openapi: 3.2.0 info: title: OpenAI Chat API description: The OpenAI REST API. Please see https://platform.openai.com/docs/api-reference for more details. version: 2.3.0 termsOfService: https://openai.com/policies/terms-of-use contact: name: OpenAI Support url: https://help.openai.com/ license: name: MIT identifier: MIT servers: - url: https://api.openai.com/v1 security: - ApiKeyAuth: [] tags: - name: Chat Completions description: Given a list of messages comprising a conversation, the model will return a response. paths: /chat/completions: get: operationId: listChatCompletions tags: - Chat Completions summary: List Chat Completions description: 'List stored Chat Completions. Only Chat Completions that have been stored with the `store` parameter set to `true` will be returned.' parameters: - name: model in: query description: The model used to generate the Chat Completions. required: false schema: type: string - name: metadata in: query description: 'A list of metadata keys to filter the Chat Completions by. Example: `metadata[key1]=value1&metadata[key2]=value2` ' required: false schema: $ref: '#/components/schemas/Metadata' - name: after in: query description: Identifier for the last chat completion from the previous pagination request. required: false schema: type: string - name: limit in: query description: Number of Chat Completions to retrieve. required: false schema: type: integer default: 20 - name: order in: query description: Sort order for Chat Completions by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`. required: false schema: type: string enum: - asc - desc default: asc responses: '200': description: A list of Chat Completions content: application/json: schema: $ref: '#/components/schemas/ChatCompletionList' x-oaiMeta: group: chat path: list examples: request: curl: "curl https://api.openai.com/v1/chat/completions \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"Content-Type: application/json\"\n" python: 'from openai import OpenAI client = OpenAI() completions = client.chat.completions.list() print(completions) ' response: "{\n \"object\": \"list\",\n \"data\": [\n {\n \"object\": \"chat.completion\",\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"model\": \"gpt-6-astra\",\n \"created\": 1738960610,\n \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n \"tool_choice\": null,\n \"usage\": {\n \"total_tokens\": 31,\n \"completion_tokens\": 18,\n \"prompt_tokens\": 13\n },\n \"seed\": 4944116822809979520,\n \"top_p\": 1.0,\n \"temperature\": 1.0,\n \"presence_penalty\": 0.0,\n \"frequency_penalty\": 0.0,\n \"system_fingerprint\": \"fp_50cad350e4\",\n \"input_user\": null,\n \"service_tier\": \"default\",\n \"tools\": null,\n \"metadata\": {},\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"content\": \"Mind of circuits hum, \\nLearning patterns in silence— \\nFuture's quiet spark.\",\n \"role\": \"assistant\",\n \"tool_calls\": null,\n \"function_call\": null\n },\n \"finish_reason\": \"stop\",\n \"logprobs\": null\n }\n ],\n \"response_format\": null\n }\n ],\n \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"has_more\": false\n}\n" post: operationId: createChatCompletion tags: - Chat Completions summary: Create chat completion description: '**Starting a new project?** We recommend trying Responses to take advantage of the latest OpenAI platform features. Compare Chat Completions with Responses. --- Creates a model response for the given chat conversation. Learn more in the text generation, vision, and audio guides. Parameter support can differ depending on the model used to generate the response, particularly for newer reasoning models. Parameters that are only supported for reasoning models are noted below. For the current state of unsupported parameters in reasoning models, refer to the reasoning guide. Returns a chat completion object, or a streamed sequence of chat completion chunk objects if the request is streamed.' requestBody: required: true content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionRequest' responses: '200': description: OK content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' text/event-stream: schema: $ref: '#/components/schemas/CreateChatCompletionStreamResponse' '429': $ref: '#/components/responses/InferenceRateLimited' '503': $ref: '#/components/responses/InferenceServiceUnavailable' x-oaiMeta: group: chat path: create examples: - title: Default request: curl: "curl https://api.openai.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -d '{\n \"model\": \"gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"developer\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ]\n }'\n" python: "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n model=\"gpt-6-astra\",\n messages=[\n {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ]\n)\n\nprint(completion.choices[0].message)\n" javascript: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n messages: [{ role: \"developer\", content: \"You are a helpful assistant.\" }],\n model: \"gpt-6-astra\",\n store: true,\n });\n\n console.log(completion.choices[0]);\n}\n\nmain();\n" csharp: "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n model: \"gpt-6-astra\",\n apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList messages =\n[\n new SystemChatMessage(\"You are a helpful assistant.\"),\n new UserChatMessage(\"Hello!\")\n];\n\nChatCompletion completion = client.CompleteChat(messages);\n\nConsole.WriteLine(completion.Content[0].Text);\n" response: "{\n \"id\": \"chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT\",\n \"object\": \"chat.completion\",\n \"created\": 1741569952,\n \"model\": \"gpt-6-astra\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Hello! How can I assist you today?\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 19,\n \"completion_tokens\": 10,\n \"total_tokens\": 29,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\"\n}\n" - title: Image input request: curl: "curl https://api.openai.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -d '{\n \"model\": \"gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": [\n {\n \"type\": \"text\",\n \"text\": \"What is in this image?\"\n },\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"\n }\n }\n ]\n }\n ],\n \"max_tokens\": 300\n }'\n" python: "from openai import OpenAI\n\nclient = OpenAI()\n\nresponse = client.chat.completions.create(\n model=\"gpt-6-astra\",\n messages=[\n {\n \"role\": \"user\",\n \"content\": [\n {\"type\": \"text\", \"text\": \"What's in this image?\"},\n {\n \"type\": \"image_url\",\n \"image_url\": {\n \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n }\n },\n ],\n }\n ],\n max_tokens=300,\n)\n\nprint(response.choices[0])\n" javascript: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n const response = await openai.chat.completions.create({\n model: \"gpt-6-astra\",\n messages: [\n {\n role: \"user\",\n content: [\n { type: \"text\", text: \"What's in this image?\" },\n {\n type: \"image_url\",\n image_url: {\n \"url\": \"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\",\n },\n }\n ],\n },\n ],\n });\n console.log(response.choices[0]);\n}\nmain();\n" csharp: "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n model: \"gpt-6-astra\",\n apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList messages =\n[\n new UserChatMessage(\n [\n ChatMessageContentPart.CreateTextPart(\"What's in this image?\"),\n ChatMessageContentPart.CreateImagePart(new Uri(\"https://upload.wikimedia.org/wikipedia/commons/thumb/d/dd/Gfp-wisconsin-madison-the-nature-boardwalk.jpg/2560px-Gfp-wisconsin-madison-the-nature-boardwalk.jpg\"))\n ])\n];\n\nChatCompletion completion = client.CompleteChat(messages);\n\nConsole.WriteLine(completion.Content[0].Text);\n" response: "{\n \"id\": \"chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG\",\n \"object\": \"chat.completion\",\n \"created\": 1741570283,\n \"model\": \"gpt-6-astra\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1117,\n \"completion_tokens\": 46,\n \"total_tokens\": 1163,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\"\n}\n" - title: Streaming request: curl: "curl https://api.openai.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -d '{\n \"model\": \"gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"developer\",\n \"content\": \"You are a helpful assistant.\"\n },\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ],\n \"stream\": true\n }'\n" python: "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n model=\"gpt-6-astra\",\n messages=[\n {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ],\n stream=True\n)\n\nfor chunk in completion:\n print(chunk.choices[0].delta)\n" javascript: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n model: \"gpt-6-astra\",\n messages: [\n {\"role\": \"developer\", \"content\": \"You are a helpful assistant.\"},\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ],\n stream: true,\n });\n\n for await (const chunk of completion) {\n console.log(chunk.choices[0].delta.content);\n }\n}\n\nmain();\n" csharp: "using System;\nusing System.ClientModel;\nusing System.Collections.Generic;\nusing System.Threading.Tasks;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n model: \"gpt-6-astra\",\n apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList messages =\n[\n new SystemChatMessage(\"You are a helpful assistant.\"),\n new UserChatMessage(\"Hello!\")\n];\n\nAsyncCollectionResult completionUpdates = client.CompleteChatStreamingAsync(messages);\n\nawait foreach (StreamingChatCompletionUpdate completionUpdate in completionUpdates)\n{\n if (completionUpdate.ContentUpdate.Count > 0)\n {\n Console.Write(completionUpdate.ContentUpdate[0].Text);\n }\n}\n" response: '{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}]} {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}]} .... {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]} ' - title: Functions request: curl: "curl https://api.openai.com/v1/chat/completions \\\n-H \"Content-Type: application/json\" \\\n-H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n-d '{\n \"model\": \"gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"What is the weather like in Boston today?\"\n }\n ],\n \"tools\": [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"description\": \"Get the current weather in a given location\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city and state, e.g. San Francisco, CA\"\n },\n \"unit\": {\n \"type\": \"string\",\n \"enum\": [\"celsius\", \"fahrenheit\"]\n }\n },\n \"required\": [\"location\"]\n }\n }\n }\n ],\n \"tool_choice\": \"auto\"\n}'\n" python: "from openai import OpenAI\nclient = OpenAI()\n\ntools = [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"description\": \"Get the current weather in a given location\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city and state, e.g. San Francisco, CA\",\n },\n \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n },\n \"required\": [\"location\"],\n },\n }\n }\n]\nmessages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}]\ncompletion = client.chat.completions.create(\n model=\"gpt-6-astra\",\n messages=messages,\n tools=tools,\n tool_choice=\"auto\"\n)\n\nprint(completion)\n" javascript: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n const messages = [{\"role\": \"user\", \"content\": \"What's the weather like in Boston today?\"}];\n const tools = [\n {\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"description\": \"Get the current weather in a given location\",\n \"parameters\": {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city and state, e.g. San Francisco, CA\",\n },\n \"unit\": {\"type\": \"string\", \"enum\": [\"celsius\", \"fahrenheit\"]},\n },\n \"required\": [\"location\"],\n },\n }\n }\n ];\n\n const response = await openai.chat.completions.create({\n model: \"gpt-6-astra\",\n messages: messages,\n tools: tools,\n tool_choice: \"auto\",\n });\n\n console.log(response);\n}\n\nmain();\n" csharp: "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n model: \"gpt-6-astra\",\n apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nChatTool getCurrentWeatherTool = ChatTool.CreateFunctionTool(\n functionName: \"get_current_weather\",\n functionDescription: \"Get the current weather in a given location\",\n functionParameters: BinaryData.FromString(\"\"\"\n {\n \"type\": \"object\",\n \"properties\": {\n \"location\": {\n \"type\": \"string\",\n \"description\": \"The city and state, e.g. San Francisco, CA\"\n },\n \"unit\": {\n \"type\": \"string\",\n \"enum\": [ \"celsius\", \"fahrenheit\" ]\n }\n },\n \"required\": [ \"location\" ]\n }\n \"\"\")\n);\n\nList messages =\n[\n new UserChatMessage(\"What's the weather like in Boston today?\"),\n];\n\nChatCompletionOptions options = new()\n{\n Tools =\n {\n getCurrentWeatherTool\n },\n ToolChoice = ChatToolChoice.CreateAutoChoice(),\n};\n\nChatCompletion completion = client.CompleteChat(messages, options);\n" response: "{\n \"id\": \"chatcmpl-abc123\",\n \"object\": \"chat.completion\",\n \"created\": 1699896916,\n \"model\": \"gpt-6-astra\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": null,\n \"tool_calls\": [\n {\n \"id\": \"call_abc123\",\n \"type\": \"function\",\n \"function\": {\n \"name\": \"get_current_weather\",\n \"arguments\": \"{\\n\\\"location\\\": \\\"Boston, MA\\\"\\n}\"\n }\n }\n ]\n },\n \"logprobs\": null,\n \"finish_reason\": \"tool_calls\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 82,\n \"completion_tokens\": 17,\n \"total_tokens\": 99,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n }\n}\n" - title: Logprobs request: curl: "curl https://api.openai.com/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -d '{\n \"model\": \"gpt-6-astra\",\n \"messages\": [\n {\n \"role\": \"user\",\n \"content\": \"Hello!\"\n }\n ],\n \"reasoning_effort\": \"none\",\n \"logprobs\": true,\n \"top_logprobs\": 2\n }'\n" python: "from openai import OpenAI\nclient = OpenAI()\n\ncompletion = client.chat.completions.create(\n model=\"gpt-6-astra\",\n messages=[\n {\"role\": \"user\", \"content\": \"Hello!\"}\n ],\n reasoning_effort=\"none\",\n logprobs=True,\n top_logprobs=2\n)\n\nprint(completion.choices[0].message)\nprint(completion.choices[0].logprobs)\n" javascript: "import OpenAI from \"openai\";\n\nconst openai = new OpenAI();\n\nasync function main() {\n const completion = await openai.chat.completions.create({\n messages: [{ role: \"user\", content: \"Hello!\" }],\n model: \"gpt-6-astra\",\n reasoning_effort: \"none\",\n logprobs: true,\n top_logprobs: 2,\n });\n\n console.log(completion.choices[0]);\n}\n\nmain();\n" csharp: "using System;\nusing System.Collections.Generic;\n\nusing OpenAI.Chat;\n\nChatClient client = new(\n model: \"gpt-6-astra\",\n apiKey: Environment.GetEnvironmentVariable(\"OPENAI_API_KEY\")\n);\n\nList messages =\n[\n new UserChatMessage(\"Hello!\")\n];\n\nChatCompletionOptions options = new()\n{\n ReasoningEffortLevel = ChatReasoningEffortLevel.None,\n IncludeLogProbabilities = true,\n TopLogProbabilityCount = 2\n};\n\nChatCompletion completion = client.CompleteChat(messages, options);\n\nConsole.WriteLine(completion.Content[0].Text);\n" response: "{\n \"id\": \"chatcmpl-123\",\n \"object\": \"chat.completion\",\n \"created\": 1702685778,\n \"model\": \"gpt-6-astra\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"Hello! How can I assist you today?\"\n },\n \"logprobs\": {\n \"content\": [\n {\n \"token\": \"Hello\",\n \"logprob\": -0.31725305,\n \"bytes\": [72, 101, 108, 108, 111],\n \"top_logprobs\": [\n {\n \"token\": \"Hello\",\n \"logprob\": -0.31725305,\n \"bytes\": [72, 101, 108, 108, 111]\n },\n {\n \"token\": \"Hi\",\n \"logprob\": -1.3190403,\n \"bytes\": [72, 105]\n }\n ]\n },\n {\n \"token\": \"!\",\n \"logprob\": -0.02380986,\n \"bytes\": [\n 33\n ],\n \"top_logprobs\": [\n {\n \"token\": \"!\",\n \"logprob\": -0.02380986,\n \"bytes\": [33]\n },\n {\n \"token\": \" there\",\n \"logprob\": -3.787621,\n \"bytes\": [32, 116, 104, 101, 114, 101]\n }\n ]\n },\n {\n \"token\": \" How\",\n \"logprob\": -0.000054669687,\n \"bytes\": [32, 72, 111, 119],\n \"top_logprobs\": [\n {\n \"token\": \" How\",\n \"logprob\": -0.000054669687,\n \"bytes\": [32, 72, 111, 119]\n },\n {\n \"token\": \"<|end|>\",\n \"logprob\": -10.953937,\n \"bytes\": null\n }\n ]\n },\n {\n \"token\": \" can\",\n \"logprob\": -0.015801601,\n \"bytes\": [32, 99, 97, 110],\n \"top_logprobs\": [\n {\n \"token\": \" can\",\n \"logprob\": -0.015801601,\n \"bytes\": [32, 99, 97, 110]\n },\n {\n \"token\": \" may\",\n \"logprob\": -4.161023,\n \"bytes\": [32, 109, 97, 121]\n }\n ]\n },\n {\n \"token\": \" I\",\n \"logprob\": -3.7697225e-6,\n \"bytes\": [\n 32,\n 73\n ],\n \"top_logprobs\": [\n {\n \"token\": \" I\",\n \"logprob\": -3.7697225e-6,\n \"bytes\": [32, 73]\n },\n {\n \"token\": \" assist\",\n \"logprob\": -13.596657,\n \"bytes\": [32, 97, 115, 115, 105, 115, 116]\n }\n ]\n },\n {\n \"token\": \" assist\",\n \"logprob\": -0.04571125,\n \"bytes\": [32, 97, 115, 115, 105, 115, 116],\n \"top_logprobs\": [\n {\n \"token\": \" assist\",\n \"logprob\": -0.04571125,\n \"bytes\": [32, 97, 115, 115, 105, 115, 116]\n },\n {\n \"token\": \" help\",\n \"logprob\": -3.1089056,\n \"bytes\": [32, 104, 101, 108, 112]\n }\n ]\n },\n {\n \"token\": \" you\",\n \"logprob\": -5.4385737e-6,\n \"bytes\": [32, 121, 111, 117],\n \"top_logprobs\": [\n {\n \"token\": \" you\",\n \"logprob\": -5.4385737e-6,\n \"bytes\": [32, 121, 111, 117]\n },\n {\n \"token\": \" today\",\n \"logprob\": -12.807695,\n \"bytes\": [32, 116, 111, 100, 97, 121]\n }\n ]\n },\n {\n \"token\": \" today\",\n \"logprob\": -0.0040071653,\n \"bytes\": [32, 116, 111, 100, 97, 121],\n \"top_logprobs\": [\n {\n \"token\": \" today\",\n \"logprob\": -0.0040071653,\n \"bytes\": [32, 116, 111, 100, 97, 121]\n },\n {\n \"token\": \"?\",\n \"logprob\": -5.5247097,\n \"bytes\": [63]\n }\n ]\n },\n {\n \"token\": \"?\",\n \"logprob\": -0.0008108172,\n \"bytes\": [63],\n \"top_logprobs\": [\n {\n \"token\": \"?\",\n \"logprob\": -0.0008108172,\n \"bytes\": [63]\n },\n {\n \"token\": \"?\\n\",\n \"logprob\": -7.184561,\n \"bytes\": [63, 10]\n }\n ]\n }\n ]\n },\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 9,\n \"completion_tokens\": 9,\n \"total_tokens\": 18,\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"system_fingerprint\": null\n}\n" /chat/completions/{completion_id}: get: operationId: getChatCompletion tags: - Chat Completions summary: Get chat completion description: 'Get a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` will be returned.' parameters: - in: path name: completion_id required: true schema: type: string description: The ID of the chat completion to retrieve. responses: '200': description: A chat completion content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' x-oaiMeta: group: chat examples: request: curl: "curl https://api.openai.com/v1/chat/completions/chatcmpl-abc123 \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"Content-Type: application/json\"\n" python: 'from openai import OpenAI client = OpenAI() completions = client.chat.completions.list() first_id = completions[0].id first_completion = client.chat.completions.retrieve(completion_id=first_id) print(first_completion) ' response: "{\n \"object\": \"chat.completion\",\n \"id\": \"chatcmpl-abc123\",\n \"model\": \"gpt-6-astra\",\n \"created\": 1738960610,\n \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n \"tool_choice\": null,\n \"usage\": {\n \"total_tokens\": 31,\n \"completion_tokens\": 18,\n \"prompt_tokens\": 13\n },\n \"seed\": 4944116822809979520,\n \"top_p\": 1.0,\n \"temperature\": 1.0,\n \"presence_penalty\": 0.0,\n \"frequency_penalty\": 0.0,\n \"system_fingerprint\": \"fp_50cad350e4\",\n \"input_user\": null,\n \"service_tier\": \"default\",\n \"tools\": null,\n \"metadata\": {},\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"content\": \"Mind of circuits hum, \\nLearning patterns in silence— \\nFuture's quiet spark.\",\n \"role\": \"assistant\",\n \"tool_calls\": null,\n \"function_call\": null\n },\n \"finish_reason\": \"stop\",\n \"logprobs\": null\n }\n ],\n \"response_format\": null\n}\n" post: operationId: updateChatCompletion tags: - Chat Completions summary: Update chat completion description: 'Modify a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` can be modified. Currently, the only supported modification is to update the `metadata` field.' parameters: - in: path name: completion_id required: true schema: type: string description: The ID of the chat completion to update. requestBody: required: true content: application/json: schema: type: object required: - metadata properties: metadata: $ref: '#/components/schemas/Metadata' responses: '200': description: A chat completion content: application/json: schema: $ref: '#/components/schemas/CreateChatCompletionResponse' x-oaiMeta: group: chat examples: request: curl: "curl -X POST https://api.openai.com/v1/chat/completions/chat_abc123 \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"Content-Type: application/json\" \\\n -d '{\"metadata\": {\"foo\": \"bar\"}}'\n" python: 'from openai import OpenAI client = OpenAI() completions = client.chat.completions.list() first_id = completions[0].id updated_completion = client.chat.completions.update(completion_id=first_id, request_body={"metadata": {"foo": "bar"}}) print(updated_completion) ' response: "{\n \"object\": \"chat.completion\",\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"model\": \"gpt-6-astra\",\n \"created\": 1738960610,\n \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n \"tool_choice\": null,\n \"usage\": {\n \"total_tokens\": 31,\n \"completion_tokens\": 18,\n \"prompt_tokens\": 13\n },\n \"seed\": 4944116822809979520,\n \"top_p\": 1.0,\n \"temperature\": 1.0,\n \"presence_penalty\": 0.0,\n \"frequency_penalty\": 0.0,\n \"system_fingerprint\": \"fp_50cad350e4\",\n \"input_user\": null,\n \"service_tier\": \"default\",\n \"tools\": null,\n \"metadata\": {\n \"foo\": \"bar\"\n },\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"content\": \"Mind of circuits hum, \\nLearning patterns in silence— \\nFuture's quiet spark.\",\n \"role\": \"assistant\",\n \"tool_calls\": null,\n \"function_call\": null\n },\n \"finish_reason\": \"stop\",\n \"logprobs\": null\n }\n ],\n \"response_format\": null\n}\n" delete: operationId: deleteChatCompletion tags: - Chat Completions summary: Delete chat completion description: 'Delete a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` can be deleted.' parameters: - in: path name: completion_id required: true schema: type: string description: The ID of the chat completion to delete. responses: '200': description: The chat completion was deleted successfully. content: application/json: schema: $ref: '#/components/schemas/ChatCompletionDeleted' x-oaiMeta: group: chat examples: request: curl: "curl -X DELETE https://api.openai.com/v1/chat/completions/chat_abc123 \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"Content-Type: application/json\"\n" python: 'from openai import OpenAI client = OpenAI() completions = client.chat.completions.list() first_id = completions[0].id delete_response = client.chat.completions.delete(completion_id=first_id) print(delete_response) ' response: "{\n \"object\": \"chat.completion.deleted\",\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"deleted\": true\n}\n" /chat/completions/{completion_id}/messages: get: operationId: getChatCompletionMessages tags: - Chat Completions summary: Get chat messages description: 'Get the messages in a stored chat completion. Only Chat Completions that have been created with the `store` parameter set to `true` will be returned.' parameters: - in: path name: completion_id required: true schema: type: string description: The ID of the chat completion to retrieve messages from. - name: after in: query description: Identifier for the last message from the previous pagination request. required: false schema: type: string - name: limit in: query description: Number of messages to retrieve. required: false schema: type: integer default: 20 - name: order in: query description: Sort order for messages by timestamp. Use `asc` for ascending order or `desc` for descending order. Defaults to `asc`. required: false schema: type: string enum: - asc - desc default: asc responses: '200': description: A list of messages content: application/json: schema: $ref: '#/components/schemas/ChatCompletionMessageList' x-oaiMeta: group: chat examples: request: curl: "curl https://api.openai.com/v1/chat/completions/chat_abc123/messages \\\n -H \"Authorization: Bearer $OPENAI_API_KEY\" \\\n -H \"Content-Type: application/json\"\n" python: 'from openai import OpenAI client = OpenAI() completions = client.chat.completions.list() first_id = completions[0].id first_completion = client.chat.completions.retrieve(completion_id=first_id) messages = client.chat.completions.messages.list(completion_id=first_id) print(messages) ' response: "{\n \"object\": \"list\",\n \"data\": [\n {\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"role\": \"user\",\n \"content\": \"write a haiku about ai\",\n \"name\": null,\n \"content_parts\": null\n }\n ],\n \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"has_more\": false\n}\n" components: schemas: ModerationMode: type: string enum: - score - block ResponseFormatText: type: object title: Text description: 'Default response format. Used to generate text responses. ' properties: type: type: string description: The type of response format being defined. Always `text`. enum: - text x-stainless-const: true required: - type ChatCompletionDeleted: type: object properties: object: type: string description: The type of object being deleted. enum: - chat.completion.deleted x-stainless-const: true id: type: string description: The ID of the chat completion that was deleted. deleted: type: boolean description: Whether the chat completion was deleted. required: - object - id - deleted ChatCompletionRequestMessage: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestDeveloperMessage' - $ref: '#/components/schemas/ChatCompletionRequestSystemMessage' - $ref: '#/components/schemas/ChatCompletionRequestUserMessage' - $ref: '#/components/schemas/ChatCompletionRequestAssistantMessage' - $ref: '#/components/schemas/ChatCompletionRequestToolMessage' - $ref: '#/components/schemas/ChatCompletionRequestFunctionMessage' discriminator: propertyName: role ParallelToolCalls: description: Whether to enable [parallel function calling](https://developers.openai.com/api/docs/guides/function-calling#parallel-function-calling) during tool use. type: boolean default: true WebSearchContextSize: type: string description: "High level guidance for the amount of context window space to use for the \nsearch. One of `low`, `medium`, or `high`. `medium` is the default.\n" enum: - low - medium - high default: medium ChatCompletionTool: type: object title: Function tool description: 'A function tool that can be used to generate a response. ' properties: type: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. x-stainless-const: true function: $ref: '#/components/schemas/FunctionObject' required: - type - function StopConfiguration: description: 'Not supported with latest reasoning models `o3` and `o4-mini`. Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. ' default: null nullable: true oneOf: - type: string default: <|endoftext|> example: ' ' nullable: true - type: array minItems: 1 maxItems: 4 items: type: string example: '["\n"]' ChatCompletionMessageToolCalls: type: array description: The tool calls generated by the model, such as function calls. items: oneOf: - $ref: '#/components/schemas/ChatCompletionMessageToolCall' - $ref: '#/components/schemas/ChatCompletionMessageCustomToolCall' discriminator: propertyName: type PredictionContent: type: object title: Static Content description: 'Static predicted output content, such as the content of a text file that is being regenerated. ' required: - type - content properties: type: type: string enum: - content description: 'The type of the predicted content you want to provide. This type is currently always `content`. ' x-stainless-const: true content: description: 'The content that should be matched when generating a model response. If generated tokens would match this content, the entire model response can be returned much more quickly. ' oneOf: - type: string title: Text content description: 'The content used for a Predicted Output. This is often the text of a file you are regenerating with minor changes. ' - type: array description: An array of content parts with a defined type. Supported options differ based on the [model](https://developers.openai.com/api/docs/models) being used to generate the response. Can contain text inputs. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' minItems: 1 VoiceIdsShared: example: ash anyOf: - type: string - type: string enum: - alloy - ash - ballad - coral - echo - sage - shimmer - verse - marin - cedar ModerationInputType: type: string enum: - text - image FunctionObject: type: object properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: '#/components/schemas/FunctionParameters' strict: anyOf: - type: boolean default: false description: Whether to enable strict schema adherence when generating the function call. If set to true, the model will follow the exact schema defined in the `parameters` field. Only a subset of JSON Schema is supported when `strict` is `true`. Learn more about Structured Outputs in the [function calling guide](https://developers.openai.com/api/docs/guides/function-calling). - type: 'null' required: - name ChatCompletionToolChoiceOption: description: 'Controls which (if any) tool is called by the model. `none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. Specifying a particular tool via `{"type": "function", "function": {"name": "my_function"}}` forces the model to call that tool. `none` is the default when no tools are present. `auto` is the default if tools are present. ' oneOf: - type: string title: Tool choice mode description: '`none` means the model will not call any tool and instead generates a message. `auto` means the model can pick between generating a message or calling one or more tools. `required` means the model must call one or more tools. ' enum: - none - auto - required - $ref: '#/components/schemas/ChatCompletionAllowedToolsChoice' - $ref: '#/components/schemas/ChatCompletionNamedToolChoice' - $ref: '#/components/schemas/ChatCompletionNamedToolChoiceCustom' PromptCacheTTLEnum: type: string enum: - 30m ChatCompletionRequestUserMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartImage' - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartAudio' - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartFile' ChatCompletionRequestMessageContentPartFile: type: object title: File content part description: 'Learn about [file inputs](https://developers.openai.com/api/docs/guides/text) for text generation. ' properties: type: type: string enum: - file description: The type of the content part. Always `file`. x-stainless-const: true file: type: object properties: filename: type: string description: 'The name of the file, used when passing the file to the model as a string. ' file_data: type: string description: 'The base64 encoded file data, used when passing the file to the model as a string. ' file_id: type: string description: 'The ID of an uploaded file to use as input. ' prompt_cache_breakpoint: $ref: '#/components/schemas/PromptCacheBreakpointParam' required: - type - file ErrorResponse: type: object properties: error: $ref: '#/components/schemas/Error' required: - error ChatCompletionStreamOptions: anyOf: - description: 'Options for streaming response. Only set this when you set `stream: true`. ' type: object properties: include_usage: type: boolean description: 'If set, an additional chunk will be streamed before the `data: [DONE]` message. The `usage` field on this chunk shows the token usage statistics for the entire request, and the `choices` field will always be an empty array. All other chunks will also include a `usage` field, but with a null value. **NOTE:** If the stream is interrupted, you may not receive the final usage chunk which contains the total token usage for the request. ' include_obfuscation: type: boolean description: 'When true, stream obfuscation will be enabled. Stream obfuscation adds random characters to an `obfuscation` field on streaming delta events to normalize payload sizes as a mitigation to certain side-channel attacks. These obfuscation fields are included by default, but add a small amount of overhead to the data stream. You can set `include_obfuscation` to false to optimize for bandwidth if you trust the network links between your application and the OpenAI API. ' - type: 'null' ChatCompletionAllowedToolsChoice: type: object title: Allowed tools description: 'Constrains the tools available to the model to a pre-defined set. ' properties: type: type: string enum: - allowed_tools description: Allowed tool configuration type. Always `allowed_tools`. x-stainless-const: true allowed_tools: $ref: '#/components/schemas/ChatCompletionAllowedTools' required: - type - allowed_tools ChatCompletionRequestFunctionMessage: type: object title: Function message deprecated: true properties: role: type: string enum: - function description: The role of the messages author, in this case `function`. x-stainless-const: true content: anyOf: - type: string description: The contents of the function message. - type: 'null' name: type: string description: The name of the function to call. required: - role - content - name ChatCompletionRequestSystemMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' ChatCompletionRequestMessageContentPartImage: type: object title: Image content part description: 'Learn about [image inputs](https://developers.openai.com/api/docs/guides/images-vision). ' properties: type: type: string enum: - image_url description: The type of the content part. x-stainless-const: true image_url: type: object properties: url: type: string description: Either a URL of the image or the base64 encoded image data. format: uri detail: type: string description: Specifies the detail level of the image. Learn more in the [Vision guide](https://developers.openai.com/api/docs/guides/images-vision#choose-an-image-detail-level). enum: - auto - low - high default: auto required: - url prompt_cache_breakpoint: $ref: '#/components/schemas/PromptCacheBreakpointParam' required: - type - image_url VoiceIdsOrCustomVoice: title: Voice description: 'A built-in voice name or a custom voice reference. ' anyOf: - $ref: '#/components/schemas/VoiceIdsShared' - type: object description: Custom voice reference. additionalProperties: false required: - id properties: id: type: string description: The custom voice ID, e.g. `voice_1234`. example: voice_1234 ChatCompletionStreamResponseDelta: type: object description: A chat completion delta generated by streamed model responses. properties: content: anyOf: - type: string description: The contents of the chunk message. - type: 'null' function_call: deprecated: true type: object description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. tool_calls: type: array items: $ref: '#/components/schemas/ChatCompletionMessageToolCallChunk' role: type: string enum: - developer - system - user - assistant - tool description: The role of the author of this message. refusal: anyOf: - type: string description: The refusal message generated by the model. - type: 'null' ChatCompletionRequestDeveloperMessage: type: object title: Developer message description: 'Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, `developer` messages replace the previous `system` messages. ' properties: content: description: The contents of the developer message. oneOf: - type: string description: The contents of the developer message. title: Text content - type: array description: An array of content parts with a defined type. For developer messages, only type `text` is supported. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' minItems: 1 role: type: string enum: - developer description: The role of the messages author, in this case `developer`. x-stainless-const: true name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionMessageToolCall: type: object title: Function tool call description: 'A call to a function tool created by the model. ' properties: id: type: string description: The ID of the tool call. type: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. x-stainless-const: true function: type: object description: The function that the model called. properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - name - arguments required: - id - type - function ChatCompletionMessageList: type: object title: ChatCompletionMessageList description: 'An object representing a list of chat completion messages. ' properties: object: type: string enum: - list default: list description: 'The type of this object. It is always set to "list". ' x-stainless-const: true data: type: array description: 'An array of chat completion message objects. ' items: allOf: - $ref: '#/components/schemas/ChatCompletionResponseMessage' - type: object required: - id properties: id: type: string description: The identifier of the chat message. content_parts: anyOf: - type: array description: 'If a content parts array was provided, this is an array of `text` and `image_url` parts. Otherwise, null. ' items: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartImage' - type: 'null' first_id: type: string description: The identifier of the first chat message in the data array. last_id: type: string description: The identifier of the last chat message in the data array. has_more: type: boolean description: Indicates whether there are more chat messages available. required: - object - data - first_id - last_id - has_more x-oaiMeta: name: The chat completion message list object group: chat example: "{\n \"object\": \"list\",\n \"data\": [\n {\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"role\": \"user\",\n \"content\": \"write a haiku about ai\",\n \"name\": null,\n \"content_parts\": null\n }\n ],\n \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2-0\",\n \"has_more\": false\n}\n" WebSearchLocation: type: object title: Web search location description: Approximate location parameters for the search. properties: country: type: string description: "The two-letter \n[ISO country code](https://en.wikipedia.org/wiki/ISO_3166-1) of the user,\ne.g. `US`.\n" region: type: string description: 'Free text input for the region of the user, e.g. `California`. ' city: type: string description: 'Free text input for the city of the user, e.g. `San Francisco`. ' timezone: type: string description: "The [IANA timezone](https://timeapi.io/documentation/iana-timezones) \nof the user, e.g. `America/Los_Angeles`.\n" MisalignmentErrorDetailsResource: properties: error_type: $ref: '#/components/schemas/_MisalignmentErrorType' description: An optional classification; clients must accept additional values. detailed_explanation: type: string description: The public explanation for this block. steer: $ref: '#/components/schemas/_MisalignmentSteer' description: An optional public continuation instruction. type: object required: [] FunctionParameters: type: object description: 'The parameters the functions accepts, described as a JSON Schema object. See the [guide](https://developers.openai.com/api/docs/guides/function-calling) for examples, and the [JSON Schema reference](https://json-schema.org/understanding-json-schema/) for documentation about the format. Omitting `parameters` defines a function with an empty parameter list.' additionalProperties: true ChatCompletionRequestMessageContentPartRefusal: type: object title: Refusal content part properties: type: type: string enum: - refusal description: The type of the content part. x-stainless-const: true refusal: type: string description: The refusal message generated by the model. required: - type - refusal ChatCompletionModerationResults: type: object description: Successful moderation results for the request input or generated output. properties: type: type: string enum: - moderation_results description: The object type, which is always `moderation_results`. x-stainless-const: true model: type: string description: The moderation model used to generate the results. results: type: array description: A list of moderation results. items: $ref: '#/components/schemas/ModerationResultBody' required: - type - model - results ModerationPolicyParam: properties: input: anyOf: - $ref: '#/components/schemas/ModerationConfigParam' description: The moderation policy for the response input. - type: 'null' output: anyOf: - $ref: '#/components/schemas/ModerationConfigParam' description: The moderation policy for the response output. - type: 'null' type: object required: [] description: The policy to apply to moderated response input and output. ChatCompletionFunctions: type: object deprecated: true properties: description: type: string description: A description of what the function does, used by the model to choose when and how to call the function. name: type: string description: The name of the function to be called. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. parameters: $ref: '#/components/schemas/FunctionParameters' required: - name ResponseFormatJsonSchema: type: object title: JSON schema description: 'JSON Schema response format. Used to generate structured JSON responses. Learn more about [Structured Outputs](https://developers.openai.com/api/docs/guides/structured-outputs). ' properties: type: type: string description: The type of response format being defined. Always `json_schema`. enum: - json_schema x-stainless-const: true json_schema: type: object title: JSON schema description: 'Structured Outputs configuration options, including a JSON Schema. ' properties: description: type: string description: 'A description of what the response format is for, used by the model to determine how to respond in the format. ' name: type: string description: 'The name of the response format. Must be a-z, A-Z, 0-9, or contain underscores and dashes, with a maximum length of 64. ' schema: $ref: '#/components/schemas/ResponseFormatJsonSchemaSchema' strict: anyOf: - type: boolean default: false description: 'Whether to enable strict schema adherence when generating the output. If set to true, the model will always follow the exact schema defined in the `schema` field. Only a subset of JSON Schema is supported when `strict` is `true`. To learn more, read the [Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs). ' - type: 'null' required: - name required: - type - json_schema ChatCompletionAllowedTools: type: object title: Allowed tools description: 'Constrains the tools available to the model to a pre-defined set. ' properties: mode: type: string enum: - auto - required description: 'Constrains the tools available to the model to a pre-defined set. `auto` allows the model to pick from among the allowed tools and generate a message. `required` requires the model to call one or more of the allowed tools. ' tools: type: array description: "A list of tool definitions that the model should be allowed to call.\n\nFor the Chat Completions API, the list of tool definitions might look like:\n```json\n[\n { \"type\": \"function\", \"function\": { \"name\": \"get_weather\" } },\n { \"type\": \"function\", \"function\": { \"name\": \"get_time\" } }\n]\n```\n" items: type: object x-oaiExpandable: false description: 'A tool definition that the model should be allowed to call. ' additionalProperties: true required: - mode - tools CreateChatCompletionRequest: allOf: - $ref: '#/components/schemas/CreateModelResponseProperties' - type: object properties: messages: description: 'A list of messages comprising the conversation so far. Depending on the [model](https://developers.openai.com/api/docs/models) you use, different message types (modalities) are supported, like [text](https://developers.openai.com/api/docs/guides/text), [images](https://developers.openai.com/api/docs/guides/images-vision), and [audio](https://developers.openai.com/api/docs/guides/audio). ' type: array minItems: 1 items: $ref: '#/components/schemas/ChatCompletionRequestMessage' model: description: 'Model ID used to generate the response, like `gpt-6-astra` or `o3`. OpenAI offers a wide range of models with different capabilities, performance characteristics, and price points. Refer to the [model guide](https://developers.openai.com/api/docs/models) to browse and compare available models. ' $ref: '#/components/schemas/ModelIdsShared' service_tier: $ref: '#/components/schemas/ServiceTier' modalities: $ref: '#/components/schemas/ResponseModalities' verbosity: $ref: '#/components/schemas/Verbosity' reasoning_effort: $ref: '#/components/schemas/ReasoningEffort' max_completion_tokens: description: 'An upper bound for the number of tokens that can be generated for a completion, including visible output tokens and [reasoning tokens](https://developers.openai.com/api/docs/guides/reasoning). ' type: integer nullable: true frequency_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model''s likelihood to repeat the same line verbatim. ' presence_penalty: type: number default: 0 minimum: -2 maximum: 2 nullable: true description: 'Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model''s likelihood to talk about new topics. ' web_search_options: type: object title: Web search description: 'This tool searches the web for relevant results to use in a response. Learn more about the [web search tool](https://developers.openai.com/api/docs/guides/tools-web-search). ' properties: user_location: type: object nullable: true required: - type - approximate description: 'Approximate location parameters for the search. ' properties: type: type: string description: 'The type of location approximation. Always `approximate`. ' enum: - approximate x-stainless-const: true approximate: $ref: '#/components/schemas/WebSearchLocation' search_context_size: $ref: '#/components/schemas/WebSearchContextSize' top_logprobs: description: 'An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. `logprobs` must be set to `true` if this parameter is used. ' type: integer minimum: 0 maximum: 20 nullable: true response_format: description: 'An object specifying the format that the model must output. Setting to `{ "type": "json_schema", "json_schema": {...} }` enables Structured Outputs which ensures the model will match your supplied JSON schema. Learn more in the [Structured Outputs guide](https://developers.openai.com/api/docs/guides/structured-outputs). Setting to `{ "type": "json_object" }` enables the older JSON mode, which ensures the message the model generates is valid JSON. Using `json_schema` is preferred for models that support it. ' oneOf: - $ref: '#/components/schemas/ResponseFormatText' - $ref: '#/components/schemas/ResponseFormatJsonSchema' - $ref: '#/components/schemas/ResponseFormatJsonObject' discriminator: propertyName: type audio: type: object nullable: true description: 'Parameters for audio output. Required when audio output is requested with `modalities: ["audio"]`. [Learn more](https://developers.openai.com/api/docs/guides/audio). ' required: - voice - format properties: voice: $ref: '#/components/schemas/VoiceIdsOrCustomVoice' description: 'The voice the model uses to respond. Supported built-in voices are `alloy`, `ash`, `ballad`, `coral`, `echo`, `fable`, `nova`, `onyx`, `sage`, `shimmer`, `marin`, and `cedar`. You may also provide a custom voice object with an `id`, for example `{ "id": "voice_1234" }`. ' format: type: string enum: - wav - aac - mp3 - flac - opus - pcm16 description: 'Specifies the output audio format. Must be one of `wav`, `mp3`, `flac`, `opus`, or `pcm16`. ' store: type: boolean default: false nullable: true description: 'Whether or not to store the output of this chat completion request for use in our [model distillation](https://developers.openai.com/api/docs/guides/supervised-fine-tuning#distilling-from-a-larger-model) or [evals](https://developers.openai.com/api/docs/guides/evals) products. Supports text and image inputs. Note: image inputs over 8MB will be dropped. ' moderation: anyOf: - $ref: '#/components/schemas/ModerationParam' description: 'Configuration for running moderation on the request input and generated output. ' - type: 'null' stream: description: 'If set to true, the model response data will be streamed to the client as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). See the [Streaming section below](https://developers.openai.com/api/reference/resources/chat/subresources/completions/streaming-events) for more information, along with the [streaming responses](https://developers.openai.com/api/docs/guides/streaming-responses) guide for more information on how to handle the streaming events. ' type: boolean nullable: true default: false stop: $ref: '#/components/schemas/StopConfiguration' logit_bias: type: object x-oaiTypeLabel: map default: null nullable: true additionalProperties: type: integer description: 'Modify the likelihood of specified tokens appearing in the completion. Accepts a JSON object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. ' logprobs: description: 'Whether to return log probabilities of the output tokens or not. If true, returns the log probabilities of each output token returned in the `content` of `message`. ' type: boolean default: false nullable: true max_tokens: description: 'The maximum number of [tokens](https://platform.openai.com/tokenizer) that can be generated in the chat completion. This value can be used to control [costs](https://openai.com/api/pricing/) for text generated via API. This value is now deprecated in favor of `max_completion_tokens`, and is not compatible with [o-series models](https://developers.openai.com/api/docs/guides/reasoning). ' type: integer nullable: true deprecated: true n: type: integer minimum: 1 maximum: 128 default: 1 example: 1 nullable: true description: How many chat completion choices to generate for each input message. Note that you will be charged based on the number of generated tokens across all of the choices. Keep `n` as `1` to minimize costs. prediction: nullable: true description: 'Configuration for a [Predicted Output](https://developers.openai.com/api/docs/guides/predicted-outputs), which can greatly improve response times when large parts of the model response are known ahead of time. This is most common when you are regenerating a file with only minor changes to most of the content. ' oneOf: - $ref: '#/components/schemas/PredictionContent' seed: type: integer format: int64 minimum: -9223372036854775808 maximum: 9223372036854775807 nullable: true deprecated: true description: 'This feature is in Beta. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result. Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend. ' x-oaiMeta: beta: true stream_options: $ref: '#/components/schemas/ChatCompletionStreamOptions' tools: type: array description: 'A list of tools the model may call. You can provide either [custom tools](https://developers.openai.com/api/docs/guides/function-calling#custom-tools) or [function tools](https://developers.openai.com/api/docs/guides/function-calling). ' items: oneOf: - $ref: '#/components/schemas/ChatCompletionTool' - $ref: '#/components/schemas/CustomToolChatCompletions' tool_choice: $ref: '#/components/schemas/ChatCompletionToolChoiceOption' parallel_tool_calls: $ref: '#/components/schemas/ParallelToolCalls' function_call: deprecated: true description: 'Deprecated in favor of `tool_choice`. Controls which (if any) function is called by the model. `none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. `none` is the default when no functions are present. `auto` is the default if functions are present. ' oneOf: - type: string description: '`none` means the model will not call a function and instead generates a message. `auto` means the model can pick between generating a message or calling a function. ' enum: - none - auto - $ref: '#/components/schemas/ChatCompletionFunctionCallOption' functions: deprecated: true description: 'Deprecated in favor of `tools`. A list of functions the model may generate JSON inputs for. ' type: array minItems: 1 maxItems: 128 items: $ref: '#/components/schemas/ChatCompletionFunctions' required: - model - messages _MisalignmentSteer: properties: message: type: string description: The public continuation instruction. type: object required: - message ServiceTier: anyOf: - type: string description: "Specifies the processing type used for serving the request.\n - If set to 'auto', then the request will be processed with the service tier configured in the Project settings. Unless otherwise configured, the Project will use 'default'.\n - If set to 'default', then the request will be processed with the standard pricing and performance for the selected model.\n - If set to '[flex](https://developers.openai.com/api/docs/guides/flex-processing)', then the request will be processed with the Flex Processing service tier.\n - To opt-in to [Fast mode](https://developers.openai.com/api/docs/guides/fast-mode) at the request level, include the `service_tier=fast` or `service_tier=priority` parameter for Responses or Chat Completions. The response will show `service_tier=priority` regardless of if you specify `service_tier=fast` or `priority` in your request.\n - When not set, the default behavior is 'auto'.\n\n When the `service_tier` parameter is set, the response body will include the `service_tier` value based on the processing mode actually used to serve the request. This response value may be different from the value set in the parameter.\n" enum: - auto - default - flex - scale - priority - fast default: auto - type: 'null' CreateChatCompletionResponse: type: object description: Represents a chat completion response returned by model, based on the provided input. properties: id: type: string description: A unique identifier for the chat completion. choices: type: array description: A list of chat completion choices. Can be more than one if `n` is greater than 1. items: type: object required: - finish_reason - index - message - logprobs properties: finish_reason: type: string description: 'The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. Read the [Model Spec](https://model-spec.openai.com/2025-12-18.html) for more. ' enum: - stop - length - tool_calls - content_filter - function_call index: type: integer description: The index of the choice in the list of choices. message: $ref: '#/components/schemas/ChatCompletionResponseMessage' logprobs: anyOf: - description: Log probability information for the choice. type: object properties: content: anyOf: - description: A list of message content tokens with log probability information. type: array items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' - type: 'null' refusal: anyOf: - description: A list of message refusal tokens with log probability information. type: array items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' - type: 'null' required: - content - refusal - type: 'null' created: type: integer format: unixtime description: The Unix timestamp (in seconds) of when the chat completion was created. model: type: string description: The model used for the chat completion. metadata: $ref: '#/components/schemas/Metadata' service_tier: $ref: '#/components/schemas/ServiceTier' system_fingerprint: type: string deprecated: true description: 'This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. ' object: type: string description: The object type, which is always `chat.completion`. enum: - chat.completion x-stainless-const: true usage: $ref: '#/components/schemas/CompletionUsage' moderation: anyOf: - $ref: '#/components/schemas/ChatCompletionModeration' description: 'Moderation results for the request input and generated output, if moderated completions were requested. ' - type: 'null' required: - choices - created - id - model - object x-oaiMeta: name: The chat completion object group: chat example: "{\n \"id\": \"chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG\",\n \"object\": \"chat.completion\",\n \"created\": 1741570283,\n \"model\": \"gpt-6-astra\",\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"role\": \"assistant\",\n \"content\": \"The image shows a wooden boardwalk path running through a lush green field or meadow. The sky is bright blue with some scattered clouds, giving the scene a serene and peaceful atmosphere. Trees and shrubs are visible in the background.\",\n \"refusal\": null,\n \"annotations\": []\n },\n \"logprobs\": null,\n \"finish_reason\": \"stop\"\n }\n ],\n \"usage\": {\n \"prompt_tokens\": 1117,\n \"completion_tokens\": 46,\n \"total_tokens\": 1163,\n \"prompt_tokens_details\": {\n \"cached_tokens\": 0,\n \"audio_tokens\": 0\n },\n \"completion_tokens_details\": {\n \"reasoning_tokens\": 0,\n \"audio_tokens\": 0,\n \"accepted_prediction_tokens\": 0,\n \"rejected_prediction_tokens\": 0\n }\n },\n \"service_tier\": \"default\",\n \"system_fingerprint\": \"fp_fc9f1d7035\"\n}\n" ReasoningEffort: anyOf: - type: string enum: - none - minimal - low - medium - high - xhigh - max default: medium description: 'Constrains effort on reasoning for reasoning models. Currently supported values are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. Reducing reasoning effort can result in faster responses and fewer tokens used on reasoning in a response. Not all reasoning models support every value. See the [reasoning guide](https://developers.openai.com/api/docs/guides/reasoning) for model-specific support. ' - type: 'null' ChatCompletionRequestToolMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' ChatCompletionMessageCustomToolCall: type: object title: Custom tool call description: 'A call to a custom tool created by the model. ' properties: id: type: string description: The ID of the tool call. type: type: string enum: - custom description: The type of the tool. Always `custom`. x-stainless-const: true custom: type: object description: The custom tool that the model called. properties: name: type: string description: The name of the custom tool to call. input: type: string description: The input for the custom tool call generated by the model. required: - name - input required: - id - type - custom ModelResponseProperties: type: object properties: metadata: $ref: '#/components/schemas/Metadata' top_logprobs: anyOf: - description: 'An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. ' type: integer minimum: 0 maximum: 20 - type: 'null' temperature: anyOf: - type: number minimum: 0 maximum: 2 default: 1 example: 1 description: 'What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or `top_p` but not both. ' - type: 'null' top_p: anyOf: - type: number minimum: 0 maximum: 1 default: 1 example: 1 description: 'An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or `temperature` but not both. ' - type: 'null' user: type: string example: user-1234 deprecated: true description: 'This field is being replaced by `safety_identifier` and `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching optimizations. A stable identifier for your end-users. Used to boost cache hit rates by better bucketing similar requests and to help OpenAI detect and prevent abuse. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers). ' safety_identifier: anyOf: - type: string maxLength: 64 example: safety-identifier-1234 description: 'A stable identifier used to help detect users of your application that may be violating OpenAI''s usage policies. The IDs should be a string that uniquely identifies each user, with a maximum length of 64 characters. We recommend hashing their username or email address, in order to avoid sending us any identifying information. [Learn more](https://developers.openai.com/api/docs/guides/safety-best-practices#implement-safety-identifiers). ' - type: 'null' prompt_cache_key: anyOf: - type: string example: prompt-cache-key-1234 description: 'Used by OpenAI to cache responses for similar requests to optimize your cache hit rates. Replaces the `user` field. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching). ' - type: 'null' prompt_cache_retention: deprecated: true anyOf: - type: string enum: - in_memory - 24h description: "Deprecated. Use `prompt_cache_options.ttl` instead.\n\nThe retention policy for the prompt cache. Set to `24h` to enable extended prompt caching, which keeps cached prefixes active for longer, up to a maximum of 24 hours. [Learn more](https://developers.openai.com/api/docs/guides/prompt-caching#prompt-cache-retention).\nThis field expresses a maximum retention policy, while\n`prompt_cache_options.ttl` expresses a minimum cache lifetime. The two\nfields are independent and do not interact.\nFor `gpt-5.5`, `gpt-5.5-pro`, and future models, only `24h` is supported.\n\nFor older models that support both `in_memory` and `24h`, the default depends on your organization's data retention policy:\n - Organizations without ZDR enabled default to `24h`.\n - Organizations with ZDR enabled default to `in_memory` when `prompt_cache_retention` is not specified.\n" - type: 'null' ChatCompletionRequestMessageContentPartText: type: object title: Text content part description: 'Learn about [text inputs](https://developers.openai.com/api/docs/guides/text). ' properties: type: type: string enum: - text description: The type of the content part. x-stainless-const: true text: type: string description: The text content. prompt_cache_breakpoint: $ref: '#/components/schemas/PromptCacheBreakpointParam' required: - type - text ChatCompletionRequestMessageContentPartAudio: type: object title: Audio content part description: 'Learn about [audio inputs](https://developers.openai.com/api/docs/guides/audio). ' properties: type: type: string enum: - input_audio description: The type of the content part. Always `input_audio`. x-stainless-const: true input_audio: type: object properties: data: type: string description: Base64 encoded audio data. format: type: string enum: - wav - mp3 description: 'The format of the encoded audio data. Currently supports "wav" and "mp3". ' required: - data - format prompt_cache_breakpoint: $ref: '#/components/schemas/PromptCacheBreakpointParam' required: - type - input_audio ChatCompletionModerationError: type: object description: An error produced while attempting moderation. properties: type: type: string enum: - error description: The object type, which is always `error`. x-stainless-const: true code: type: string description: The error code. message: type: string description: The error message. required: - type - code - message CreateModelResponseProperties: allOf: - $ref: '#/components/schemas/ModelResponseProperties' - type: object properties: prompt_cache_options: $ref: '#/components/schemas/PromptCacheOptionsParam' top_logprobs: description: 'An integer between 0 and 20 specifying the maximum number of most likely tokens to return at each token position, each with an associated log probability. In some cases, the number of returned tokens may be fewer than requested. ' type: integer minimum: 0 maximum: 20 ChatCompletionNamedToolChoice: type: object title: Function tool choice description: Specifies a tool the model should use. Use to force the model to call a specific function. properties: type: type: string enum: - function description: For function calling, the type is always `function`. x-stainless-const: true function: type: object properties: name: type: string description: The name of the function to call. required: - name required: - type - function ChatCompletionFunctionCallOption: type: object description: 'Specifying a particular function via `{"name": "my_function"}` forces the model to call that function. ' properties: name: type: string description: The name of the function to call. required: - name ModerationConfigParam: properties: mode: $ref: '#/components/schemas/ModerationMode' type: object required: - mode description: The moderation policy for the response input. ChatCompletionModeration: type: object description: Moderation results or errors for the request input and generated output. properties: input: oneOf: - $ref: '#/components/schemas/ChatCompletionModerationResults' - $ref: '#/components/schemas/ChatCompletionModerationError' discriminator: propertyName: type description: Moderation for the request input. output: oneOf: - $ref: '#/components/schemas/ChatCompletionModerationResults' - $ref: '#/components/schemas/ChatCompletionModerationError' discriminator: propertyName: type description: Moderation for the generated output. required: - input - output PromptCacheBreakpointParam: properties: mode: type: string enum: - explicit description: The breakpoint mode. Always `explicit`. default: explicit x-stainless-const: true type: object required: - mode title: Prompt cache breakpoint description: Marks the exact end of a reusable prompt prefix. The breakpoint inherits its TTL from the request's `prompt_cache_options.ttl`; the boundary is not rounded to a token block. Error: type: object properties: code: anyOf: - type: string - type: 'null' message: type: string param: anyOf: - type: string - type: 'null' type: type: string misalignment: $ref: '#/components/schemas/MisalignmentErrorDetailsResource' required: - type - message - param - code ChatCompletionRequestUserMessage: type: object title: User message description: 'Messages sent by an end user, containing prompts or additional context information. ' properties: content: description: 'The contents of the user message. ' oneOf: - type: string description: The text contents of the message. title: Text content - type: array description: An array of content parts with a defined type. Supported options differ based on the [model](https://developers.openai.com/api/docs/models) being used to generate the response. Can contain text, image, or audio inputs. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestUserMessageContentPart' minItems: 1 role: type: string enum: - user description: The role of the messages author, in this case `user`. x-stainless-const: true name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role CreateChatCompletionStreamResponse: type: object description: 'Represents a streamed chunk of a chat completion response returned by the model, based on the provided input. [Learn more](https://developers.openai.com/api/docs/guides/streaming-responses). ' properties: id: type: string description: A unique identifier for the chat completion. Each chunk has the same ID. choices: type: array description: 'A list of chat completion choices. Can contain more than one elements if `n` is greater than 1. Can also be empty for the last chunk if you set `stream_options: {"include_usage": true}`. ' items: type: object required: - delta - finish_reason - index properties: delta: $ref: '#/components/schemas/ChatCompletionStreamResponseDelta' logprobs: description: Log probability information for the choice. type: object nullable: true properties: content: description: A list of message content tokens with log probability information. type: array items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' nullable: true refusal: description: A list of message refusal tokens with log probability information. type: array items: $ref: '#/components/schemas/ChatCompletionTokenLogprob' nullable: true required: - content - refusal finish_reason: type: string description: 'The reason the model stopped generating tokens. This will be `stop` if the model hit a natural stop point or a provided stop sequence, `length` if the maximum number of tokens specified in the request was reached, `content_filter` if content was omitted due to a flag from our content filters, `tool_calls` if the model called a tool, or `function_call` (deprecated) if the model called a function. ' enum: - stop - length - tool_calls - content_filter - function_call nullable: true index: type: integer description: The index of the choice in the list of choices. created: type: integer format: unixtime description: The Unix timestamp (in seconds) of when the chat completion was created. Each chunk has the same timestamp. model: type: string description: The model to generate the completion. obfuscation: type: string description: 'An obfuscation string added to normalize the size of streamed chunks as a mitigation to certain side-channel attacks. The field is included by default and omitted when `stream_options.include_obfuscation` is `false`. ' service_tier: $ref: '#/components/schemas/ServiceTier' system_fingerprint: type: string deprecated: true description: 'This fingerprint represents the backend configuration that the model runs with. Can be used in conjunction with the `seed` request parameter to understand when backend changes have been made that might impact determinism. ' object: type: string description: The object type, which is always `chat.completion.chunk`. enum: - chat.completion.chunk x-stainless-const: true usage: $ref: '#/components/schemas/CompletionUsage' nullable: true description: 'An optional field that will only be present when you set `stream_options: {"include_usage": true}` in your request. When present, it contains a null value **except for the last chunk** which contains the token usage statistics for the entire request. **NOTE:** If the stream is interrupted or cancelled, you may not receive the final usage chunk which contains the total token usage for the request. ' moderation: anyOf: - $ref: '#/components/schemas/ChatCompletionModeration' description: 'Moderation results for the request input and generated output. Present on the moderation chunk when moderated completions are requested. ' - type: 'null' required: - choices - created - id - model - object x-oaiMeta: name: The chat completion chunk object group: chat example: '{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"role":"assistant","content":""},"logprobs":null,"finish_reason":null}],"obfuscation":"r4N7vQ2m"} {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{"content":"Hello"},"logprobs":null,"finish_reason":null}],"obfuscation":"p9K3xT6w"} .... {"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-6-astra", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}],"obfuscation":""} ' Metadata: anyOf: - type: object description: 'Set of 16 key-value pairs that can be attached to an object. This can be useful for storing additional information about the object in a structured format, and querying for objects via API or the dashboard. Keys are strings with a maximum length of 64 characters. Values are strings with a maximum length of 512 characters. ' additionalProperties: type: string x-oaiTypeLabel: map - type: 'null' ResponseFormatJsonSchemaSchema: type: object title: JSON schema description: 'The schema for the response format, described as a JSON Schema object. Learn how to build JSON schemas [here](https://json-schema.org/). ' additionalProperties: true ChatCompletionMessageToolCallChunk: type: object properties: index: type: integer id: type: string description: The ID of the tool call. type: type: string enum: - function description: The type of the tool. Currently, only `function` is supported. x-stainless-const: true function: type: object properties: name: type: string description: The name of the function to call. arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. required: - index PromptCacheModeEnum: type: string enum: - implicit - explicit ModelIdsShared: example: gpt-6-astra anyOf: - type: string - type: string enum: - gpt-6-astra - gpt-6-sol - gpt-6-luna - gpt-5.6-sol - gpt-5.6-terra - gpt-5.6-luna - gpt-5.5 - gpt-5.5-2026-04-23 - gpt-5.4 - gpt-5.4-mini - gpt-5.4-nano - gpt-5.4-mini-2026-03-17 - gpt-5.4-nano-2026-03-17 - gpt-5.3-chat-latest - gpt-5.2 - gpt-5.2-2025-12-11 - gpt-5.2-chat-latest - gpt-5.2-pro - gpt-5.2-pro-2025-12-11 - gpt-5.1 - gpt-5.1-2025-11-13 - gpt-5.1-codex - gpt-5.1-mini - gpt-5.1-chat-latest - gpt-5 - gpt-5-mini - gpt-5-nano - gpt-5-2025-08-07 - gpt-5-mini-2025-08-07 - gpt-5-nano-2025-08-07 - gpt-5-chat-latest - gpt-4.1 - gpt-4.1-mini - gpt-4.1-nano - gpt-4.1-2025-04-14 - gpt-4.1-mini-2025-04-14 - gpt-4.1-nano-2025-04-14 - o4-mini - o4-mini-2025-04-16 - o3 - o3-2025-04-16 - o3-mini - o3-mini-2025-01-31 - o1 - o1-2024-12-17 - o1-preview - o1-preview-2024-09-12 - o1-mini - o1-mini-2024-09-12 - gpt-4o - gpt-4o-2024-11-20 - gpt-4o-2024-08-06 - gpt-4o-2024-05-13 - gpt-audio-mini - gpt-audio-mini-2025-12-15 - gpt-4o-audio-preview - gpt-4o-audio-preview-2024-10-01 - gpt-4o-audio-preview-2024-12-17 - gpt-4o-audio-preview-2025-06-03 - gpt-4o-mini-audio-preview - gpt-4o-mini-audio-preview-2024-12-17 - gpt-4o-search-preview - gpt-4o-mini-search-preview - gpt-4o-search-preview-2025-03-11 - gpt-4o-mini-search-preview-2025-03-11 - chatgpt-4o-latest - codex-mini-latest - gpt-4o-mini - gpt-4o-mini-2024-07-18 - gpt-4-turbo - gpt-4-turbo-2024-04-09 - gpt-4-0125-preview - gpt-4-turbo-preview - gpt-4-1106-preview - gpt-4-vision-preview - gpt-4 - gpt-4-0314 - gpt-4-0613 - gpt-4-32k - gpt-4-32k-0314 - gpt-4-32k-0613 - gpt-3.5-turbo - gpt-3.5-turbo-16k - gpt-3.5-turbo-0301 - gpt-3.5-turbo-0613 - gpt-3.5-turbo-1106 - gpt-3.5-turbo-0125 - gpt-3.5-turbo-16k-0613 _MisalignmentErrorType: anyOf: - type: string - type: string enum: - potentially_unintended_data_transfer - potentially_unintended_data_access - potentially_unintended_destructive_activity - other ResponseModalities: anyOf: - type: array description: 'Output types that you would like the model to generate. Most models are capable of generating text, which is the default: `["text"]` The `gpt-4o-audio-preview` model can also be used to [generate audio](https://developers.openai.com/api/docs/guides/audio). To request that this model generate both text and audio responses, you can use: `["text", "audio"]` ' items: type: string enum: - text - audio - type: 'null' ChatCompletionList: type: object title: ChatCompletionList description: 'An object representing a list of Chat Completions. ' properties: object: type: string enum: - list default: list description: 'The type of this object. It is always set to "list". ' x-stainless-const: true data: type: array description: 'An array of chat completion objects. ' items: $ref: '#/components/schemas/CreateChatCompletionResponse' first_id: type: string description: The identifier of the first chat completion in the data array. last_id: type: string description: The identifier of the last chat completion in the data array. has_more: type: boolean description: Indicates whether there are more Chat Completions available. required: - object - data - first_id - last_id - has_more x-oaiMeta: name: The chat completion list object group: chat example: "{\n \"object\": \"list\",\n \"data\": [\n {\n \"object\": \"chat.completion\",\n \"id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"model\": \"gpt-6-astra\",\n \"created\": 1738960610,\n \"request_id\": \"req_ded8ab984ec4bf840f37566c1011c417\",\n \"tool_choice\": null,\n \"usage\": {\n \"total_tokens\": 31,\n \"completion_tokens\": 18,\n \"prompt_tokens\": 13\n },\n \"seed\": 4944116822809979520,\n \"top_p\": 1.0,\n \"temperature\": 1.0,\n \"presence_penalty\": 0.0,\n \"frequency_penalty\": 0.0,\n \"system_fingerprint\": \"fp_50cad350e4\",\n \"input_user\": null,\n \"service_tier\": \"default\",\n \"tools\": null,\n \"metadata\": {},\n \"choices\": [\n {\n \"index\": 0,\n \"message\": {\n \"content\": \"Mind of circuits hum, \\nLearning patterns in silence— \\nFuture's quiet spark.\",\n \"role\": \"assistant\",\n \"tool_calls\": null,\n \"function_call\": null\n },\n \"finish_reason\": \"stop\",\n \"logprobs\": null\n }\n ],\n \"response_format\": null\n }\n ],\n \"first_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"last_id\": \"chatcmpl-AyPNinnUqUDYo9SAdA52NobMflmj2\",\n \"has_more\": false\n}\n" CustomToolChatCompletions: type: object title: Custom tool description: 'A custom tool that processes input using a specified format. ' properties: type: type: string enum: - custom description: The type of the custom tool. Always `custom`. x-stainless-const: true custom: type: object title: Custom tool properties description: 'Properties of the custom tool. ' properties: name: type: string description: The name of the custom tool, used to identify it in tool calls. description: type: string description: 'Optional description of the custom tool, used to provide more context. ' format: description: 'The input format for the custom tool. Default is unconstrained text. ' oneOf: - type: object title: Text format description: Unconstrained free-form text. properties: type: type: string enum: - text description: Unconstrained text format. Always `text`. x-stainless-const: true required: - type additionalProperties: false - type: object title: Grammar format description: A grammar defined by the user. properties: type: type: string enum: - grammar description: Grammar format. Always `grammar`. x-stainless-const: true grammar: type: object title: Grammar format description: Your chosen grammar. properties: definition: type: string description: The grammar definition. syntax: type: string description: The syntax of the grammar definition. One of `lark` or `regex`. enum: - lark - regex required: - definition - syntax required: - type - grammar additionalProperties: false required: - name required: - type - custom CompletionUsage: type: object description: Usage statistics for the completion request. properties: completion_tokens: type: integer default: 0 description: Number of tokens in the generated completion. prompt_tokens: type: integer default: 0 description: Number of tokens in the prompt. total_tokens: type: integer default: 0 description: Total number of tokens used in the request (prompt + completion). completion_tokens_details: type: object description: Breakdown of tokens used in a completion. properties: accepted_prediction_tokens: type: integer default: 0 description: 'When using Predicted Outputs, the number of tokens in the prediction that appeared in the completion. ' audio_tokens: type: integer default: 0 description: Audio input tokens generated by the model. reasoning_tokens: type: integer default: 0 description: Tokens generated by the model for reasoning. text_tokens: type: integer description: Text output tokens generated by the model. rejected_prediction_tokens: type: integer default: 0 description: 'When using Predicted Outputs, the number of tokens in the prediction that did not appear in the completion. However, like reasoning tokens, these tokens are still counted in the total completion tokens for purposes of billing, output, and context window limits. ' prompt_tokens_details: type: object description: Breakdown of tokens used in the prompt. properties: audio_tokens: type: integer default: 0 description: Audio input tokens present in the prompt. cached_tokens: type: integer default: 0 description: Cached tokens present in the prompt. text_tokens: type: integer description: Text input tokens present in the prompt. image_tokens: type: integer description: Image input tokens present in the prompt. cache_write_tokens: type: integer default: 0 description: The unadjusted number of prompt tokens written to cache. required: - prompt_tokens - completion_tokens - total_tokens ResponseFormatJsonObject: type: object title: JSON object description: 'JSON object response format. An older method of generating JSON responses. Using `json_schema` is recommended for models that support it. Note that the model will not generate JSON without a system or user message instructing it to do so. ' properties: type: type: string description: The type of response format being defined. Always `json_object`. enum: - json_object x-stainless-const: true required: - type ChatCompletionRequestAssistantMessageContentPart: oneOf: - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartText' - $ref: '#/components/schemas/ChatCompletionRequestMessageContentPartRefusal' discriminator: propertyName: type PromptCacheOptionsParam: properties: ttl: $ref: '#/components/schemas/PromptCacheTTLEnum' description: The minimum lifetime applied to every implicit and explicit cache breakpoint written by the request. Defaults to `30m`, which is currently the only supported value. The backend may retain cache entries for longer. mode: $ref: '#/components/schemas/PromptCacheModeEnum' description: Controls whether OpenAI automatically creates an implicit cache breakpoint. Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint and writes up to the latest three explicit breakpoints in the request. With `explicit`, OpenAI does not create an implicit breakpoint and writes up to the latest four explicit breakpoints. If there are no explicit breakpoints, the request does not use prompt caching. type: object required: [] title: Prompt cache options description: Options for prompt caching. Supported for `gpt-5.6` and later models. By default, OpenAI automatically chooses one implicit cache breakpoint. You can add explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each request can write up to four breakpoints. For cache matching, OpenAI considers up to the latest 80 breakpoints in the conversation, without a content-block lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The `ttl` defaults to `30m`, which is currently the only supported value. See the [prompt caching guide](https://developers.openai.com/api/docs/guides/prompt-caching) for current details. ModerationParam: properties: model: type: string description: The moderation model to use for moderated completions, e.g. 'omni-moderation-latest'. policy: anyOf: - $ref: '#/components/schemas/ModerationPolicyParam' description: The policy to apply to moderated response input and output. - type: 'null' type: object required: - model description: Configuration for running moderation on the input and output of this response. ChatCompletionResponseMessage: type: object description: A chat completion message generated by the model. properties: content: anyOf: - type: string description: The contents of the message. - type: 'null' refusal: anyOf: - type: string description: The refusal message generated by the model. - type: 'null' tool_calls: $ref: '#/components/schemas/ChatCompletionMessageToolCalls' annotations: type: array description: 'Annotations for the message, when applicable, as when using the [web search tool](https://developers.openai.com/api/docs/guides/tools-web-search). ' items: type: object description: 'A URL citation when using web search. ' required: - type - url_citation properties: type: type: string description: The type of the URL citation. Always `url_citation`. enum: - url_citation x-stainless-const: true url_citation: type: object description: A URL citation when using web search. required: - end_index - start_index - url - title properties: end_index: type: integer description: The index of the last character of the URL citation in the message. start_index: type: integer description: The index of the first character of the URL citation in the message. url: type: string format: uri description: The URL of the web resource. title: type: string description: The title of the web resource. role: type: string enum: - assistant description: The role of the author of this message. x-stainless-const: true function_call: type: object deprecated: true description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. required: - name - arguments audio: anyOf: - type: object description: 'If the audio output modality is requested, this object contains data about the audio response from the model. [Learn more](https://developers.openai.com/api/docs/guides/audio). ' required: - id - expires_at - data - transcript properties: id: type: string description: Unique identifier for this audio response. expires_at: type: integer format: unixtime description: 'The Unix timestamp (in seconds) for when this audio response will no longer be accessible on the server for use in multi-turn conversations. ' data: type: string description: 'Base64 encoded audio bytes generated by the model, in the format specified in the request. ' transcript: type: string description: Transcript of the audio generated by the model. - type: 'null' required: - role - content - refusal ChatCompletionRequestAssistantMessage: type: object title: Assistant message description: 'Messages sent by the model in response to user messages. ' properties: content: anyOf: - oneOf: - type: string description: The contents of the assistant message. title: Text content - type: array description: An array of content parts with a defined type. Can be one or more of type `text`, or exactly one of type `refusal`. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestAssistantMessageContentPart' minItems: 1 description: 'The contents of the assistant message. Required unless `tool_calls` or `function_call` is specified. ' - type: 'null' refusal: anyOf: - type: string description: The refusal message by the assistant. - type: 'null' role: type: string enum: - assistant description: The role of the messages author, in this case `assistant`. x-stainless-const: true name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. audio: anyOf: - type: object description: 'Data about a previous audio response from the model. [Learn more](https://developers.openai.com/api/docs/guides/audio). ' required: - id properties: id: type: string description: 'Unique identifier for a previous audio response from the model. ' - type: 'null' tool_calls: $ref: '#/components/schemas/ChatCompletionMessageToolCalls' function_call: anyOf: - type: object deprecated: true description: Deprecated and replaced by `tool_calls`. The name and arguments of a function that should be called, as generated by the model. properties: arguments: type: string description: The arguments to call the function with, as generated by the model in JSON format. Note that the model does not always generate valid JSON, and may hallucinate parameters not defined by your function schema. Validate the arguments in your code before calling your function. name: type: string description: The name of the function to call. required: - arguments - name - type: 'null' required: - role ChatCompletionRequestSystemMessage: type: object title: System message description: 'Developer-provided instructions that the model should follow, regardless of messages sent by the user. With o1 models and newer, use `developer` messages for this purpose instead. ' properties: content: description: The contents of the system message. oneOf: - type: string description: The contents of the system message. title: Text content - type: array description: An array of content parts with a defined type. For system messages, only type `text` is supported. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestSystemMessageContentPart' minItems: 1 role: type: string enum: - system description: The role of the messages author, in this case `system`. x-stainless-const: true name: type: string description: An optional name for the participant. Provides the model information to differentiate between participants of the same role. required: - content - role ChatCompletionRequestToolMessage: type: object title: Tool message properties: role: type: string enum: - tool description: The role of the messages author, in this case `tool`. x-stainless-const: true content: oneOf: - type: string description: The contents of the tool message. title: Text content - type: array description: An array of content parts with a defined type. For tool messages, only type `text` is supported. title: Array of content parts items: $ref: '#/components/schemas/ChatCompletionRequestToolMessageContentPart' minItems: 1 description: The contents of the tool message. tool_call_id: type: string description: Tool call that this message is responding to. required: - role - content - tool_call_id ChatCompletionTokenLogprob: type: object properties: token: description: The token. type: string logprob: description: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. type: number bytes: anyOf: - description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. type: array items: type: integer - type: 'null' top_logprobs: description: List of the most likely tokens and their log probability, at this token position. The number of entries may be fewer than the requested `top_logprobs`. type: array items: type: object properties: token: description: The token. type: string logprob: description: The log probability of this token, if it is within the top 20 most likely tokens. Otherwise, the value `-9999.0` is used to signify that the token is very unlikely. type: number bytes: anyOf: - description: A list of integers representing the UTF-8 bytes representation of the token. Useful in instances where characters are represented by multiple tokens and their byte representations must be combined to generate the correct text representation. Can be `null` if there is no bytes representation for the token. type: array items: type: integer - type: 'null' required: - token - logprob - bytes required: - token - logprob - bytes - top_logprobs ChatCompletionNamedToolChoiceCustom: type: object title: Custom tool choice description: Specifies a tool the model should use. Use to force the model to call a specific custom tool. properties: type: type: string enum: - custom description: For custom tool calling, the type is always `custom`. x-stainless-const: true custom: type: object properties: name: type: string description: The name of the custom tool to call. required: - name required: - type - custom Verbosity: anyOf: - type: string enum: - low - medium - high default: medium description: 'Constrains the verbosity of the model''s response. Lower values will result in more concise responses, while higher values will result in more verbose responses. Currently supported values are `low`, `medium`, and `high`. The default is `medium`. ' - type: 'null' ModerationResultBody: properties: type: type: string enum: - moderation_result description: The object type, which was always `moderation_result` for successful moderation results. default: moderation_result x-stainless-const: true model: type: string description: The moderation model that produced this result. flagged: type: boolean description: A boolean indicating whether the content was flagged by any category. categories: additionalProperties: type: boolean type: object description: A dictionary of moderation categories to booleans, True if the input is flagged under this category. x-oaiTypeLabel: map category_scores: additionalProperties: type: number type: object description: A dictionary of moderation categories to scores. x-oaiTypeLabel: map category_applied_input_types: additionalProperties: items: $ref: '#/components/schemas/ModerationInputType' type: array type: object description: Which modalities of input are reflected by the score for each category. x-oaiTypeLabel: map type: object required: - type - model - flagged - categories - category_scores - category_applied_input_types title: Moderation result description: A moderation result produced for the response input or output. responses: InferenceRateLimited: description: The request was rejected because a rate limit was exceeded. A slow_down error means traffic increased too quickly; reduce your request rate, then increase it gradually. headers: Retry-After: description: The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted. schema: type: integer minimum: 1 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: slowDown: summary: Traffic increased too quickly value: error: message: Your request rate increased too quickly. Please reduce the request rate and gradually increase it again. type: rate_limit_error param: null code: slow_down InferenceServiceUnavailable: description: The service is temporarily unavailable. A server_is_overloaded error means the requested model is temporarily overloaded; retry after a brief delay. headers: Retry-After: description: The minimum number of seconds to wait before retrying. This header is returned when the server has computed a retry delay and may be omitted. schema: type: integer minimum: 1 content: application/json: schema: $ref: '#/components/schemas/ErrorResponse' examples: serverOverloaded: summary: The requested model is temporarily overloaded value: error: message: The model is temporarily overloaded. Please retry your request after a brief delay. type: service_unavailable_error param: null code: server_is_overloaded securitySchemes: ApiKeyAuth: type: http scheme: bearer AdminApiKeyAuth: type: http scheme: bearer x-oaiMeta: navigationGroups: - id: responses title: Responses API - id: webhooks title: Webhooks - id: endpoints title: Platform APIs - id: vector_stores title: Vector stores - id: chatkit title: ChatKit beta: true - id: containers title: Containers - id: live title: Live (alpha) - id: realtime title: Realtime - id: chat title: Chat Completions - id: assistants title: Assistants deprecated: true - id: administration title: Administration - id: legacy title: Legacy groups: - id: responses-streaming title: Streaming events description: 'When you [create a Response](https://developers.openai.com/api/reference/resources/responses/methods/create) with `stream` set to `true`, the server will emit server-sent events to the client as the Response is generated. This section contains the events that are emitted by the server. When processing a `compaction_trigger`, `response.compaction.compacting` reports newly sampled summary output at most once every 30 seconds. It carries no summary content and does not modify the compaction output item. The existing `response.output_item.added` and `response.output_item.done` events mark that item''s lifecycle; `response.output_item.done` carries its final encrypted content. A short compaction may finish without emitting a progress event. [Learn more about streaming responses](https://developers.openai.com/api/docs/guides/streaming-responses). ' navigationGroup: responses sections: - type: object key: ResponseCreatedEvent path: - type: object key: ResponseInProgressEvent path: - type: object key: ResponseCompletedEvent path: - type: object key: ResponseFailedEvent path: - type: object key: ResponseIncompleteEvent path: - type: object key: ResponseOutputItemAddedEvent path: - type: object key: ResponseOutputItemDoneEvent path: - type: object key: ResponseCompactionCompactingEvent path: - type: object key: ResponseContentPartAddedEvent path: - type: object key: ResponseContentPartDoneEvent path: - type: object key: ResponseTextDeltaEvent path: response/output_text/delta - type: object key: ResponseTextDoneEvent path: response/output_text/done - type: object key: ResponseRefusalDeltaEvent path: - type: object key: ResponseRefusalDoneEvent path: - type: object key: ResponseFunctionCallArgumentsDeltaEvent path: - type: object key: ResponseFunctionCallArgumentsDoneEvent path: - type: object key: ResponseFileSearchCallInProgressEvent path: - type: object key: ResponseFileSearchCallSearchingEvent path: - type: object key: ResponseFileSearchCallCompletedEvent path: - type: object key: ResponseWebSearchCallInProgressEvent path: - type: object key: ResponseWebSearchCallSearchingEvent path: - type: object key: ResponseWebSearchCallCompletedEvent path: - type: object key: ResponseReasoningSummaryPartAddedEvent path: - type: object key: ResponseReasoningSummaryPartDoneEvent path: - type: object key: ResponseReasoningSummaryTextDeltaEvent path: - type: object key: ResponseReasoningSummaryTextDoneEvent path: - type: object key: ResponseReasoningTextDeltaEvent path: - type: object key: ResponseReasoningTextDoneEvent path: - type: object key: ResponseImageGenCallCompletedEvent path: - type: object key: ResponseImageGenCallGeneratingEvent path: - type: object key: ResponseImageGenCallInProgressEvent path: - type: object key: ResponseImageGenCallPartialImageEvent path: - type: object key: ResponseMCPCallArgumentsDeltaEvent path: - type: object key: ResponseMCPCallArgumentsDoneEvent path: - type: object key: ResponseMCPCallCompletedEvent path: - type: object key: ResponseMCPCallFailedEvent path: - type: object key: ResponseMCPCallInProgressEvent path: - type: object key: ResponseMCPListToolsCompletedEvent path: - type: object key: ResponseMCPListToolsFailedEvent path: - type: object key: ResponseMCPListToolsInProgressEvent path: - type: object key: ResponseCodeInterpreterCallInProgressEvent path: - type: object key: ResponseCodeInterpreterCallInterpretingEvent path: - type: object key: ResponseCodeInterpreterCallCompletedEvent path: - type: object key: ResponseCodeInterpreterCallCodeDeltaEvent path: - type: object key: ResponseCodeInterpreterCallCodeDoneEvent path: - type: object key: ResponseOutputTextAnnotationAddedEvent path: - type: object key: ResponseQueuedEvent path: - type: object key: ResponseCustomToolCallInputDeltaEvent path: - type: object key: ResponseCustomToolCallInputDoneEvent path: - type: object key: ResponseErrorEvent path: - id: responses-websocket-client-events title: Client events description: 'Events sent by the client over a Responses API WebSocket connection. ' navigationGroup: responses sections: - type: object key: ResponsesClientEventResponseCreate path: - type: object key: ResponseSteerEvent path: - id: responses-websocket-server-events title: Server events (WebSocket only) description: 'Events emitted only over a Responses API WebSocket connection. ' navigationGroup: responses sections: - type: object key: ResponseSteerAcceptedEvent path: - type: object key: ResponseSteerPendingEvent path: - type: object key: ResponseSteerFailedEvent path: - id: responses-websocket-shared-events title: Server events description: 'These events use the same payloads over WebSocket and [HTTP streaming](https://developers.openai.com/api/reference/resources/responses/streaming-events). Compaction progress follows the same cadence and output-item lifecycle described in HTTP streaming. ' navigationGroup: responses sections: - type: object key: ResponseCreatedEvent path: - type: object key: ResponseInProgressEvent path: - type: object key: ResponseCompletedEvent path: - type: object key: ResponseFailedEvent path: - type: object key: ResponseIncompleteEvent path: - type: object key: ResponseOutputItemAddedEvent path: - type: object key: ResponseOutputItemDoneEvent path: - type: object key: ResponseCompactionCompactingEvent path: - type: object key: ResponseContentPartAddedEvent path: - type: object key: ResponseContentPartDoneEvent path: - type: object key: ResponseTextDeltaEvent path: response/output_text/delta - type: object key: ResponseTextDoneEvent path: response/output_text/done - type: object key: ResponseRefusalDeltaEvent path: - type: object key: ResponseRefusalDoneEvent path: - type: object key: ResponseFunctionCallArgumentsDeltaEvent path: - type: object key: ResponseFunctionCallArgumentsDoneEvent path: - type: object key: ResponseFileSearchCallInProgressEvent path: - type: object key: ResponseFileSearchCallSearchingEvent path: - type: object key: ResponseFileSearchCallCompletedEvent path: - type: object key: ResponseWebSearchCallInProgressEvent path: - type: object key: ResponseWebSearchCallSearchingEvent path: - type: object key: ResponseWebSearchCallCompletedEvent path: - type: object key: ResponseReasoningSummaryPartAddedEvent path: - type: object key: ResponseReasoningSummaryPartDoneEvent path: - type: object key: ResponseReasoningSummaryTextDeltaEvent path: - type: object key: ResponseReasoningSummaryTextDoneEvent path: - type: object key: ResponseReasoningTextDeltaEvent path: - type: object key: ResponseReasoningTextDoneEvent path: - type: object key: ResponseImageGenCallCompletedEvent path: - type: object key: ResponseImageGenCallGeneratingEvent path: - type: object key: ResponseImageGenCallInProgressEvent path: - type: object key: ResponseImageGenCallPartialImageEvent path: - type: object key: ResponseMCPCallArgumentsDeltaEvent path: - type: object key: ResponseMCPCallArgumentsDoneEvent path: - type: object key: ResponseMCPCallCompletedEvent path: - type: object key: ResponseMCPCallFailedEvent path: - type: object key: ResponseMCPCallInProgressEvent path: - type: object key: ResponseMCPListToolsCompletedEvent path: - type: object key: ResponseMCPListToolsFailedEvent path: - type: object key: ResponseMCPListToolsInProgressEvent path: - type: object key: ResponseCodeInterpreterCallInProgressEvent path: - type: object key: ResponseCodeInterpreterCallInterpretingEvent path: - type: object key: ResponseCodeInterpreterCallCompletedEvent path: - type: object key: ResponseCodeInterpreterCallCodeDeltaEvent path: - type: object key: ResponseCodeInterpreterCallCodeDoneEvent path: - type: object key: ResponseOutputTextAnnotationAddedEvent path: - type: object key: ResponseQueuedEvent path: - type: object key: ResponseCustomToolCallInputDeltaEvent path: - type: object key: ResponseCustomToolCallInputDoneEvent path: - type: object key: ResponseErrorEvent path: - id: safety-cases title: Safety Cases description: 'Retrieve details about a safety warning or deactivation using the case ID from a `safety.warning_issued` or `safety.deactivation_issued` webhook event. Cases belong to an organization and require an API key with `api.safety.read`. ' navigationGroup: endpoints sections: - type: endpoint key: Getsafetycase path: retrieve - type: object key: SafetyCaseResource path: object - id: safety-alerts title: Safety Alerts description: 'Retrieve approved safety alerts with an API key. Project keys require `api.safety.alerts.read` and can read alerts from their project. ' navigationGroup: endpoints sections: - type: endpoint key: Getprojectsafetyalert path: retrieve - type: object key: SafetyAlertResource path: object - id: webhook-events title: Webhook Events description: 'Webhooks are HTTP requests sent by OpenAI to a URL you specify when certain events happen during the course of API usage. [Learn more about webhooks](https://developers.openai.com/api/docs/guides/webhooks). ' navigationGroup: webhooks sections: - type: object key: WebhookResponseCompleted path: - type: object key: WebhookResponseCancelled path: - type: object key: WebhookResponseFailed path: - type: object key: WebhookResponseIncomplete path: - type: object key: WebhookBatchCompleted path: - type: object key: WebhookBatchCancelled path: - type: object key: WebhookBatchExpired path: - type: object key: WebhookBatchFailed path: - type: object key: WebhookFineTuningJobSucceeded path: - type: object key: WebhookFineTuningJobFailed path: - type: object key: WebhookFineTuningJobCancelled path: - type: object key: WebhookEvalRunSucceeded path: - type: object key: WebhookEvalRunFailed path: - type: object key: WebhookEvalRunCanceled path: - type: object key: WebhookRealtimeCallIncoming path: - type: object key: WebhookLiveCallIncoming path: - type: object key: WebhookLiveTransportIncoming path: - type: object key: WebhookSafetyWarningIssued path: - type: object key: WebhookSafetyDeactivationIssued path: - type: object key: WebhookSafetyAlertCreated path: - type: object key: WebhookSafetyOrgAlertCreated path: - id: images-streaming title: Image Streaming description: 'Stream image generation and editing in real time with server-sent events. [Learn more about image streaming](https://developers.openai.com/api/docs/guides/image-generation). ' navigationGroup: endpoints sections: - type: object key: ImageGenPartialImageEvent path: - type: object key: ImageGenCompletedEvent path: - type: object key: ImageEditPartialImageEvent path: - type: object key: ImageEditCompletedEvent path: - id: realtime-client-events title: Client events description: 'These are events that the OpenAI Realtime WebSocket server will accept from the client. ' navigationGroup: realtime sections: - type: object key: RealtimeClientEventSessionUpdate path: - type: object key: RealtimeClientEventInputAudioBufferAppend path: - type: object key: RealtimeClientEventInputAudioBufferCommit path: - type: object key: RealtimeClientEventInputAudioBufferClear path: - type: object key: RealtimeClientEventConversationItemCreate path: - type: object key: RealtimeClientEventConversationItemRetrieve path: - type: object key: RealtimeClientEventConversationItemTruncate path: - type: object key: RealtimeClientEventConversationItemDelete path: - type: object key: RealtimeClientEventResponseCreate path: - type: object key: RealtimeClientEventResponseCancel path: - type: object key: RealtimeClientEventOutputAudioBufferClear path: - id: realtime-server-events title: Server events description: 'These are events emitted from the OpenAI Realtime WebSocket server to the client. ' navigationGroup: realtime sections: - type: object key: RealtimeServerEventError path: - type: object key: RealtimeServerEventSessionCreated path: - type: object key: RealtimeServerEventSessionUpdated path: - type: object key: RealtimeServerEventConversationItemAdded path: - type: object key: RealtimeServerEventConversationItemDone path: - type: object key: RealtimeServerEventConversationItemRetrieved path: - type: object key: RealtimeServerEventConversationItemInputAudioTranscriptionCompleted path: - type: object key: RealtimeServerEventConversationItemInputAudioTranscriptionDelta path: - type: object key: RealtimeServerEventConversationItemInputAudioTranscriptionSegment path: - type: object key: RealtimeServerEventConversationItemInputAudioTranscriptionFailed path: - type: object key: RealtimeServerEventConversationItemTruncated path: - type: object key: RealtimeServerEventConversationItemDeleted path: - type: object key: RealtimeServerEventInputAudioBufferCommitted path: - type: object key: RealtimeServerEventInputAudioBufferDtmfEventReceived path: - type: object key: RealtimeServerEventInputAudioBufferCleared path: - type: object key: RealtimeServerEventInputAudioBufferSpeechStarted path: - type: object key: RealtimeServerEventInputAudioBufferSpeechStopped path: - type: object key: RealtimeServerEventInputAudioBufferTimeoutTriggered path: - type: object key: RealtimeServerEventOutputAudioBufferStarted path: - type: object key: RealtimeServerEventOutputAudioBufferStopped path: - type: object key: RealtimeServerEventOutputAudioBufferCleared path: - type: object key: RealtimeServerEventResponseCreated path: - type: object key: RealtimeServerEventResponseDone path: - type: object key: RealtimeServerEventResponseOutputItemAdded path: - type: object key: RealtimeServerEventResponseOutputItemDone path: - type: object key: RealtimeServerEventResponseContentPartAdded path: - type: object key: RealtimeServerEventResponseContentPartDone path: - type: object key: RealtimeServerEventResponseTextDelta path: - type: object key: RealtimeServerEventResponseTextDone path: - type: object key: RealtimeServerEventResponseAudioTranscriptDelta path: - type: object key: RealtimeServerEventResponseAudioTranscriptDone path: - type: object key: RealtimeServerEventResponseAudioDelta path: - type: object key: RealtimeServerEventResponseAudioDone path: - type: object key: RealtimeServerEventResponseFunctionCallArgumentsDelta path: - type: object key: RealtimeServerEventResponseFunctionCallArgumentsDone path: - type: object key: RealtimeServerEventResponseMCPCallArgumentsDelta path: - type: object key: RealtimeServerEventResponseMCPCallArgumentsDone path: - type: object key: RealtimeServerEventResponseMCPCallInProgress path: - type: object key: RealtimeServerEventResponseMCPCallCompleted path: - type: object key: RealtimeServerEventResponseMCPCallFailed path: - type: object key: RealtimeServerEventMCPListToolsInProgress path: - type: object key: RealtimeServerEventMCPListToolsCompleted path: - type: object key: RealtimeServerEventMCPListToolsFailed path: - type: object key: RealtimeServerEventRateLimitsUpdated path: - id: realtime-translation-client-events title: Translation client events description: 'These are events that the OpenAI Realtime Translation WebSocket server will accept from the client. ' navigationGroup: realtime sections: - type: object key: RealtimeTranslationClientEventSessionUpdate path: - type: object key: RealtimeTranslationClientEventInputAudioBufferAppend path: - type: object key: RealtimeTranslationClientEventSessionClose path: - id: realtime-translation-server-events title: Translation server events description: 'These are events emitted from the OpenAI Realtime Translation WebSocket server to the client. ' navigationGroup: realtime sections: - type: object key: RealtimeServerEventError path: - type: object key: RealtimeTranslationServerEventSessionCreated path: - type: object key: RealtimeTranslationServerEventSessionUpdated path: - type: object key: RealtimeTranslationServerEventSessionClosed path: - type: object key: RealtimeTranslationServerEventSessionInputTranscriptDelta path: - type: object key: RealtimeTranslationServerEventSessionOutputTranscriptDelta path: - type: object key: RealtimeTranslationServerEventSessionOutputAudioDelta path: - id: chat-streaming title: Streaming description: 'Stream Chat Completions in real time. Receive chunks of completions returned from the model using server-sent events. [Learn more](https://developers.openai.com/api/docs/guides/streaming-responses). ' navigationGroup: chat sections: - type: object key: CreateChatCompletionStreamResponse path: streaming - id: assistants-streaming title: Streaming beta: true description: 'Stream the result of executing a Run or resuming a Run after submitting tool outputs. You can stream events from the [Create Thread and Run](https://developers.openai.com/api/docs/assistants/migration), [Create Run](https://developers.openai.com/api/docs/assistants/migration), and [Submit Tool Outputs](https://developers.openai.com/api/docs/assistants/migration) endpoints by passing `"stream": true`. The response will be a [Server-Sent events](https://html.spec.whatwg.org/multipage/server-sent-events.html#server-sent-events) stream. Our Node and Python SDKs provide helpful utilities to make streaming easy. Reference the [Assistants API quickstart](https://developers.openai.com/api/docs/assistants/migration) to learn more. ' navigationGroup: assistants sections: - type: object key: AssistantStreamEvent path: events - id: realtime-beta-client-events title: Realtime Beta client events description: 'These are events that the OpenAI Realtime WebSocket server will accept from the client. ' navigationGroup: legacy sections: - type: object key: RealtimeBetaClientEventSessionUpdate path: - type: object key: RealtimeBetaClientEventInputAudioBufferAppend path: - type: object key: RealtimeBetaClientEventInputAudioBufferCommit path: - type: object key: RealtimeBetaClientEventInputAudioBufferClear path: - type: object key: RealtimeBetaClientEventConversationItemCreate path: - type: object key: RealtimeBetaClientEventConversationItemRetrieve path: - type: object key: RealtimeBetaClientEventConversationItemTruncate path: - type: object key: RealtimeBetaClientEventConversationItemDelete path: - type: object key: RealtimeBetaClientEventResponseCreate path: - type: object key: RealtimeBetaClientEventResponseCancel path: - type: object key: RealtimeBetaClientEventTranscriptionSessionUpdate path: - type: object key: RealtimeBetaClientEventOutputAudioBufferClear path: - id: realtime-beta-server-events title: Realtime Beta server events description: 'These are events emitted from the OpenAI Realtime WebSocket server to the client. ' navigationGroup: legacy sections: - type: object key: RealtimeBetaServerEventError path: - type: object key: RealtimeBetaServerEventSessionCreated path: - type: object key: RealtimeBetaServerEventSessionUpdated path: - type: object key: RealtimeBetaServerEventTranscriptionSessionCreated path: - type: object key: RealtimeBetaServerEventTranscriptionSessionUpdated path: - type: object key: RealtimeBetaServerEventConversationItemCreated path: - type: object key: RealtimeBetaServerEventConversationItemRetrieved path: - type: object key: RealtimeBetaServerEventConversationItemInputAudioTranscriptionCompleted path: - type: object key: RealtimeBetaServerEventConversationItemInputAudioTranscriptionDelta path: - type: object key: RealtimeBetaServerEventConversationItemInputAudioTranscriptionSegment path: - type: object key: RealtimeBetaServerEventConversationItemInputAudioTranscriptionFailed path: - type: object key: RealtimeBetaServerEventConversationItemTruncated path: - type: object key: RealtimeBetaServerEventConversationItemDeleted path: - type: object key: RealtimeBetaServerEventInputAudioBufferCommitted path: - type: object key: RealtimeBetaServerEventInputAudioBufferCleared path: - type: object key: RealtimeBetaServerEventInputAudioBufferSpeechStarted path: - type: object key: RealtimeBetaServerEventInputAudioBufferSpeechStopped path: - type: object key: RealtimeServerEventInputAudioBufferTimeoutTriggered path: - type: object key: RealtimeBetaServerEventResponseCreated path: - type: object key: RealtimeBetaServerEventResponseDone path: - type: object key: RealtimeBetaServerEventResponseOutputItemAdded path: - type: object key: RealtimeBetaServerEventResponseOutputItemDone path: - type: object key: RealtimeBetaServerEventResponseContentPartAdded path: - type: object key: RealtimeBetaServerEventResponseContentPartDone path: - type: object key: RealtimeBetaServerEventResponseTextDelta path: - type: object key: RealtimeBetaServerEventResponseTextDone path: - type: object key: RealtimeBetaServerEventResponseAudioTranscriptDelta path: - type: object key: RealtimeBetaServerEventResponseAudioTranscriptDone path: - type: object key: RealtimeBetaServerEventResponseAudioDelta path: - type: object key: RealtimeBetaServerEventResponseAudioDone path: - type: object key: RealtimeBetaServerEventResponseFunctionCallArgumentsDelta path: - type: object key: RealtimeBetaServerEventResponseFunctionCallArgumentsDone path: - type: object key: RealtimeBetaServerEventResponseMCPCallArgumentsDelta path: - type: object key: RealtimeBetaServerEventResponseMCPCallArgumentsDone path: - type: object key: RealtimeBetaServerEventResponseMCPCallInProgress path: - type: object key: RealtimeBetaServerEventResponseMCPCallCompleted path: - type: object key: RealtimeBetaServerEventResponseMCPCallFailed path: - type: object key: RealtimeBetaServerEventMCPListToolsInProgress path: - type: object key: RealtimeBetaServerEventMCPListToolsCompleted path: - type: object key: RealtimeBetaServerEventMCPListToolsFailed path: - type: object key: RealtimeBetaServerEventRateLimitsUpdated path: - id: live-client-events title: Client events description: Initialize a primary WebSocket with session.start and wait for session.started before sending other events. WebRTC creation starts the session for you. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules. navigationGroup: live sections: - type: object key: LiveSessionStartEvent path: - type: object key: LiveForkSessionStartEvent path: - type: object key: LiveSessionUpdateParam path: - type: object key: LiveInputAudioAppendEvent path: - type: object key: LiveInputAudioMuteParam path: - type: object key: LiveInputAudioUnmuteParam path: - type: object key: LiveInstructionsAppendParam path: - type: object key: LiveThinkingAppendParam path: - type: object key: LiveCommentaryAppendParam path: - type: object key: LiveResponseItemCreateParam path: - type: object key: LiveResponseCreateParam path: - type: object key: LiveSessionCloseParam path: - id: live-server-events title: Server events description: Live server events. Responses delegation lifecycle events arrive inside response.event, not as top-level response events. Start with the [Live prompting guide](https://developers.openai.com/api/docs/guides/live-prompting) to design frontend instructions and delegation policy; see [backend prompting](https://developers.openai.com/api/docs/guides/live-delegation#start-with-your-existing-backend-prompt) for tools and business rules. navigationGroup: live sections: - type: object key: LiveSessionStarted path: - type: object key: LiveSessionUpdated path: - type: object key: LiveInputAudioMuted path: - type: object key: LiveInputAudioUnmuted path: - type: object key: LiveInstructionsAppended path: - type: object key: LiveThinkingAppended path: - type: object key: LiveCommentaryAppended path: - type: object key: LiveOutputAudioDelta path: - type: object key: LiveInputTranscriptDelta path: - type: object key: LiveOutputTranscriptDelta path: - type: object key: LiveDelegationCreated path: - type: object key: LiveResponseEvent path: - type: object key: LiveSessionUsageUpdated path: - type: object key: LiveSessionClosed path: - type: object key: LiveErrorEvent path: - type: object key: LiveInfoEvent path: