创建对话补全
POST/chat/completions
请求体参数JSON
frequency_penalty: 可选 number
介于 -2.0 和 2.0 之间的数字。正值会根据新 token 在迄今为止的文本中出现的频率对其进行惩罚，从而降低模型逐字重复同一行文字的可能性。
最小值-2
最大值2
logit_bias: 可选 map[number]
修改指定 token 在补全中出现的可能性。
接受一个 JSON 对象，该对象将 token（通过其在分词器中的 token ID 指定）映射到关联的偏差值（从 -100 到 100）。从数学上讲，偏差会在采样前添加到模型生成的对数概率（logits）中。具体效果因模型而异，但介于 -1 和 1 之间的值应该会降低或增加被选择的可能性；像 -100 或 100 这样的值应该会导致禁用或独占选择相关的 token。
max_completion_tokens: 可选 number
可为补全生成的 token 数量的上限，包括可见的输出 token 和推理 token。
可以附加到对象的 16 个键值对集合。这对于以结构化格式存储对象的附加信息，以及通过 API 或仪表板查询对象非常有用。
键是最大长度为 64 个字符的字符串。值是最大长度为 512 个字符的字符串。
parallel_tool_calls: 可选的 布尔值
在工具使用期间是否启用并行函数调用。
presence_penalty: 可选 number
介于 -2.0 和 2.0 之间的数字。正值会根据新 token 是否出现在迄今为止的文本中对其进行惩罚，从而增加模型谈论新主题的可能性。
最小值-2
最大值2
prompt_cache_key: 可选 string
由 OpenAI 用于缓存相似请求的响应，以优化您的缓存命中率。取代了 user 字段。了解更多。
safety_identifier: 可选 string
一个稳定的标识符，用于帮助检测可能违反 OpenAI 使用政策的应用用户。该 ID 应为唯一标识每个用户的字符串，最大长度为 64 个字符。我们建议对他们的用户名或邮箱地址进行哈希处理，以避免向我们发送任何身份识别信息。了解更多。
maxLength64
已弃用seed: 可选 number
此功能目前处于 Beta 测试阶段。如果指定了该参数，我们的系统将尽最大努力进行确定性采样，以便使用相同的 seed 和参数的重复请求应返回相同的结果。确定性并不能保证，您应该参考 system_fingerprint 响应参数以监控后端的更改。
最小值-9223372036854776000
最大值9223372036854776000
store: 可选 boolean
是否存储此聊天补全请求的输出，以便在我们的模型蒸馏或评估 (evals)产品中使用。
支持文本和图像输入。注意：超过 8MB 的图像输入将被丢弃。
stream: 可选 boolean
如果设置为 true，模型响应数据将在生成时使用服务器发送事件 (SSE)流式传输到客户端。有关更多信息，请参阅下面的流式传输部分，以及有关如何处理流式传输事件的流式传输响应指南。
temperature: 可选 number
要使用的采样温度，介于 0 和 2 之间。较高的值（如 0.8）会使输出更加随机，而较低的值（如 0.2）会使其更加集中且确定。我们通常建议修改此参数或 top_p，但不要同时修改两者。
最小值0
最大值2
top_logprobs: 可选 number
一个介于 0 到 20 之间的整数，指定在每个 token 位置返回的最大最可能 token 数量，每个 token 都有一个关联的对数概率。在某些情况下，返回的 token 数量可能会少于请求的数量。如果使用此参数，必须将 logprobs 设置为 true。
最小值0
最大值20
top_p: 可选 number
温度采样的替代方案，称为核采样（nucleus sampling），其中模型仅考虑具有 top_p 概率质量的 token 的结果。因此，0.1 意味着仅考虑包含前 10% 概率质量的 token。
我们通常建议修改此参数或 temperature，但不要同时修改两者。
最小值0
maximum1
已弃用user: 可选 string
此字段正在被 safety_identifier 和 prompt_cache_key 取代。请改用 prompt_cache_key 以维持缓存优化。您最终用户的稳定标识符。用于通过更好地分桶相似请求来提高缓存命中率，并帮助 OpenAI 检测和防止滥用。了解更多。
创建对话补全
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
]
}'
{
"id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
"object": "chat.completion",
"created": 1741569952,
"model": "gpt-5.4",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 10,
"total_tokens": 29,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
创建对话补全
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "What is in this image?"
},
{
"type": "image_url",
"image_url": {
"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"
}
}
]
}
],
"max_tokens": 300
}'
{
"id": "chatcmpl-B9MHDbslfkBeAs8l4bebGdFOJ6PeG",
"object": "chat.completion",
"created": 1741570283,
"model": "gpt-5.4",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"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.",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 1117,
"completion_tokens": 46,
"total_tokens": 1163,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}
创建对话补全
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "developer",
"content": "You are a helpful assistant."
},
{
"role": "user",
"content": "Hello!"
}
],
"stream": true
}'
{"id":"chatcmpl-123","object":"chat.completion.chunk","created":1694268190,"model":"gpt-4o-mini", "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-4o-mini", "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-4o-mini", "system_fingerprint": "fp_44709d6fcb", "choices":[{"index":0,"delta":{},"logprobs":null,"finish_reason":"stop"}]}
创建对话补全
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "gpt-5.4",
"messages": [
{
"role": "user",
"content": "What is the weather like in Boston today?"
}
],
"tools": [
{
"type": "function",
"function": {
"name": "get_current_weather",
"description": "Get the current weather in a given location",
"parameters": {
"type": "object",
"properties": {
"location": {
"type": "string",
"description": "The city and state, e.g. San Francisco, CA"
},
"unit": {
"type": "string",
"enum": ["celsius", "fahrenheit"]
}
},
"required": ["location"]
}
}
}
],
"tool_choice": "auto"
}'
{
"id": "chatcmpl-abc123",
"object": "chat.completion",
"created": 1699896916,
"model": "gpt-4o-mini",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": null,
"tool_calls": [
{
"id": "call_abc123",
"type": "function",
"function": {
"name": "get_current_weather",
"arguments": "{\n\"location\": \"Boston, MA\"\n}"
}
}
]
},
"logprobs": null,
"finish_reason": "tool_calls"
}
],
"usage": {
"prompt_tokens": 82,
"completion_tokens": 17,
"total_tokens": 99,
"completion_tokens_details": {
"reasoning_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
}
}
创建对话补全
curl https://api.openai.com/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $OPENAI_API_KEY" \
-d '{
"model": "VAR_chat_model_id",
"messages": [
{
"role": "user",
"content": "Hello!"
}
],
"logprobs": true,
"top_logprobs": 2
}'
{
"id": "chatcmpl-123",
"object": "chat.completion",
"created": 1702685778,
"model": "gpt-4o-mini",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?"
},
"logprobs": {
"content": [
{
"token": "Hello",
"logprob": -0.31725305,
"bytes": [72, 101, 108, 108, 111],
"top_logprobs": [
{
"token": "Hello",
"logprob": -0.31725305,
"bytes": [72, 101, 108, 108, 111]
},
{
"token": "Hi",
"logprob": -1.3190403,
"bytes": [72, 105]
}
]
},
{
"token": "!",
"logprob": -0.02380986,
"bytes": [
33
],
"top_logprobs": [
{
"token": "!",
"logprob": -0.02380986,
"bytes": [33]
},
{
"token": " there",
"logprob": -3.787621,
"bytes": [32, 116, 104, 101, 114, 101]
}
]
},
{
"token": " How",
"logprob": -0.000054669687,
"bytes": [32, 72, 111, 119],
"top_logprobs": [
{
"token": " How",
"logprob": -0.000054669687,
"bytes": [32, 72, 111, 119]
},
{
"token": "<|end|>",
"logprob": -10.953937,
"bytes": null
}
]
},
{
"token": " can",
"logprob": -0.015801601,
"bytes": [32, 99, 97, 110],
"top_logprobs": [
{
"token": " can",
"logprob": -0.015801601,
"bytes": [32, 99, 97, 110]
},
{
"token": " may",
"logprob": -4.161023,
"bytes": [32, 109, 97, 121]
}
]
},
{
"token": " I",
"logprob": -3.7697225e-6,
"bytes": [
32,
73
],
"top_logprobs": [
{
"token": " I",
"logprob": -3.7697225e-6,
"bytes": [32, 73]
},
{
"token": " assist",
"logprob": -13.596657,
"bytes": [32, 97, 115, 115, 105, 115, 116]
}
]
},
{
"token": " assist",
"logprob": -0.04571125,
"bytes": [32, 97, 115, 115, 105, 115, 116],
"top_logprobs": [
{
"token": " assist",
"logprob": -0.04571125,
"bytes": [32, 97, 115, 115, 105, 115, 116]
},
{
"token": " help",
"logprob": -3.1089056,
"bytes": [32, 104, 101, 108, 112]
}
]
},
{
"token": " you",
"logprob": -5.4385737e-6,
"bytes": [32, 121, 111, 117],
"top_logprobs": [
{
"token": " you",
"logprob": -5.4385737e-6,
"bytes": [32, 121, 111, 117]
},
{
"token": " today",
"logprob": -12.807695,
"bytes": [32, 116, 111, 100, 97, 121]
}
]
},
{
"token": " today",
"logprob": -0.0040071653,
"bytes": [32, 116, 111, 100, 97, 121],
"top_logprobs": [
{
"token": " today",
"logprob": -0.0040071653,
"bytes": [32, 116, 111, 100, 97, 121]
},
{
"token": "?",
"logprob": -5.5247097,
"bytes": [63]
}
]
},
{
"token": "?",
"logprob": -0.0008108172,
"bytes": [63],
"top_logprobs": [
{
"token": "?",
"logprob": -0.0008108172,
"bytes": [63]
},
{
"token": "?\n",
"logprob": -7.184561,
"bytes": [63, 10]
}
]
}
]
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 9,
"completion_tokens": 9,
"total_tokens": 18,
"completion_tokens_details": {
"reasoning_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"system_fingerprint": null
}
返回示例
{
"id": "chatcmpl-B9MBs8CjcvOU2jLn4n570S5qMJKcT",
"object": "chat.completion",
"created": 1741569952,
"model": "gpt-5.4",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Hello! How can I assist you today?",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 10,
"total_tokens": 29,
"prompt_tokens_details": {
"cached_tokens": 0,
"audio_tokens": 0
},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0
}
},
"service_tier": "default"
}