使用 CometAPI POST /v1/chat/completions 发送多消息对话,并通过流式输出、temperature 和 max_tokens 控制来获取 LLM 回复。
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key="<COMETAPI_KEY>",
)
completion = client.chat.completions.create(
model="gpt-5.4",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"},
],
)
print(completion.choices[0].message){
"id": "chatcmpl-DNA27oKtBUL8TmbGpBM3B3zhWgYfZ",
"object": "chat.completion",
"created": 1774412483,
"model": "gpt-4.1-nano-2025-04-14",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Four",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 29,
"completion_tokens": 2,
"total_tokens": 31,
"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",
"system_fingerprint": "fp_490a4ad033"
}model 参数即可在不同模型之间切换。
base_url 改为 https://api.cometapi.com/v1 即可与 CometAPI 配合使用。reasoning_effort 仅适用于推理模型(o-series、GPT-5.1+),某些模型也可能不支持 logprobs 或 n > 1。o1-pro),请改用 responses 端点。| 角色 | 描述 |
|---|---|
system | 设置助手的行为和个性。放置在对话开头。 |
developer | 在较新的模型(o1+)中替代 system。无论用户输入如何,都提供模型应遵循的指令。 |
user | 来自最终用户的消息。 |
assistant | 先前的模型响应,用于维持对话历史。 |
tool | 工具/函数调用的结果。必须包含与原始工具调用匹配的 tool_call_id。 |
developer 而不是 system。两者都可用,但 developer 能提供更强的指令遵循行为。content 的数组格式来发送多模态消息:
{
"role": "user",
"content": [
{"type": "text", "text": "Describe this image"},
{
"type": "image_url",
"image_url": {
"url": "https://example.com/image.png",
"detail": "high"
}
}
]
}
detail 参数控制图像分析深度:
low —— 更快,使用更少的 tokens(固定成本)high —— 更详细的分析,消耗更多 tokensauto —— 由模型决定(默认)stream 设置为 true 时,响应会以 Server-Sent Events (SSE) 的形式传输。每个事件都包含一个带有增量内容的 chat.completion.chunk 对象:
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"role":"assistant"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"Hello"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{"content":"!"},"finish_reason":null}]}
data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}
data: [DONE]
stream_options.include_usage 设置为 true。使用量数据会出现在 [DONE] 之前的最后一个 chunk 中。response_format 强制模型返回符合特定 schema 的有效 JSON:
{
"response_format": {
"type": "json_schema",
"json_schema": {
"name": "result",
"strict": true,
"schema": {
"type": "object",
"properties": {
"answer": {"type": "string"},
"confidence": {"type": "number"}
},
"required": ["answer", "confidence"],
"additionalProperties": false
}
}
}
}
json_schema)可保证输出与您的 schema 严格匹配。JSON Object 模式(json_object)仅保证返回的是有效 JSON——并不保证具体结构。{
"tools": [
{
"type": "function",
"function": {
"name": "get_weather",
"description": "Get current weather for a city",
"parameters": {
"type": "object",
"properties": {
"location": {"type": "string", "description": "City name"}
},
"required": ["location"]
}
}
}
],
"tool_choice": "auto"
}
finish_reason 会是 tool_calls,并且 message.tool_calls 数组会包含函数名称和参数。随后,您需要执行该函数,并将结果作为一个带有匹配 tool_call_id 的 tool 消息发送回去。
| 字段 | 说明 |
|---|---|
id | 唯一的补全标识符(例如 chatcmpl-abc123)。 |
object | 始终为 chat.completion。 |
model | 生成该响应的模型(可能包含版本后缀)。 |
choices | 补全候选数组(通常为 1,除非 n > 1)。 |
choices[].message | assistant 的响应消息,包含 role、content,以及可选的 tool_calls。 |
choices[].finish_reason | 模型停止的原因:stop、length、tool_calls 或 content_filter。 |
usage | Token 消耗明细:prompt_tokens、completion_tokens、total_tokens,以及更详细的子项统计。 |
system_fingerprint | 用于调试可复现性的后端配置指纹。 |
各提供商的参数支持情况
| Parameter | OpenAI GPT | Claude (via compat) | Gemini (via compat) |
|---|---|---|---|
temperature | 0–2 | 0–1 | 0–2 |
top_p | 0–1 | 0–1 | 0–1 |
n | 1–128 | 仅支持 1 | 1–8 |
stop | 最多 4 个 | 最多 4 个 | 最多 5 个 |
tools | ✅ | ✅ | ✅ |
response_format | ✅ | ✅ (json_schema) | ✅ |
logprobs | ✅ | ❌ | ❌ |
reasoning_effort | o-series、GPT-5.1+ | ❌ | ❌(Gemini 原生请使用 thinking) |
max_tokens 与 max_completion_tokens
max_tokens — 旧版参数。适用于大多数模型,但对较新的 OpenAI 模型已被弃用。max_completion_tokens — GPT-4.1、GPT-5 系列和 o-series 模型推荐使用的参数。推理模型必须使用该参数,因为它同时包含输出 tokens 和 reasoning tokens。system 与 developer role
system — 传统的指令角色。适用于所有模型。developer — 随 o1 模型引入。对较新的模型提供更强的指令遵循能力。在旧模型上会回退为 system 的行为。developer。429 Too Many Requests 时,请实现指数退避:
import time
import random
from openai import OpenAI, RateLimitError
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key="<COMETAPI_KEY>",
)
def chat_with_retry(messages, max_retries=3):
for i in range(max_retries):
try:
return client.chat.completions.create(
model="gpt-5.4",
messages=messages,
)
except RateLimitError:
if i < max_retries - 1:
wait_time = (2 ** i) + random.random()
time.sleep(wait_time)
else:
raise
messages 数组中:
messages = [
{"role": "developer", "content": "You are a helpful assistant."},
{"role": "user", "content": "What is Python?"},
{"role": "assistant", "content": "Python is a high-level programming language..."},
{"role": "user", "content": "What are its main advantages?"},
]
finish_reason 是什么意思?| Value | Meaning |
|---|---|
stop | 自然完成,或命中停止序列。 |
length | 达到 max_tokens 或 max_completion_tokens 限制。 |
tool_calls | 模型调用了一个或多个工具/函数。 |
content_filter | 由于内容策略,输出被过滤。 |
max_completion_tokens 限制输出长度。gpt-5.4-mini 或 gpt-5.4-nano)。usage 响应字段中监控 token 使用情况。Bearer token authentication. Use your CometAPI key.
Model ID to use for this request. See the Models page for current options.
"gpt-4.1"
A list of messages forming the conversation. Each message has a role (system, user, assistant, or developer) and content (text string or multimodal content array).
Show child attributes
If true, partial response tokens are delivered incrementally via server-sent events (SSE). The stream ends with a data: [DONE] message.
Sampling temperature between 0 and 2. Higher values (e.g., 0.8) produce more random output; lower values (e.g., 0.2) make output more focused and deterministic. Recommended to adjust this or top_p, but not both.
0 <= x <= 2Nucleus sampling parameter. The model considers only the tokens whose cumulative probability reaches top_p. For example, 0.1 means only the top 10% probability tokens are considered. Recommended to adjust this or temperature, but not both.
0 <= x <= 1Number of completion choices to generate for each input message. Defaults to 1.
Up to 4 sequences where the API will stop generating further tokens. Can be a string or an array of strings.
Maximum number of tokens to generate in the completion. The total of input + output tokens is capped by the model's context length.
Number between -2.0 and 2.0. Positive values penalize tokens based on whether they have already appeared, encouraging the model to explore new topics.
-2 <= x <= 2Number between -2.0 and 2.0. Positive values penalize tokens proportionally to how often they have appeared, reducing verbatim repetition.
-2 <= x <= 2A JSON object mapping token IDs to bias values from -100 to 100. The bias is added to the model's logits before sampling. Values between -1 and 1 subtly adjust likelihood; -100 or 100 effectively ban or force selection of a token.
A unique identifier for your end-user. Helps with abuse detection and monitoring.
An upper bound for the number of tokens to generate, including visible output tokens and reasoning tokens. Use this instead of max_tokens for GPT-4.1+, GPT-5 series, and o-series models.
Specifies the output format. Use {"type": "json_object"} for JSON mode, or {"type": "json_schema", "json_schema": {...}} for strict structured output.
Show child attributes
A list of tools the model may call. Currently supports function type tools.
Show child attributes
Controls how the model selects tools. auto (default): model decides. none: no tools. required: must call a tool.
Whether to return log probabilities of the output tokens.
Number of most likely tokens to return at each position (0-20). Requires logprobs to be true.
0 <= x <= 20Controls the reasoning effort for o-series and GPT-5.1+ models.
low, medium, high Options for streaming. Only valid when stream is true.
Show child attributes
Specifies the processing tier.
auto, default, flex, priority Successful chat completion response.
Unique completion identifier.
"chatcmpl-abc123"
chat.completion "chat.completion"
Unix timestamp of creation.
1774412483
The model used (may include version suffix).
"gpt-5.4-2025-07-16"
Array of completion choices.
Show child attributes
Show child attributes
"default"
"fp_490a4ad033"
from openai import OpenAI
client = OpenAI(
base_url="https://api.cometapi.com/v1",
api_key="<COMETAPI_KEY>",
)
completion = client.chat.completions.create(
model="gpt-5.4",
messages=[
{"role": "system", "content": "You are a helpful assistant."},
{"role": "user", "content": "Hello!"},
],
)
print(completion.choices[0].message){
"id": "chatcmpl-DNA27oKtBUL8TmbGpBM3B3zhWgYfZ",
"object": "chat.completion",
"created": 1774412483,
"model": "gpt-4.1-nano-2025-04-14",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "Four",
"refusal": null,
"annotations": []
},
"logprobs": null,
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 29,
"completion_tokens": 2,
"total_tokens": 31,
"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",
"system_fingerprint": "fp_490a4ad033"
}