Fa'avae poto / Atia'i Fausiaina

Talanoaga, Fa'antwortu ma Fe'au

Ni auala e tolu e fesili ai i se model, i foafoaga e tolu o lo'o tautala ai tautua, e fa'atino uma i luga o le lava uma o modele ma e fa'asino lava i le auala e totogi ai.

O lenei itulau ua fa'aliliuina i masini mo le fa'afaigofieina. O le ulua'i fa'a-Peretania o le fa'amatalaga lea e fa'atatau.

Fa'auna o Talanoaga

O le tulaga o le talanoaga a le OpenAI, ma le tulaga o lo'o lagolagoina e le tele o meafaigaluega. Auina atu le talanoaga o lo'o fa'asolo pea ma maua le fe'au soso'o.

POST https://nymbot.ai/api/v1/chat/completions — e mana'omia se API key.

Na'o model ma messages e mana'omia. O se vaega o le fa'ata'ita'iga e le fa'aaoga e le filifilia le fa'ata'ita'iga, e aveese e aunoa ma se mea sese, o le mea lea e galue ai le tasi fa'amatalaga mo fa'ata'ita'iga uma. O le lisi o fa'ata'ita'iga e tu'uina atu ai le fa'ata'ita'iga ta'itasi e supported_parametersO le mea e fa'ataga ae lē fa'asaga pe a tū, o so'o se mea e lē mafai e le modele ona fai lava: ata mo se modele e lē mafai ona va'ai, meafaigaluega mo se modele e lē mafai ona fa'aaogāina.

O le tali o se mea masani chat.completion, ma le tau i le usage.cost (i tausaga) ma i le nymbot nofoaga. model o le ID o le modele ua faia ai le faaiuga, o lea o le a toe fo'i mai se suafa pu'upu'u e pei o le suafa atoa. Afai sa mafaufau le modele a'o le'i tali atu, o lona mafaufau o lo'o i ai i message.reasoning_content, vaese mai le tali.

Aiga

{
  "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 e fa'atatau i mea na maua mai, ona fa'ailoa mai lea e eseese isi kamupani pemasena: tool_calls pe a fesili le modele mo ni meafaigaluega, length pe a ua faaaogā ai e le tali ta tấtisi o nei tokens (po o le faaaogāina e le model uma i le mafaufau ma le leai o se tali), content_filter pe a refuse le tuuina atu e le pulega, ma stop pe afai leei. usage.completion_tokens_details.reasoning_tokens e laging o le 0: fa'afoliga o token o le mafaufau o lo'o faitauina, ma totogiina, i le completion_tokens.

O nei fuafuaga o tulaga (status codes) o lo'o fa'asoa i endpoint uma o lo'o lisiina i lalo o inoino.

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);

Fa'aataina i luga o le initaneti

Fa'atasi 'i "stream": true o le tali e sau i le taimi o lo'o tusia ai e le tautua i ni faasilasilaga lafo mai le server. O faasilasilaga ta'itasi o se chat.completion.chunk i luga o se data: lā, ma le faaiu o le malaga data: [DONE]. Mafaufau e su'u mai i delta.reasoning_content, le tali i le delta.content.

Faasologa so'o se mea lava e ono toe faatagalemu i le 100 sekone, e pei o se tali umi, se mea tele max_tokens po o se modele o le mafaufau. O se talosaga e le o fa'alauiloa i le taimi lava e tasi (streamed) e le toe lafoina se mea seia o'o ina mae'a le tali, ma o le feso'ota'iga i le va o oe ma Nymbot e ono tapuni pe a nofo mamafa le feso'ota'iga i le taimi e tusa ma le 100 sekone; ae o le modele o le a fa'ai'u pea ma o mea na tusia o le a totogiina, ae o le tali ua le toe maua. O se stream e lafo ai fa'ailoga fa'amamafa (keep-alives), ina ia tumau pea le tatala i so'o se taimi e tusia ai e le modele.

Fa'asologa

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]

• Lini e amata i le : o ia komenti keep-alive, e lafo i taimi uma i le 15 sekone a'o manatu le modele. E lē taliaina e le au SSE.
• Fai talosaga mo "stream_options": {"include_usage": true} ina ia maua le vaega mulimuli i luga, ma se mea e leai se mea choices, o numera o le token, o le tau ma le nymbot nofoaga.
• E fa'atatau le totogi pe a mae'a le streaming. Afai e te tapuni le fesootaiga vave, e leai fo'i le fa'amumulia o le model: o lo'o faitau le Nymbot i le totoe o le streaming a le la'uina mai, mo se taimi e o'o i le 25 sekone, ina ia maua lona numera o upu (token count), ma e te totogi le mea ua lipoti mai e le la'uina mai. Afai e leai lena numera, o le a fa'atatau le totogi mai lau mea na tu'uina atu ma mea na tusia, fa'apea fo'i le tapua'iga atoa o le output mo se model e mafai ona mafaufau.
• O se mea sese ae le'i amata le vaega muamua, e pei o le 401 poʻo 402, toe fo'i mai e pei o se JSON masani fa'atasi i lona status code, ae lē o se stream. O se mea sese pe a uma ona amata le stream e sau fa'ai'u data: {"error": {…}} fa'alavelave, ma ua mae'a le lala pe a le'i... [DONE].
• O luʻitau ma meafaigaluega, faʻapea modele i luga o le OpenAI's Responses transport, e le o faʻaauau le lafoina mai i le pulega o loʻo tuʻuina atu auaunaga. E tali pea i se faʻasologa moni, e lafoina pe a maeʻa le tali.

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);
}

Fa'auiga o meafaigaluega

Faamatalaina galuega i le tools ma le modele e mafai ona talosaga mo se tasi e valaauina nai lo le tali atu. E te fa'atino le fa'agaioiga, ma fa'aopoopo i lona i'uga e pei o se tool feau e tutusa ma le mea lava lea tool_call_id, ma toe lafo le talanoaga. E le fa'atino e Nymbot au galuega; e toe fa'asaoina le talosaga a le modele i ia te oe.

tool_choice a'u mai "auto", "none", "required" poʻo {"type": "function", "function": {"name": "…"}}. O le lisi o modele o faailogaina ai po o fea modele e mafai ona valaauina ni meafaigaluega (capabilities.tools). O meafaigaluega e fa'atama'ia ai ma 400 unsupported_tool i luga nymbot/auto ma i luga o itu lava o ata faʻataʻitaʻiga o le katalogo e galue i luga o le OpenAI's Responses transport, lea e le mafai ai e Nymbot ona tuʻuina atu ni meafaigaluega

Fa'atasi 'i "stream": true, o se talosaga ma meafaigaluega e fa'atino i se vaega e tasi ona lafoina atu e pei o se fa'asologa masani o vaega: le tulagaaga, se vaega e tauveleina ai so'o se valaauina o meafaigaluega fa'atasi ma lona numera, id, igoa ma alaoaiga, ma le vaega fa'ai'u. O tagata fa'aaoga o lo'o faitauina valaauina o meafaigaluega fa'asologa e fa'agaoioia i le auala masani.

Tali, i se vaega

"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);

O ata i se talosaga

Faʻataʻitaʻiga ma capabilities.vision e mafai ona faitau ata. Fa'aopoopo i se image_url vaega o se feau a se tagata fa'aaoga, ma se tasi o se lautele https:// so'otaga po'o se data:image/…;base64, URL. O le upu e oo atu i le 20 ata i le talosaga taatasi. O ata SVG e faamaualaloina, faapea foi se sootaga e sili atu i le 4,096 o nei faamau, pe iai se igoa faaaoga po o se upu faamaonia i ai (400 invalid_image_url). O se filifiliga e lē mana'omia detail o lo'o auto, low poʻo high.

Fa'atasi 'i nymbot/auto, o se talosaga o lo'o iai se ata e lafo atu i se faʻataʻitaʻiga masani e mafai ona vaʻai. O se faʻataʻitaʻiga o se katalog e aunoa ma capabilities.vision te'ena ki ata ma 400 unsupported_contentO ata e mafai ona i ai na o i faamessages a le tagata faaaoga. O se sootaga e tatau ona tulaga i se nofoaga o lo'o tatala i tagata uma; o Nymbot e tuuina atu le ata i le pulega o le filimali o le modele ma e lē taofia ai.

O se ata e totogiina e pei o fa'apuupuuina o fa'amatalaga (input tokens) e faitauina e le tu'uina atu, e pei o isi vaega o le talosaga.

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);

Mafaufau

Faʻataʻitaʻiga ma capabilities.reasoning e mafai ona mafaufau a o le'i tali atu. Talosaga mo se tele atu po'o se itiiti atu o lena ma reasoning_effort ("minimal", "low", "medium" poʻo "high") po o "reasoning": {"effort": "high"}, po o fa'aopoopo :thinking i le suafa o le polokalame, o lona uiga o se taumafaiga maualuga. I se polokalame e aunoa ma le faamanatuina, e le mafai ona faaaogā le faasologa. Ma nymbot/auto, :thinking aunai le talosaga i le ala masani o le mafaufau.

I luga o modele a Anthropic, o le taumafaiga e avea ma paketi o le mafaufau e tusa ma le 1,000, 2,000, 8,000 po o le 16,000 tokens, e le o sili atu i se tulaga soo max_tokens fa'atagaina. O le mafaufau e tuua pe a tool_choice fa'amalosi ai se meafaigaluega, ma pe a fa'aauau le talosaga se fa'asologa o meafaigaluega (o lona fe'au mulimuli o se i'uga o se meafaigaluega), ona mana'omia lava e le Anthropic le mafaufau ua fa'amamafa muamua ina ia toe amata ai. E tutusa fo'i lenei mea i vaega o Responses ma Messages endpoints.

Ua toe fo'i mai le mafaufau i totonu message.reasoning_content, pe delta.reasoning_content pe a streaming, aua ne'i fa'alavelave i le tali. O le fa'amoemoe o le fa'alogoina ma e totogi i lena tulaga, i totonu completion_tokensO nisi laoutaga e lē toe foai mai lava le tusitusiga o le faamatalaga, ae o lo'o totogia lava.

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);

Fa'auiga o le modele

O se fa'apuupuu i le igoa o le modele e suia ai le auala e fa'atautaia ai le talosaga, e aunoa ma se isi vaega. E galulue i id atoatoa ma igoa fa'apuupuu e pei o, anthropic/claude-sonnet-5:online.

E le iloga se isi fa'aopoopo lava. E muamua taumafai le igoa atoa, ina ia mafai lava ona galue se model o lona ID o lo'o ia ai moni se fa'ailoga (colon); pe a le mafai, e aveese fa'aopoopo mai le pito i'osi ta'itasi se'ia o'o ina tutusa le model. E mafai ona umi le igoa o se model i le 200 o fa'ailoga i le tele ma le 4 fa'aopoopo i le tele; o se mea e sili atu ona umi e teena i le 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);

Su'esu'e Web

O so'o se ata chat e mafai ona tali mai i le upega tafa'ilagi fa'asolo atu. O lo'o su'esu'e e Nymbot le fe'au mulimuli a le tagata fa'aaoga (ana 2,000 ulutala muamua), faitau i itū sili ona lelei ma tu'uina atu i le ata fa'atasi ma le fesili, e fa'ailoa mai o ni mea o lo'o fa'atāuaina i fafo e le tatau ona maua ni fa'atonuga mai e le ata. O lo'o iai ni faiga e lua:

• Aiga lava le su'esu'eaga: "plugins": [{"id": "web", "max_results": 5}], po o se :online fa'ai'uga i luga o le fa'ata'ita'iga.
• Su'e pe a fesoasoani: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}], o le foi fa'atumuaina fo'i e pei o web_search_preview poʻo openrouter:web_search. Nymbot su'esu'e na'o taimi lava e pei ona foliga mai o loo mana'omia ni fa'amatalaga fa'ata\"ata, o le ilimaga lava e fa'aaog=\"a e polokalame.

max_results e 5 i le tulaga masani ma le tele o le 10. O punaoa e toe fo'i mai i le nymbot.web_search.sources, o le isi lava ma se title, snippet ma url, ma pe a url_citation fa'amatalaga i luga o le fe'au.

O le su'esu'ega ta'itasi e fa'atinoina e taugata le $0.008, ua liliu ina avea ma sats, i luga o le tau o tokens, ma o lona vaega lea o le hold. O ituaiga pepa ua faitauina o ni input tokens fo'i, o lea o le tali mai le upega tafa'ilagi e taugata atu i le fesili lava e tasi ae le'i fa'aaogāina se upega tafa'ilagi, o nisi taimi e sili atu lona taugata i le tele o taimi.

Tali, i se vaega

"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);

API o Tali

O le faiga fou a le OpenAI, e faaaogā e le OpenAI Agents SDK ma le Codex. E galue i luga o lava modele, totogi, ma uiga faapitoa e pei o Chat Completions.

POST https://nymbot.ai/api/v1/responses — e mana'omia se API key.

Aiga

{
  "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 }
}

O se talosaga mo se meafaigaluega ua fa'aali mai i output amata i le function_call item ma le call_id, name ma arguments; auina atu le i'uga fa'afo'i e pei o se a function_call_output item ma le tutusa call_id. Mafaufau, pe a fa'afo'i mai e le model, o se reasoning item ma le reasoning_text fa'amatalaga, fa'asolo muamua. status o lo'o incomplete pe a taunuu le tali max_output_tokens pe afai ua lē talia e le tuatusiga, ma incomplete_details.reason faatulaga i le max_output_tokens poʻo content_filter. O le tali fo'i e fa'aata ai tulaga o le talosaga (temperature, meafaigaluega, filifiliga o meafaigaluega ma isi fa'apena) e pei ona faia e OpenAI, ma tauvevela ai le nymbot tau faʻatatau i le mea.

O le faalauiloaina, o faalavelave taatasi o se event: fa'asologa ma se data: lua e fa'atasi i le a sequence_number, i lenei faasologa: response.created, response.in_progress, response.output_item.added, response.content_part.added, so o lē NUMERA lava po o le a le NUMERA response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, ma le faaiuga response.completed ma le fa'aaogaina ma le tau. O se tali ua lē mae'a e fa'ai'u i le response.incomplete i le isi, ma se failauga pe a uma ona amata le fa'asologa ma response.failed. O le auaunaga o mafaufau o se mea faapitoa lava ia ma response.reasoning_text.delta ma .done. O fa'asalalauga o le meafaigaluega e sau pe a mae'a le fe'au, o le lava lava o se vaega ma response.function_call_arguments.delta ma .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);

Feau a Anthropic

O le tulaga a Anthropic, mo Anthropic SDKs ma le Claude Code. E galulue faatasi ma so'o se masini i le mea faaputuuputu, e le na'o Claude: e faalagolago le talosaga, e fa'agaioia e ala i le lava lava o le polokalame, ma toe fa'alili atu.

POST https://nymbot.ai/api/v1/messages — e manaʻomia se API key, ona x-api-key poʻo Authorization: Bearer.

Le anthropic-version ma anthropic-beta e talia fa'amau (headers) ma e le o mafai ona fa'aaogāina. O igoa o modele a Anthropic e fa'atusatusa i le kataloge, ina ia mafai ai ona galue Claude Code ma SDKs i igoa o lo'o latou fa'aaogāina nei:

• O se igoa e iloa e le katalogi, e pei o claude-sonnet-5 poʻo anthropic/claude-opus-5, e faaaogā lava pe a faasaga mai.
• Isi lava e se aso (-20260514), -latest, se vaega o se taga e pei o le -v1, se vaega o lo'o i totonu o fa'ailoga e pei o [1m] ma se anthropic/ poʻo anthropic. ua aveesea fa'ailoga i luma, ma ua suʻe i ni auala e lua ni dot ma dash i le fa'atauga (claude-haiku-4-5 su'ega claude-haiku-4.5).
• Afai e toe le fetaui lava ma se mea lava, e faaaogā le aiga (Opus, Sonnet po o le Haiku), o tusa lava po o le tauga o le katalog o le lava lava po o se tasi fou atu i le mea na talosaga atu ai.
• O se suafa e le fetaui ma se mea lava e toe fo'i mai ai 404 not_found_error.

Aiga

{
  "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 e mafai fo'i ona taofia tool_use fa'asologa ma se thinking fa'amau, o ai signature ua mamā. stop_reason o lo'o end_turn, max_tokens, tool_use poʻo refusal, fa'atinoina i le lava lava ala e pei o finish_reason i luga Fa'auna o Talanoaga; stop_sequence e tumau pea null, tusa lava pe na faaiuina e se faasologa e taofi ai le tali. input_tokens numera na'o fa'amatalaga fou; o fa'amatalaga o lo'o teuina o lo'o i vaega o le cache e lua. O le tau o lo'o i le nymbot oboitioga ma le X-Nymbot-Cost-Sats ulutala.

O mea na faasologa atu, o mea na tupu a Anthropic: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta poʻo thinking_delta), content_block_stop, message_delta ma le mafuaaga o le tuai, le fa'aaogaina ma le nymbot fa'amoemoe tau, ma message_stop. A ping e lafo fo'i i taimi uma e 15 sekone a'o galue le model. O valaau i meafaigaluega e sau i tua atu o le tusitusiga, o le isi lava e pei o se tool_use taumi ma lona mea uma ua fa'atasi i le tasi input_json_delta.

O mea sese i lenei endpoint e faaaogā ai le tulaga o Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}. A o se tupe maualalo o le 402 billing_error, o se tagata o loo tu'uina atu auaunaga ua tele tele le galuega 503 overloaded_errorO se lamatia pe a uma ona amata le streamer e lafoina aoga se mea e error tala.

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);

Numeraina o tokeni

O se fua o le a faitau le NUM mostia e se talosaga o Messages, ina ia mafai ai e se tagata fa'aaoga ona siaki ae le'i lafoina. E sa'o lava, ae e mana'omia lava se ki.

POST https://nymbot.ai/api/v1/messages/count_tokens — e mana'omia se API key. Sa'oloto.

O le tino e tutusa lava ma le mo Feau, e aunoa ma max_tokense tatau ona fa'atino le igoa o le tautua. O le numera lenei o se fuainumera fa'ata'ita'iga: o isi mata'itusi o le fa'atonuga o le polokalame, fe'au, vala'auina o meafaigaluega, ma fa'amatalaga o meafaigaluega e vaevaeina i le fa'avalesolu, fa'aopoopo ai le 1,600 mo latou ata ta'itasi. E lē o le tokenizer a le tu'uina atu o auaunaga, o lea e ono ese le numera moni. O se ki ua o'o i lona tapula'a e mafai lava ona fa'aoga pea.

Aiga

{ "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);

Lisiina o modele

O so'o se polokalame ma ukilu (generator) e talia e le API, fa'atasi ma lona tau. O le lisi e faitauina mai le tusi fa'amaumauga fa'asolo (live catalog) e tutusa ma le filifilia o mea i totonu o le polokalame, ina ia tumau pea le mea o le a fa'atino e le server.

GET https://nymbot.ai/api/v1/models — e leai se ki e manaomia. Faasaoina mo ni lima minute.

GET /api/v1/models/{id} toe maua se tasi faamatalaga.

O tau o mea e totogia ai, ua aofia ai le totogi ma le margin, i ni dola ma ni sats i le tau o le Bitcoin o le taimi nei. balance fa'apea mai po'o fea le totogi o lo'o fa'aalu e le polokalame. nymbot_key o lo'o i ai le suafa puupuu o le polokalame i totonu o le app. created e tumau pea i le 0, auā e le fa'amaumauina e le katalogu le taimi na fa'aopoopo ai se model. O se model e aunoa ma ia tau o token ua fa'asalalauina e fa'atatauina le tau per_request nai lo lena.

nymbot/auto e amata pea i le muamua, e tau i le variable, ma se routes o se lisi o lo'o fa'ailoa ai tau o fa'afuafuaga masani uma. O lo'o lisiina ai le va'ai ma le mafaufau, ae le o meafaigaluega.

GET /api/v1/models/{id} e talia ai ogaoga fa'apenei ma suafa fa'aopoopo e pei o se talosaga, ma toe foai mai le fa'amaumauga mo le modele o lo'o latou fa'asino atu i ai.

Aiga

{
  "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"
    }
  ]
}

O isi ituaiga:

• Ata o lo'o iai fa'amaumauga capabilities (accepts_image_url, requires_image_url, edit) ma se tau per_generation.
• Vitio o lo'o iai fa'amaumauga max_duration_seconds ma resolutions, ma se tau per_second mo lau faaiuga taatasi.
• Fa'alogo o lo'o iai fa'amaumauga audio_type speech poʻo transcription, tau per_1k_chars poʻo per_minute.
• Fa'atofiaina o lo'o iai fa'amaumauga dimensions, context_length, max_inputs ma le tau mo le miliona o token fa'aumi.

O tau ua faailoa mai "estimated": true o suesuega a le polokalame mo se generator o lo'o lē fa'alauiloa le tau. Se mea e lē iloa type toe fo'i mai 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);