Chat Completions

POST /v1/chat/completions · 兼容 OpenAI Chat API,支持 GPT-4o-mini 与 Grok 系列,流式 SSE 与 function calling 透传上游。

完全兼容 OpenAI Chat Completions API。所有标准参数 (messages / temperature / top_p / stream / tools / response_format 等) 透传,可直接用 OpenAI SDK 调用。

支持模型见模型一览。

调用示例

curl https://api.cokeapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-coke-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [
      {"role": "system", "content": "你是简洁的助手"},
      {"role": "user", "content": "用一句话介绍 CokeAPI"}
    ]
  }'

curl -N https://api.cokeapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-coke-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-4.20-fast",
    "messages": [{"role": "user", "content": "讲一个三句的笑话"}],
    "stream": true
  }'

curl https://api.cokeapi.com/v1/chat/completions \
  -H "Authorization: Bearer sk-coke-xxxxxxxx" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o-mini",
    "messages": [{"role": "user", "content": "北京今天天气?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_weather",
        "description": "查询某城市天气",
        "parameters": {
          "type": "object",
          "properties": {"city": {"type": "string"}},
          "required": ["city"]
        }
      }
    }]
  }'

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cokeapi.com/v1",
    api_key="sk-coke-xxxxxxxx",
)

resp = client.chat.completions.create(
    model="gpt-4o-mini",
    messages=[
        {"role": "system", "content": "你是简洁的助手"},
        {"role": "user", "content": "用一句话介绍 CokeAPI"},
    ],
)
print(resp.choices[0].message.content)

from openai import OpenAI

client = OpenAI(
    base_url="https://api.cokeapi.com/v1",
    api_key="sk-coke-xxxxxxxx",
)

stream = client.chat.completions.create(
    model="grok-4.20-fast",
    messages=[{"role": "user", "content": "讲一个三句的笑话"}],
    stream=True,
)
for chunk in stream:
    delta = chunk.choices[0].delta.content or ""
    print(delta, end="", flush=True)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cokeapi.com/v1",
  apiKey: process.env.COKEAPI_KEY,
});

const resp = await client.chat.completions.create({
  model: "gpt-4o-mini",
  messages: [
    { role: "system", content: "你是简洁的助手" },
    { role: "user", content: "用一句话介绍 CokeAPI" },
  ],
});
console.log(resp.choices[0].message.content);

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.cokeapi.com/v1",
  apiKey: process.env.COKEAPI_KEY,
});

const stream = await client.chat.completions.create({
  model: "grok-4.20-fast",
  messages: [{ role: "user", content: "讲一个三句的笑话" }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

请求参数

完全兼容 OpenAI,无差异。下表只列重点字段:

Prop

Type

响应示例

非流式

{
  "id": "chatcmpl-01HX...",
  "object": "chat.completion",
  "created": 1714200000,
  "model": "gpt-4o-mini",
  "choices": [{
    "index": 0,
    "message": {
      "role": "assistant",
      "content": "CokeAPI 是把 GPT 与 GROK 能力封装成 OpenAI 兼容协议的 AIGC 接口服务。"
    },
    "finish_reason": "stop"
  }],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 32,
    "total_tokens": 60
  }
}

流式 (SSE)

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"role":"assistant"}}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"content":"Coke"}}]}

data: {"id":"chatcmpl-...","object":"chat.completion.chunk","choices":[{"delta":{"content":"API "}}]}

...

data: {"id":"chatcmpl-...","choices":[{"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":28,"completion_tokens":32,"total_tokens":60}}

data: [DONE]

CokeAPI 自动给流式请求注入 stream_options: { include_usage: true },最后一个 chunk 一定会带 usage,便于按 token 计费对账。

计费

按 prompt_tokens 与 completion_tokens 分别计算,模型不同单价不同。完整单价见模型与价格。

错误码

code	type	含义	HTTP
400101	`invalid_param`	参数错误	400
400401	`insufficient_points`	余额不足	400
401104	`api_key_invalid`	API Key 无效	401
429101	`rate_limit_exceeded`	RPM 超限	429
429302	`daily_quota_exceeded`	每日配额耗尽	429
502201	`upstream_unavailable`	上游服务暂不可用	502

注意事项

流式调用必须 关闭客户端缓冲;Python 用 iter_lines,Node 用 for await (const chunk),浏览器用 EventSource 或 ReadableStream。
Function calling 字段完全透传上游,平台不做语义解析。
上游模型 context 不同 (gpt-4o-mini = 128K, grok-4.20 = 256K),超长会被截断或返回 400。
内容审核由上游执行,被拒返回的错误 message 不算 CokeAPI 故障,仍计费。

On this page