": {
																	"type": "string",
																	"const": "text"
																},
																"text": {
																	"type": "string"
																}
															},
															"required": [
																"type",
																"text"
															],
															"additionalProperties": false
														},
														{
															"type": "object",
															"properties": {
																"type": {
																	"type": "string",
																	"const": "image_url"
																},
																"image_url": {
																	"type": "object",
																	"properties": {
																		"url": {
																			"type": "string"
																		}
																	},
																	"required": [
																		"url"
																	],
																	"additionalProperties": false
																}
															},
															"required": [
																"type",
																"image_url"
															],
															"additionalProperties": false
														}
													]
												}
											}
										]
									},
									"tool_calls": {
										"type": "array",
										"items": {
											"type": "object",
											"properties": {
												"id": {
													"type": "string"
												},
												"type": {
													"type": "string",
													"const": "function"
												},
												"function": {
													"type": "object",
													"properties": {
														"name": {
															"type": "string"
														},
														"arguments": {
															"type": "string"
														}
													},
													"required": [
														"name",
														"arguments"
													],
													"additionalProperties": false
												}
											},
											"required": [
												"id",
												"type",
												"function"
											],
											"additionalProperties": false
										}
									}
								},
								"required": [
									"role",
									"content"
								],
								"additionalProperties": {}
							}
						},
						"temperature": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"max_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"max_completion_tokens": {
							"type": "number",
							"exclusiveMinimum": 0
						},
						"top_p": {
							"type": "number",
							"minimum": 0,
							"maximum": 1
						},
						"stream": {
							"type": "boolean"
						},
						"stream_options": {
							"type": "object",
							"properties": {
								"include_usage": {
									"type": "boolean"
								}
							},
							"additionalProperties": false
						},
						"tools": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"type": {
										"type": "string",
										"const": "function"
									},
									"function": {
										"type": "object",
										"properties": {
											"name": {
												"type": "string"
											},
											"description": {
												"type": "string"
											},
											"parameters": {}
										},
										"required": [
											"name",
											"description",
											"parameters"
										],
										"additionalProperties": false
									}
								},
								"required": [
									"type",
									"function"
								],
								"additionalProperties": false
							}
						},
						"tool_choice": {
							"type": "string",
							"enum": [
								"none",
								"auto"
							]
						},
						"response_format": {
							"type": "object",
							"properties": {
								"type": {
									"type": "string",
									"const": "json_schema"
								},
								"json_schema": {
									"type": "object",
									"properties": {
										"name": {
											"type": "string",
											"maxLength": 64
										},
										"description": {
											"type": "string"
										},
										"schema": {
											"type": "object",
											"properties": {
												"type": {
													"type": "string",
													"const": "object"
												},
												"properties": {}
											},
											"required": [
												"type",
												"properties"
											],
											"additionalProperties": false
										}
									},
									"required": [
										"name",
										"schema"
									],
									"additionalProperties": false
								}
							},
							"required": [
								"type",
								"json_schema"
							],
							"additionalProperties": false
						},
						"mask_sensitive_info": {
							"type": "boolean"
						}
					},
					"required": [
						"messages"
					],
					"additionalProperties": false,
					"title": "Chat Completions"
				},
				{
					"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"
				}
			]
		},
		"output": {
			"$schema": "https://json-schema.org/draft/2020-12/schema",
			"oneOf": [
				{
					"type": "object",
					"properties": {
						"id": {
							"type": "string"
						},
						"choices": {
							"type": "array",
							"items": {
								"type": "object",
								"properties": {
									"index": {
										"type": "number"
									},
									"message": {
										"type": "object",
										"properties": {
											"role": {
												"type": "string",
												"const": "assistant"
											},
											"content": {
												"type": "string"
											},
											"tool_calls": {
												"type": "array",
												"items": {
													"type": "object",
													"properties": {
														"id": {
															"type": "string"
														},
														"type": {
															"type": "string",
															"const": "function"
														},
														"function": {
															"type": "object",
															"properties": {
																"name": {
																	"type": "string"
																},
																"arguments": {
																	"type": "string"
																}
															},
															"required": [
																"name",
																"arguments"
															],
															"additionalProperties": false
														}
													},
													"required": [
														"id",
														"type",
														"function"
													],
													"additionalProperties": false
												}
											}
										},
										"required": [
											"role",
											"content"
										],
										"additionalProperties": {}
									},
									"finish_reason": {
										"type": "string",
										"enum": [
											"stop",
											"length",
											"tool_calls"
										]
									}
								},
								"required": [
									"index",
									"message",
									"finish_reason"
								],
								"additionalProperties": {}
							}
						},
						"created": {
							"type": "number"
						},
						"model": {
							"type": "string"
						},
						"object": {
							"type": "string",
							"enum": [
								"chat.completion",
								"chat.completion.chunk"
							]
						},
						"usage": {
							"type": "object",
							"properties": {
								"total_tokens": {
									"type": "number"
								},
								"prompt_tokens": {
									"type": "number"
								},
								"completion_tokens": {
									"type": "number"
								}
							},
							"required": [
								"total_tokens",
								"prompt_tokens",
								"completion_tokens"
							],
							"additionalProperties": {}
						},
						"input_sensitive": {
							"type": "boolean"
						},
						"output_sensitive": {
							"type": "boolean"
						},
						"base_resp": {
							"type": "object",
							"properties": {
								"status_code": {
									"type": "number"
								},
								"status_msg": {
									"type": "string"
								}
							},
							"required": [
								"status_code",
								"status_msg"
							],
							"additionalProperties": false
						}
					},
					"required": [
						"id",
						"choices",
						"created",
						"model",
						"object"
					],
					"additionalProperties": {},
					"title": "Chat Completions"
				},
				{
					"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"
				}
			]
		}
	}
}