知识库 / 开发者

聊天,回复和消息

有三种方式来询问一个模型,在三个格式中客户已经说话,所有这些都运行在相同的模型上,并以相同的方式发票。

为了方便起见，此页面是机器翻译的。英文原件为适用版本。

Chat 完成

OpenAI聊天格式,几乎每个工具都支持的格式. 发送到目前为止的对话并收到下一个消息。

POST https://nymbot.ai/api/v1/chat/completions 需要一个 API 密钥。

只有 model 和 messages 选择的模型不采取的样本参数没有出现错误,所以一个请求器官在模型之间工作。 supported_parameters被拒绝的,而不是被抛弃的,是模特根本做不到的东西:看不见的模特的照片,不能呼叫的模特的工具。

答案是普通的 chat.completion随着成本在 usage.cost (美元)和在 nymbot 对象。 model 是解决的模型id,所以一个短名返回为完整的。 message.reasoning_content与答案分开。

回应

{
  "id": "chatcmpl-5f1c0a9e27d84b3c",
  "object": "chat.completion",
  "created": 1790726400,
  "model": "anthropic/claude-sonnet-5",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "A Lightning invoice is a one-time payment request..."
      },
      "logprobs": null,
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 1240,
    "completion_tokens": 380,
    "total_tokens": 1620,
    "prompt_tokens_details": { "cached_tokens": 0 },
    "completion_tokens_details": { "reasoning_tokens": 0 },
    "cost": 0.01895
  },
  "nymbot": {
    "balance": "pro",
    "charged_credits": 0.162,
    "charged_sats": 16.2,
    "balance_credits": 412.425,
    "balance_sats": 41242.5
  }
}

finish_reason 这是从回来的结果中进行的,因为供应商以不同的方式报告: tool_calls 当模型要求工具时, length 当答案使用每一个允许的代币(或模型花了他们所有的推理,没有写答案), content_filter 经销商拒绝,并 stop 否则。 usage.completion_tokens_details.reasoning_tokens 总是 0:隐藏的推理代币被计算,并在 completion_tokens.

每个终端股票的状态代码列在下方 错误.

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [
      {"role": "system", "content": "Answer in one short paragraph."},
      {"role": "user", "content": "What is a Lightning invoice?"}
    ],
    "max_tokens": 400
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[
        {"role": "system", "content": "Answer in one short paragraph."},
        {"role": "user", "content": "What is a Lightning invoice?"},
    ],
    max_tokens=400,
)
print(reply.choices[0].message.content)
print(reply.usage.cost)

JavaScript

import OpenAI from "openai";

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

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  messages: [
    { role: "system", content: "Answer in one short paragraph." },
    { role: "user", content: "What is a Lightning invoice?" },
  ],
  max_tokens: 400,
});
console.log(reply.choices[0].message.content);
console.log(reply.usage.cost);

流媒体

与 "stream": true 答案作为服务器发送的事件来临,而模型则写入它。 chat.completion.chunk 是 A data: 线,和流结束与 data: [DONE]理性来到了 delta.reasoning_content答案在 delta.content.

流任何可能需要大约 100 秒以上的内容,例如长答案、大答案。 max_tokens 或推理模型. 未流式的请求不会发送任何东西,直到答案完成,你和Nymbot之间的网络可能会在大约100秒后关闭无线连接;模型仍然完成,它所写的东西被加载,但答案丢失。

流量

data: {"id":"chatcmpl-5f1c0a9e27d84b3c","object":"chat.completion.chunk","created":1790726400,"model":"anthropic/claude-sonnet-5","choices":[{"index":0,"delta":{"role":"assistant","content":""},"finish_reason":null}]}

data: {"id":"chatcmpl-5f1c0a9e27d84b3c","object":"chat.completion.chunk","created":1790726400,"model":"anthropic/claude-sonnet-5","choices":[{"index":0,"delta":{"content":"A Lightning invoice"},"finish_reason":null}]}

: keep-alive

data: {"id":"chatcmpl-5f1c0a9e27d84b3c","object":"chat.completion.chunk","created":1790726400,"model":"anthropic/claude-sonnet-5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}]}

data: {"id":"chatcmpl-5f1c0a9e27d84b3c","object":"chat.completion.chunk","created":1790726400,"model":"anthropic/claude-sonnet-5","choices":[],"usage":{"prompt_tokens":1240,"completion_tokens":380,"total_tokens":1620,"cost":0.01895},"nymbot":{"balance":"pro","charged_credits":0.162,"charged_sats":16.2,"balance_credits":412.425,"balance_sats":41242.5}}

data: [DONE]

• 线开始于 : 每15秒钟发送的评论,而模特正在思考。
• 请求 "stream_options": {"include_usage": true} 要得到上面的最后一块,与一个空的 choices,代币计数,成本和 nymbot 对象。
• 如果您提前关闭连接,模型不会停止:Nymbot会读取提供商的其余流量,长达25秒,以获得其代币数目,您会支付提供商报告的费用。
• 在第一个片段之前的错误,如 401 或 402,以其状态代码作为普通的 JSON 返回,而不是作为流。 data: {"error": {…}} 事件,而流程没有结束 [DONE].
• 使用工具的请求,以及OpenAI的响应传输上的模型,不会从提供商传输,他们仍然会用有效的流来响应,一旦答案完成,就会发送。

cURL

curl -N https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "nymbot/auto",
    "stream": true,
    "stream_options": {"include_usage": true},
    "messages": [{"role": "user", "content": "Write a haiku about sats."}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

stream = client.chat.completions.create(
    model="nymbot/auto",
    stream=True,
    stream_options={"include_usage": True},
    messages=[{"role": "user", "content": "Write a haiku about sats."}],
)
for chunk in stream:
    if chunk.choices:
        print(chunk.choices[0].delta.content or "", end="", flush=True)
    elif chunk.usage:
        print("\ncost:", chunk.usage.cost)

JavaScript

import OpenAI from "openai";

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

const stream = await client.chat.completions.create({
  model: "nymbot/auto",
  stream: true,
  stream_options: { include_usage: true },
  messages: [{ role: "user", content: "Write a haiku about sats." }],
});
for await (const chunk of stream) {
  if (chunk.choices.length) process.stdout.write(chunk.choices[0].delta.content || "");
  else if (chunk.usage) console.log("\ncost:", chunk.usage.cost);
}

工具呼叫

描述函数在 tools 并且模型可以要求一个被调用而不是响应。你运行该函数,将其结果添加为一个 tool 同样的消息 tool_call_idNymbot 永遠不會執行您的功能;它將模型的要求傳回給您。

tool_choice 得 "auto", "none", "required" 或 {"type": "function", "function": {"name": "…"}}模型列表标记哪些模型可以调用工具(capabilities.tools) 工具被拒绝 400 unsupported_tool 是 nymbot/auto 以及在OpenAI的响应传输上运行的少数目录模型上,Nymbot无法传输工具。

与 "stream": true,一个有工具的请求运行在一个部分,然后作为一个正常的片段序列发送:角色,一个片段携带每个工具调用,其索引,ID,名称和参数,以及终端片段。

答案,部分

"choices": [
  {
    "index": 0,
    "message": {
      "role": "assistant",
      "content": null,
      "tool_calls": [
        {
          "id": "call_7d2e",
          "type": "function",
          "function": { "name": "get_invoice_status", "arguments": "{\"invoice_id\":\"a41f\"}" }
        }
      ]
    },
    "finish_reason": "tool_calls"
  }
]

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{"role": "user", "content": "Has invoice a41f been paid?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "get_invoice_status",
        "description": "Look up whether an invoice is paid.",
        "parameters": {
          "type": "object",
          "properties": {"invoice_id": {"type": "string"}},
          "required": ["invoice_id"]
        }
      }
    }]
  }'

Python

import json, os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

tools = [{
    "type": "function",
    "function": {
        "name": "get_invoice_status",
        "description": "Look up whether an invoice is paid.",
        "parameters": {
            "type": "object",
            "properties": {"invoice_id": {"type": "string"}},
            "required": ["invoice_id"],
        },
    },
}]
messages = [{"role": "user", "content": "Has invoice a41f been paid?"}]

reply = client.chat.completions.create(model="anthropic/claude-sonnet-5", messages=messages, tools=tools)
call = reply.choices[0].message.tool_calls[0]
args = json.loads(call.function.arguments)

messages.append(reply.choices[0].message)
messages.append({"role": "tool", "tool_call_id": call.id, "content": json.dumps({"paid": True})})

final = client.chat.completions.create(model="anthropic/claude-sonnet-5", messages=messages, tools=tools)
print(final.choices[0].message.content)

JavaScript

import OpenAI from "openai";

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

const tools = [{
  type: "function",
  function: {
    name: "get_invoice_status",
    description: "Look up whether an invoice is paid.",
    parameters: {
      type: "object",
      properties: { invoice_id: { type: "string" } },
      required: ["invoice_id"],
    },
  },
}];
const messages = [{ role: "user", content: "Has invoice a41f been paid?" }];

const reply = await client.chat.completions.create({ model: "anthropic/claude-sonnet-5", messages, tools });
const call = reply.choices[0].message.tool_calls[0];
const args = JSON.parse(call.function.arguments);

messages.push(reply.choices[0].message);
messages.push({ role: "tool", tool_call_id: call.id, content: JSON.stringify({ paid: true }) });

const final = await client.chat.completions.create({ model: "anthropic/claude-sonnet-5", messages, tools });
console.log(final.choices[0].message.content);

图片在请求中

模型与 capabilities.vision 可以阅读图片. 添加 image_url 分享到一个用户消息,与一个观众 https:// 链接或A data:image/…;base64, 网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网页网400 invalid_image_url(一)可选 detail 是 auto, low 或 high.

与 nymbot/auto,其中包含图像的请求被路由到可以看到的标准模型。 capabilities.vision 拒绝与照片 400 unsupported_content图像只能在用户消息中。链接必须指向公共主机;Nymbot将图像传递给模型提供商,而不会保留。

图像作为输入代币被提供商计算,就像其他请求一样。

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "What is in this picture?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/receipt.jpg"}}
      ]
    }]
  }'

Python

import base64, os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

with open("receipt.jpg", "rb") as f:
    data_url = "data:image/jpeg;base64," + base64.b64encode(f.read()).decode()

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{
        "role": "user",
        "content": [
            {"type": "text", "text": "What is in this picture?"},
            {"type": "image_url", "image_url": {"url": data_url}},
        ],
    }],
)
print(reply.choices[0].message.content)

JavaScript

import { readFile } from "node:fs/promises";
import OpenAI from "openai";

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

const dataUrl = "data:image/jpeg;base64," + (await readFile("receipt.jpg")).toString("base64");

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  messages: [{
    role: "user",
    content: [
      { type: "text", text: "What is in this picture?" },
      { type: "image_url", image_url: { url: dataUrl } },
    ],
  }],
});
console.log(reply.choices[0].message.content);

理性

模型与 capabilities.reasoning 在回答之前,你可以想一想,或多或少地问。 reasoning_effort ("minimal", "low", "medium" 或 "high")或 "reasoning": {"effort": "high"},或添加 :thinking 到模型名称,这意味着高努力. 在没有推理的模型上,设置被忽略。 nymbot/auto, :thinking 将请求发送到标准推理路径。

在人类模型上,努力成为大约1000、2000、8000或16000个代币的思维预算,从不超过 max_tokens 允许!思考被抛弃时 tool_choice 强迫一个工具,当请求继续一个工具循环(其最后的消息是工具结果),因为Anthropic需要先前签署的思维来恢复它。

理性回归于 message.reasoning_content,或 delta.reasoning_content 当流时,从不混合到答案中. 理性是输出,并且作为这样被收取,内部 completion_tokens一些提供商根本不返回推理文本,它仍然被收取费用。

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "reasoning_effort": "high",
    "messages": [{"role": "user", "content": "Is 2^61 - 1 prime? Show why."}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    reasoning_effort="high",
    messages=[{"role": "user", "content": "Is 2^61 - 1 prime? Show why."}],
)
message = reply.choices[0].message
print(getattr(message, "reasoning_content", None))
print(message.content)

JavaScript

import OpenAI from "openai";

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

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  reasoning_effort: "high",
  messages: [{ role: "user", content: "Is 2^61 - 1 prime? Show why." }],
});
console.log(reply.choices[0].message.reasoning_content);
console.log(reply.choices[0].message.content);

模型补充

模型名称上的补丁改变了请求的处理方式,没有其他字段。 anthropic/claude-sonnet-5:online.

任何其他附加字符都被忽略了. 整个名称首先被尝试,所以一个模型,其ID确实包含一个结肠;如果不这样做,附加字符会随时取出结尾,直到一个模型匹配。 400 invalid_value.

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5:thinking",
    "messages": [{"role": "user", "content": "Plan a three-day trip to Lisbon."}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5:thinking",
    messages=[{"role": "user", "content": "Plan a three-day trip to Lisbon."}],
)
print(reply.choices[0].message.content)

JavaScript

import OpenAI from "openai";

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

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5:thinking",
  messages: [{ role: "user", content: "Plan a three-day trip to Lisbon." }],
});
console.log(reply.choices[0].message.content);

网站搜索

任何聊天模型都可以从实时网络中回答。Nymbot搜索最后的用户消息(其前2000个字符),读取最好的页面,并将其交给模型有问题,标记为外部内容,模型不应该从中接收指示。

• 总是寻找: "plugins": [{"id": "web", "max_results": 5}],或 A :online 足以在模型上。
• 寻找当它有帮助: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}]也被接受为 web_search_preview 或 openrouter:web_searchNymbot 只在问题看起来需要当前信息时进行搜索,这也是应用程序使用的测试。

max_results 5 是默认的,最多 10 是源返回 nymbot.web_search.sources,每一个与A title, snippet 和 url,并作为 url_citation 留言中的注释。

每个搜索运行成本为 $0.008,转换为 sats,在代币的顶部,它是持有的一部分. 它读到的页面也是输入代币,所以来自网络的答案比同一个问冷的问题更贵,有时是几倍。

答案,部分

"nymbot": {
  "balance": "pro",
  "charged_credits": 0.431,
  "charged_sats": 43.1,
  "balance_credits": 411.994,
  "balance_sats": 41199.4,
  "web_search": {
    "sources": [
      { "title": "Lightning Network - Wikipedia", "snippet": "The Lightning Network is a payment protocol...", "url": "https://en.wikipedia.org/wiki/Lightning_Network" }
    ]
  }
}

cURL

curl https://nymbot.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "plugins": [{"id": "web", "max_results": 5}],
    "messages": [{"role": "user", "content": "What changed in the latest Bitcoin Core release?"}]
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

reply = client.chat.completions.create(
    model="anthropic/claude-sonnet-5",
    messages=[{"role": "user", "content": "What changed in the latest Bitcoin Core release?"}],
    extra_body={"plugins": [{"id": "web", "max_results": 5}]},
)
print(reply.choices[0].message.content)
for source in reply.model_extra["nymbot"]["web_search"]["sources"]:
    print(source["url"])

JavaScript

import OpenAI from "openai";

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

const reply = await client.chat.completions.create({
  model: "anthropic/claude-sonnet-5",
  plugins: [{ id: "web", max_results: 5 }],
  messages: [{ role: "user", content: "What changed in the latest Bitcoin Core release?" }],
});
console.log(reply.choices[0].message.content);
for (const source of reply.nymbot.web_search.sources) console.log(source.url);

答案 火

OpenAI 的更新的格式,由 OpenAI 代理商 SDK 和 Codex 使用,运行在与 Chat Completions 相同的模型、计费和功能上。

POST https://nymbot.ai/api/v1/responses 需要一个 API 密钥。

回应

{
  "id": "resp_8c1e4b0f9a2d4e61",
  "object": "response",
  "created_at": 1790726400,
  "status": "completed",
  "model": "anthropic/claude-sonnet-5",
  "output": [
    {
      "type": "message",
      "id": "msg_2b7f",
      "role": "assistant",
      "status": "completed",
      "content": [{ "type": "output_text", "text": "A Lightning invoice is...", "annotations": [] }]
    }
  ],
  "output_text": "A Lightning invoice is...",
  "usage": {
    "input_tokens": 1240,
    "input_tokens_details": { "cached_tokens": 0 },
    "output_tokens": 380,
    "output_tokens_details": { "reasoning_tokens": 0 },
    "total_tokens": 1620
  },
  "incomplete_details": null,
  "error": null,
  "instructions": null,
  "store": false,
  "previous_response_id": null,
  "metadata": {},
  "nymbot": { "balance": "pro", "charged_credits": 0.162, "charged_sats": 16.2, "balance_credits": 412.425, "balance_sats": 41242.5 }
}

一个工具请求显示在 output 如 A function_call 题与 call_id, name 和 arguments将结果返回为 a function_call_output 与相同的项目 call_id理性,当模型返回它时,是一个 reasoning 题与 reasoning_text 内容,先列出。 status 是 incomplete 当答案击中 max_output_tokens 或拒绝提供者。 incomplete_details.reason 设置为 max_output_tokens 或 content_filter该响应也响应了请求的设置(温度、工具、工具选择等),就像OpenAI所做的那样,并携带了 nymbot 物体成本。

流媒体,每一个事件都是一个 event: 线和A data: 线与A sequence_number,按照这个顺序: response.created, response.in_progress, response.output_item.added, response.content_part.added任何数量的 response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done,最后 response.completed 使用和成本. 一个答案缩短的结尾与 response.incomplete 相反,在流量开始后,一个失败 response.failed理性流作为它自己的项目与 response.reasoning_text.delta 和 .done工具呼叫接到消息后,每一个作为一个项目 response.function_call_arguments.delta 和 .done.

cURL

curl https://nymbot.ai/api/v1/responses \
  -H "Authorization: Bearer $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5",
    "instructions": "Answer in one short paragraph.",
    "input": "What is a Lightning invoice?"
  }'

Python

import os
from openai import OpenAI

client = OpenAI(base_url="https://nymbot.ai/api/v1", api_key=os.environ["NYMBOT_API_KEY"])

response = client.responses.create(
    model="anthropic/claude-sonnet-5",
    instructions="Answer in one short paragraph.",
    input="What is a Lightning invoice?",
)
print(response.output_text)

JavaScript

import OpenAI from "openai";

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

const response = await client.responses.create({
  model: "anthropic/claude-sonnet-5",
  instructions: "Answer in one short paragraph.",
  input: "What is a Lightning invoice?",
});
console.log(response.output_text);

人类信息

Anthropic 的格式,适用于 Anthropic SDK 和 Claude Code. 它适用于目录中的每个模型,而不仅仅是 Claude:请求被翻译,通过相同的管道运行,并被翻译回来。

POST https://nymbot.ai/api/v1/messages 需要一个 API 密钥,如 x-api-key 或 Authorization: Bearer.

该 anthropic-version 和 anthropic-beta 人类模型名称与目录相匹配,因此 Claude Code 和 SDK 可以使用他们已经使用的名称:

• 一个名称,目录知道,如 claude-sonnet-5 或 anthropic/claude-opus-5它是使用的,正如它是。
• 另一个日期( )-20260514), -latest,一个版本标签,如 -v1,一个布拉克特的日期,如 [1m] 和一个 anthropic/ 或 anthropic. 图标和图标在两个版本中都被试图使用(claude-haiku-4-5 发现 claude-haiku-4.5).
• 如果这仍然不匹配,则使用家族(Opus,Sonnet或Haiku),只要目录的版本与所请求的版本相同或更新。
• 一个与没有匹配的名字返回 404 not_found_error.

回应

{
  "id": "msg_01c7a2f93e5b4d08",
  "type": "message",
  "role": "assistant",
  "model": "anthropic/claude-sonnet-5",
  "content": [{ "type": "text", "text": "A Lightning invoice is..." }],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 1240,
    "output_tokens": 380,
    "cache_read_input_tokens": 0,
    "cache_creation_input_tokens": 0
  },
  "nymbot": { "balance": "pro", "charged_credits": 0.162, "charged_sats": 16.2, "balance_credits": 412.425, "balance_sats": 41242.5 }
}

content 也可以持 tool_use 区块链和A thinking 区块链,谁 signature 是空的。 stop_reason 是 end_turn, max_tokens, tool_use 或 refusal,以相同的方式工作,如 finish_reason 是 Chat 完成; stop_sequence 总是 null,即使停止序列结束了答案。 input_tokens 新鲜输入仅计数;缓存输入在两个缓存字段中。 nymbot 对象和 X-Nymbot-Cost-Sats 海德

流媒体,活动是Anthropic的: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta 或 thinking_delta), content_block_stop, message_delta 停止的理由,使用和 nymbot 成本对象,以及 message_stop」 A ping 在模型工作时也每15秒发送一次。工具呼叫接到文本后,每一个作为一个 tool_use 区块,其全部输入在一个 input_json_delta.

此端点上的错误使用 Anthropic 的格式: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}短暂的平衡是 402 billing_error一个过载的供应商 503 overloaded_error在流开始后出现故障将被发送为 error 事件。

cURL

curl https://nymbot.ai/api/v1/messages \
  -H "x-api-key: $NYMBOT_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [{"role": "user", "content": "What is a Lightning invoice?"}]
  }'

Python

import os
import anthropic

client = anthropic.Anthropic(base_url="https://nymbot.ai/api", api_key=os.environ["NYMBOT_API_KEY"])

message = client.messages.create(
    model="claude-sonnet-5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "What is a Lightning invoice?"}],
)
print(message.content[0].text)

JavaScript

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({ baseURL: "https://nymbot.ai/api", apiKey: process.env.NYMBOT_API_KEY });

const message = await client.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "What is a Lightning invoice?" }],
});
console.log(message.content[0].text);

计数代币

估计一个消息请求会使用多少输入代币,以便客户端在发送之前可以检查。

POST https://nymbot.ai/api/v1/messages/count_tokens 需要一个 API 密钥。

身体是相同的为 信息,没有 max_tokens;模型名称必须解决。计数是一个估计:系统提示、消息、工具调用和工具定义的字符分为四个,加上每张图像的1600个。

回应

{ "input_tokens": 318 }

cURL

curl https://nymbot.ai/api/v1/messages/count_tokens \
  -H "x-api-key: $NYMBOT_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-sonnet-5",
    "messages": [{"role": "user", "content": "What is a Lightning invoice?"}]
  }'

Python

import os
import anthropic

client = anthropic.Anthropic(base_url="https://nymbot.ai/api", api_key=os.environ["NYMBOT_API_KEY"])

count = client.messages.count_tokens(
    model="claude-sonnet-5",
    messages=[{"role": "user", "content": "What is a Lightning invoice?"}],
)
print(count.input_tokens)

JavaScript

import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({ baseURL: "https://nymbot.ai/api", apiKey: process.env.NYMBOT_API_KEY });

const count = await client.messages.countTokens({
  model: "claude-sonnet-5",
  messages: [{ role: "user", content: "What is a Lightning invoice?" }],
});
console.log(count.input_tokens);

列表模型

每个模型和发电机都接受API,它的成本。 列表是从应用程序的选择器同样的直播目录中读取的,所以它总是服务器将运行的。

GET https://nymbot.ai/api/v1/models 不需要密钥 隐藏5分钟

GET /api/v1/models/{id} 返回 1 条入口

价格是你支付的,费用和利润已经在美元和在当前比特币价格的价格。 balance 表明模型花费的平衡。 nymbot_key 是 app 中的模型的简称。 created 總是0,因為目錄沒有記錄當一個模型被添加時。 per_request 反而。

nymbot/auto 总是第一,价格为 variable,与A routes 列出每个标准路线的价格,列出愿景和推理,但不是工具。

GET /api/v1/models/{id} 接受相同的名称和副名称作为请求,并返回他们选择的模型的条目。

回应

{
  "object": "list",
  "data": [
    {
      "id": "anthropic/claude-sonnet-5",
      "object": "model",
      "type": "chat",
      "owned_by": "anthropic",
      "name": "Claude Sonnet 5",
      "created": 0,
      "context_length": 1000000,
      "max_output_tokens": 64000,
      "architecture": { "input_modalities": ["text", "image"], "output_modalities": ["text"] },
      "supported_parameters": ["max_tokens", "temperature", "tools", "tool_choice", "reasoning", "response_format", "stop"],
      "capabilities": { "vision": true, "video": false, "tools": true, "reasoning": true, "web_search": true },
      "balance": "pro",
      "pricing": {
        "type": "per_token",
        "currency": "USD",
        "input_per_1M_tokens": 4.725,
        "output_per_1M_tokens": 23.625,
        "cache_read_per_1M_tokens": 0.4725,
        "sats_input_per_1M_tokens": 4038,
        "sats_output_per_1M_tokens": 20192
      },
      "description": "...",
      "nymbot_key": "claude-sonnet"
    }
  ]
}

其他类型:

• 图像 入口有 capabilities (accepts_image_url, requires_image_url, edit(一)价格 per_generation.
• 视频 入口有 max_duration_seconds 和 resolutions而且一个价格 per_second 对于每一个决议
• 音频 入口有 audio_type speech 或 transcription价格 per_1k_chars 或 per_minute.
• 嵌入 入口有 dimensions, context_length, max_inputs 一百万个入口代币的价格。

标记价格 "estimated": true 是应用程序对没有公布价格的发电机的估计。 type 返回 400.

cURL

curl "https://nymbot.ai/api/v1/models?type=chat"

Python

import requests

models = requests.get("https://nymbot.ai/api/v1/models", params={"type": "chat"}).json()["data"]
for m in models:
    print(m["id"], m["balance"], m["pricing"].get("input_per_1M_tokens"))

JavaScript

const res = await fetch("https://nymbot.ai/api/v1/models?type=chat");
const { data } = await res.json();
for (const m of data) console.log(m.id, m.balance, m.pricing.input_per_1M_tokens);