Claude Fable 5.2

本页说明本站网关实际支持的调用方式。价格以模型详情页为准：https://modelfold.ai/models/claude-fable-5-2

接口

POST /chat/completions

完整 URL: https://modelfold.ai/v1/chat/completions

鉴权：所有请求都需要 Authorization: Bearer <API_KEY> 请求头。

本站将此请求转换为模型上游协议，返回 OpenAI 风格的对话结果。stream: true 时以 SSE 返回。编程智能体及原生协议接入见 AI Agent，模型 ID 同样是 claude-fable-5-2。

请求参数

请求体 (application/json)

参数	类型	必填	说明
model	string	是	可选值：claude-fable-5-2。 示例：claude-fable-5-2。
messages	array<object>	是	minItems: 1.
messages[].role	string	是	可选值：system / user / assistant。 示例：user。
messages[].content	string | array<object>	是	字符串，或内容数组：{"type":"text","text":"..."} 与 {"type":"image_url","image_url":{"url":"data:image/png;base64,..."}}。支持图片输入：image_url 请用 data:image base64 地址（png / jpeg / webp / gif），建议单张不超过 5MB、单次请求最多 10 张（与网页对话一致）；http(s) 图片链接只会原样转发，不保证每个模型都能读取。
max_tokens	integer	否	默认值：1024。 示例：1024。
temperature	number	否	—

请求示例

cURL

curl -X POST "https://modelfold.ai/v1/chat/completions" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-fable-5-2",
  "messages": [
    {
      "role": "user",
      "content": "In one sentence, what does a tide table tell a sailor?"
    }
  ],
  "max_tokens": 80
}'

OpenAI SDK · Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://modelfold.ai/v1", api_key=os.environ["MODELFOLD_API_KEY"])

resp = client.chat.completions.create(
    model="claude-fable-5-2",
    messages=[
        {
            "role": "user",
            "content": "In one sentence, what does a tide table tell a sailor?",
        },
    ],
)
print(resp.choices[0].message.content)

OpenAI SDK · Node

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://modelfold.ai/v1", apiKey: process.env.MODELFOLD_API_KEY });

const resp = await client.chat.completions.create({
  model: "claude-fable-5-2",
  messages: [{"role":"user","content":"In one sentence, what does a tide table tell a sailor?"}],
});
console.log(resp.choices[0].message.content);

Python

import os
import requests

resp = requests.post(
    "https://modelfold.ai/v1/chat/completions",
    headers={
        "Authorization": "Bearer " + os.environ["MODELFOLD_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "model": "claude-fable-5-2",
        "messages": [
            {
                "role": "user",
                "content": "In one sentence, what does a tide table tell a sailor?",
            },
        ],
        "max_tokens": 80,
    },
)
print(resp.json())

Node.js

const resp = await fetch("https://modelfold.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MODELFOLD_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "claude-fable-5-2",
    "messages": [
      {
        "role": "user",
        "content": "In one sentence, what does a tide table tell a sailor?"
      }
    ],
    "max_tokens": 80
  }),
});
console.log(await resp.json());

Go

package main

import (
	"fmt"
	"io"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"model":"claude-fable-5-2","messages":[{"role":"user","content":"In one sentence, what does a tide table tell a sailor?"}],"max_tokens":80}`)
	req, _ := http.NewRequest("POST", "https://modelfold.ai/v1/chat/completions", body)
	req.Header.Set("Authorization", "Bearer " + os.Getenv("MODELFOLD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
	out, _ := io.ReadAll(resp.Body)
	fmt.Println(string(out))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        String body = "{\"model\":\"claude-fable-5-2\",\"messages\":[{\"role\":\"user\",\"content\":\"In one sentence, what does a tide table tell a sailor?\"}],\"max_tokens\":80}";
        HttpRequest req = HttpRequest.newBuilder()
            .uri(URI.create("https://modelfold.ai/v1/chat/completions"))
            .header("Authorization", "Bearer " + System.getenv("MODELFOLD_API_KEY"))
            .header("Content-Type", "application/json")
            .method("POST", HttpRequest.BodyPublishers.ofString(body))
            .build();
        HttpResponse<String> resp = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString());
        System.out.println(resp.body());
    }
}

PHP

<?php
$ch = curl_init('https://modelfold.ai/v1/chat/completions');
curl_setopt_array($ch, [
    CURLOPT_CUSTOMREQUEST => "POST",
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . getenv("MODELFOLD_API_KEY"),
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => '{"model":"claude-fable-5-2","messages":[{"role":"user","content":"In one sentence, what does a tide table tell a sailor?"}],"max_tokens":80}',
]);
echo curl_exec($ch);
curl_close($ch);

C#

using System;
using System.Net.Http;
using System.Text;

var client = new HttpClient();
var req = new HttpRequestMessage(new HttpMethod("POST"), "https://modelfold.ai/v1/chat/completions");
req.Headers.TryAddWithoutValidation("Authorization", "Bearer " + Environment.GetEnvironmentVariable("MODELFOLD_API_KEY"));
req.Content = new StringContent("{\"model\":\"claude-fable-5-2\",\"messages\":[{\"role\":\"user\",\"content\":\"In one sentence, what does a tide table tell a sailor?\"}],\"max_tokens\":80}", Encoding.UTF8, "application/json");
var resp = await client.SendAsync(req);
Console.WriteLine(await resp.Content.ReadAsStringAsync());

{
  "model": "claude-fable-5-2",
  "messages": [
    {
      "role": "user",
      "content": "In one sentence, what does a tide table tell a sailor?"
    }
  ],
  "max_tokens": 80
}

图片输入示例

图片放在 content 数组里，用 data URL 传入。把 BASE64_IMAGE_DATA 换成图片文件的 base64。

cURL

curl -X POST "https://modelfold.ai/v1/chat/completions" \
  -H "Authorization: Bearer $MODELFOLD_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "claude-fable-5-2",
  "messages": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "用一句话描述这张图。"
        },
        {
          "type": "image_url",
          "image_url": {
            "url": "data:image/png;base64,<BASE64_IMAGE_DATA>"
          }
        }
      ]
    }
  ],
  "max_tokens": 512
}'

OpenAI SDK · Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://modelfold.ai/v1", api_key=os.environ["MODELFOLD_API_KEY"])

resp = client.chat.completions.create(
    model="claude-fable-5-2",
    messages=[
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "用一句话描述这张图。",
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "data:image/png;base64,<BASE64_IMAGE_DATA>",
                    },
                },
            ],
        },
    ],
)
print(resp.choices[0].message.content)

OpenAI SDK · Node

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://modelfold.ai/v1", apiKey: process.env.MODELFOLD_API_KEY });

const resp = await client.chat.completions.create({
  model: "claude-fable-5-2",
  messages: [{"role":"user","content":[{"type":"text","text":"用一句话描述这张图。"},{"type":"image_url","image_url":{"url":"data:image/png;base64,<BASE64_IMAGE_DATA>"}}]}],
});
console.log(resp.choices[0].message.content);

Python

import os
import requests

resp = requests.post(
    "https://modelfold.ai/v1/chat/completions",
    headers={
        "Authorization": "Bearer " + os.environ["MODELFOLD_API_KEY"],
        "Content-Type": "application/json",
    },
    json={
        "model": "claude-fable-5-2",
        "messages": [
            {
                "role": "user",
                "content": [
                    {
                        "type": "text",
                        "text": "用一句话描述这张图。",
                    },
                    {
                        "type": "image_url",
                        "image_url": {
                            "url": "data:image/png;base64,<BASE64_IMAGE_DATA>",
                        },
                    },
                ],
            },
        ],
        "max_tokens": 512,
    },
)
print(resp.json())

Node.js

const resp = await fetch("https://modelfold.ai/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer " + process.env.MODELFOLD_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "claude-fable-5-2",
    "messages": [
      {
        "role": "user",
        "content": [
          {
            "type": "text",
            "text": "用一句话描述这张图。"
          },
          {
            "type": "image_url",
            "image_url": {
              "url": "data:image/png;base64,<BASE64_IMAGE_DATA>"
            }
          }
        ]
      }
    ],
    "max_tokens": 512
  }),
});
console.log(await resp.json());

Go

package main

import (
	"fmt"
	"io"
	"net/http"
	"os"
	"strings"
)

func main() {
	body := strings.NewReader(`{"model":"claude-fable-5-2","messages":[{"role":"user","content":[{"type":"text","text":"用一句话描述这张图。"},{"type":"image_url","image_url":{"url":"data:image/png;base64,<BASE64_IMAGE_DATA>"}}]}],"max_tokens":512}`)
	req, _ := http.NewRequest("POST", "https://modelfold.ai/v1/chat/completions", body)
	req.Header.Set("Authorization", "Bearer " + os.Getenv("MODELFOLD_API_KEY"))
	req.Header.Set("Content-Type", "application/json")
	resp, err := http.DefaultClient.Do(req)
	if err != nil {
		panic(err)
	}
	defer resp.Body.Close()
	out, _ := io.ReadAll(resp.Body)
	fmt.Println(string(out))
}

Java

import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;

public class Main {
    public static void main(String[] args) throws Exception {
        String body = "{\"model\":\"claude-fable-5-2\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"用一句话描述这张图。\"},{\"type\":\"image_url\",\"image_url\":{\"url\":\"data:image/png;base64,<BASE64_IMAGE_DATA>\"}}]}],\"max_tokens\":512}";
        HttpRequest req = HttpRequest.newBuilder()
            .uri(URI.create("https://modelfold.ai/v1/chat/completions"))
            .header("Authorization", "Bearer " + System.getenv("MODELFOLD_API_KEY"))
            .header("Content-Type", "application/json")
            .method("POST", HttpRequest.BodyPublishers.ofString(body))
            .build();
        HttpResponse<String> resp = HttpClient.newHttpClient().send(req, HttpResponse.BodyHandlers.ofString());
        System.out.println(resp.body());
    }
}

PHP

<?php
$ch = curl_init('https://modelfold.ai/v1/chat/completions');
curl_setopt_array($ch, [
    CURLOPT_CUSTOMREQUEST => "POST",
    CURLOPT_RETURNTRANSFER => true,
    CURLOPT_HTTPHEADER => [
        'Authorization: Bearer ' . getenv("MODELFOLD_API_KEY"),
        'Content-Type: application/json',
    ],
    CURLOPT_POSTFIELDS => '{"model":"claude-fable-5-2","messages":[{"role":"user","content":[{"type":"text","text":"用一句话描述这张图。"},{"type":"image_url","image_url":{"url":"data:image/png;base64,<BASE64_IMAGE_DATA>"}}]}],"max_tokens":512}',
]);
echo curl_exec($ch);
curl_close($ch);

C#

using System;
using System.Net.Http;
using System.Text;

var client = new HttpClient();
var req = new HttpRequestMessage(new HttpMethod("POST"), "https://modelfold.ai/v1/chat/completions");
req.Headers.TryAddWithoutValidation("Authorization", "Bearer " + Environment.GetEnvironmentVariable("MODELFOLD_API_KEY"));
req.Content = new StringContent("{\"model\":\"claude-fable-5-2\",\"messages\":[{\"role\":\"user\",\"content\":[{\"type\":\"text\",\"text\":\"用一句话描述这张图。\"},{\"type\":\"image_url\",\"image_url\":{\"url\":\"data:image/png;base64,<BASE64_IMAGE_DATA>\"}}]}],\"max_tokens\":512}", Encoding.UTF8, "application/json");
var resp = await client.SendAsync(req);
Console.WriteLine(await resp.Content.ReadAsStringAsync());

响应

200 — 对话完成；usage 返回请求用量。

{
  "ok": true,
  "object": "chat.completion",
  "model": "claude-fable-5-2",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A tide table tells a sailor the predicted times and heights of high and low tides at a given location, so they can know when the water will be deep enough to navigate safely."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {}
}