Xiseketelo xa vutivi / Vaakuli wa swiendli

Xichavo, Swivutiso na Mavulavuli

Mindzila tin'wana to vutisa xihlaku-hlamuselo eka model, hi tindlela letimbirhi leti vaxavisi va tivaka, hinkwaswo va tirhisa mindzila leyi فان leyi fanaka na ku hlawulelwa hi ndlela yin'we.

Tluka leri ri hundzuluxeriwe hi muchini leswaku ri olova. Original ya Xinghezi i version leyi tirhaka.

Ku fambisela ka ku tswala ku vulavula

Fomati ya ku vulavula ya OpenAI, ni leyi xitirhisiwa hi switirhisiwa swinene swin'wana-xin'wana. Tsindza ku vulavula loko u nga ri kona u kuma xiyimbereti lexitsongo lexitshwa.

POST https://nymbot.ai/api/v1/chat/completions — e hlayiwa hi API key.

Xana ntsena model na messages swi hlayeriweke. Xihundla xa ku tshamisa leswi model lexi khetiwaka xi nga xi tshamisiweke swi huriwa nkarhi wu nga ri na xiyimo xa ku tlangula, leswaku xikombiso xa mbulavulo xi tirhisa eka model ta le ka hinkwaswo. Xikombiso xa model xi nyika ya xeacha model... supported_parametersSwi enile ku pfumala ku tshama, ku ri hi leswi model yi nga swona swi nga swi endla: swifaniso eka model leyi nga swi nga kiwaka, switirhisiwa eka model leyi nga swi nga tshimbisiwi.

Muxavetelo i wa xivuriso chat.completion, na mali yo... usage.cost (eka madola) naswona eka nymbot Xihlovo. model i id ya model leyi xavuriweke, ka leswaku vito yo komana wu ta humelela wu ri vito leyi heleleke. Loko model yi kombisele ku hlanganisa mianakanyo ku ringeta ku hlamula, mianakanyo ya yona yi ri eka message.reasoning_content, hlawuleka eka mhumelelo.

Mpfuxeto

{
  "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 swi hlamusetiwe eka leswi nga humile, hikuva vatekilaka va kombisa hi ndlela leyi avelaka hi yona: tool_calls loko model yi kombela switirhisiwa, length loko mhindzhu yi tirhise tona hinkwaswo ta madyondzolo lava enetiweke (kumbe xitirhisi xi tirhise hinkwaswo va xona eka ku pfuxa mianakanyo ku nga ri na mhindzhu), content_filter loko muhumuşi a kombelerile, naswona stop ka nti. usage.completion_tokens_details.reasoning_tokens swi rhandza 0: swi fihliwile tokens ta ku vutlhari swi hlamuriwa, naswona swi hlamuriwa, eka completion_tokens.

Swikwembu swa xiyimo leswi endpoyinti hí nkulu xin'we xi tshamaka swi kombisiwa eka mihlatshuri.

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);

Ku fikela

Na "stream": true mhluvhi wu fika hi server-sent events ka nkarhi lowu model yi tsalahaka yona. Event xin'wana na xin'wana i chat.completion.chunk e ka a data: xiga, naswona mukhala wu herisa hi data: [DONE]. Ku hlamusela swi fika eka delta.reasoning_content, xitswalo eka delta.content.

N’wi engetela xin’wana xin’wana lexi a xi nga ha teka swikati ka sekondi ta 100, ku fana na mh回答 ya leleti, leyi nkulu max_tokens kumbe model ya ku hlamusela. Xikweti leyi nga nga kombisiwanga hi ku tsakama-tsakama yi nga eneti nothinga loko hlamulo yi nga ri ku fikelela, naswona ntshikilelo exikarhi ka wena na Nymbot wu nga vala ntshikileto lowu nga riki na xin'wana mi mhantla ka sekondi 100; model yi hala ku fika naswona leswi yi swi tsaliweke swi hlawuriwa, kambe hlamulo yi lahlekile. Stream yi engetela tindzima to tiyisa, hi ku ri yi tshama yi vulavula nkarhi hinkwawo lowu model yi tsaliwaka wona.

Xitsandza-ndlela

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]

• Mitlhaya leyi sungulaka hi : ka ku rhendza swikombiso swa keep-alive, leswi tsaleriwaka swa nkarhi na nkarhi ka masiku 15 loko model yi hala ku pfuna. SSE clients ti xiya swona.
• Funza hi "stream_options": {"include_usage": true} ku kuma xiphemu xa mhaka ya le henhla, hi xin'wana lexi tswakaka choices, ku numuwa ka tokens, xikongomelo ni le... nymbot Xihlovo.
• Xikwembu xi ringanisiwa hi ku fuma ka mitsheketo. Loko u vala vuxhumano hi ku tsandzeka, xitshuri (model) xi nga vangiwi: Nymbot yi hlaya leswi salaka eka mitsheketo ya n'wana-wenge, ku ringanisa masiku ya 25, leswaku yi kuma xin'wana-wana xa ti-token, naswona u xupfela leswi n'wana-wenge a ri kombisaka. Loko ku nga ri na xin'wana-wana xa xin'wana-wana, xikwembu xi ringanisiwa hi leswi u nghenisaka na leswi a swi tsariwe, ku kombisa na xihlamuselo hinkwaswo xa mitsheketo ya xitshuri lexi hlamuselaka.
• Xiphiqiso khale hi xinkarhi xa khombo ra ku sungula, hi xikombiso xa: 401 kumbe 402, wu huma hi JSON ya xihlamuselo hi xikongomelo xa xona, hi ndlela yo riki, hi nu xitshuri. Xiphiqo hi la ka xitshuri xi sunguluxiweke xi fika hi ndlela ya vukhenxe data: {"error": {…}} ntirhandzu, naswona n'wayitela yi hetelela nga ntihi [DONE].
• Swikwembu leswi nga na switirhisiwa, na ma-models eka OpenAI's Responses transport, a hi tlangi hi ku famba (stream) ku sukela eka provider. Swi ntshikile hi ku hlamula hi stream leyi nene, leyi enzetlaka hi ku fika ka pfutelo.

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);
}

Ku tirhisiwa ka switirhisiwa

Hlamusela mintirho eka tools kambe model yi nga kombela leswaku yin'we yi vetiwa ematshan'weni ka ku hlamula. U tirhisa function, u kumeta pfunitelo wa yona hi xivumbeko xa tool tafula leri ri ni xinwe hi leswi tool_call_id, kambe u tsindzela khonvokesano hi ku tlhela. Nymbot a yi tlangi swivuriso swa wena; yi tsindzela xiphiqo xa model eka wena.

tool_choice a teka "auto", "none", "required" kumbe {"type": "function", "function": {"name": "…"}}. Xikongomelo xa mintirho xi kombisa leswaku mi tindzima leti ti nga swi kota ku tirhisa swilo (capabilities.tools). Switirhi swi dengekiwa hi 400 unsupported_tool ya hi nymbot/auto naswona eka model tshin'wana hi ntolovelo leti tirhisaka eka OpenAI's Responses transport, leyi Nymbot a nga swi kombisaka ti-tools eka yona.

Na "stream": true, xikweti hi switoho yi tshama yi ri yin'we hinkwayo ndzeni leyi tsandzekaka eka xiyimo xa xikamu xa xiyimo xa xiviri: xigidi xa vutihlamuleri, xikamu xin'we lexi hlawuleka hi xitoho xin'we xin'we xin'we lexi kumaka xikombiso, id, vito ni swivuriso, ni xikamu xa ku fhelisa. Vakwama lava nga endlaka ku hlaya xitoho xa switoho lava swi teka hi ndlela ya xiviri.

Muxwayelo, hi xiphanze

"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);

Swifaniso eka xikwembo

Mihelomu na capabilities.vision ndzi nga kona ku hlaya swifaniso. Engetela an image_url xiphemu xa xivulavokelo xa mutluketi, hi yin'wana ya xiyimo lexi tlhantlhiwaka hi vanhu hinkwavo https:// link kumbe a data:image/…;base64, URL. Misavamela ya 20 ka xiyimo hi xikwembu xin’wana xin’wana. Swifaniso swa SVG swi enzetelwa, naswona na xikwembu xa le hetelele xa le hetelele xa xiyimo xa 4,096 hi mikhala kumbe lexi nga na vito ra munhu kumbe xikwembu eka xona (400 invalid_image_url). Lexi xi nga pfuni detail i auto, low kumbe high.

Na nymbot/auto, xikwembu le xi ri na xifaniso eka xona xi hlongotshelwa eka model ya xiyero leyi nga riki na vukonondzu bya ku vona. Model ya katalog leyi nga riki na capabilities.vision u nga tikemi swifaniso hi 400 unsupported_content. Swifaniso swi nga va eka mavulavuri wa xikombiso ntsena. Xikombiso xinene xi fanele xi kombisa eka host ya vhuyetelo; Nymbot wu nyika xifaniso eka muhengeti wa ximodeli naswona a wu wu hlayisi.

Xifaneko xi xupfetiwa hi ma-tokens ya ku nghena leswi muxavisi a swi balaka hi ta xona, ku fana na swin'wana eka xikwembu.

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);

Ku hlamusela

Mihelomu na capabilities.reasoning va nga swi vava va nga tshama va karhi va tsundzuka ku hlamula. Vula leswaku u lava ntshikilelo kumbe ku kusuhi na khale na ku... reasoning_effort ("minimal", "low", "medium" kumbe "high") kumbe "reasoning": {"effort": "high"}, kumbe fikisa :thinking e ka vito ra model, leswi vulavulaka ku tirha ngopfu. E ka model leyi nga riki na ku ringisa switungusetano swi nga ringateliwi. Hi nymbot/auto, :thinking ya tsindzela xikwembo eka ndlela ya xikweni ya ku vonisela.

Eka ma-Anthropic models ntirho wu va budget ya ku ehleketa ya 1,000, 2,000, 8,000 kumbe 16,000 tokens, wu nga vi ri yo tala wu tala max_tokens swi nga pfumama. Ku pfunga swi tshikiwe loko tool_choice ehatisa tafula, naswona loko xihakaheli xi tlangela xihakaheli xa tafula (muxaka wa xihloko xa xona i pfuxeto xa tafula), hikuva Anthropic yi lava ku tshamela ku xavisa ku ehleketa lokue vumelwileke ka nkarhi lowu hundzekeke. Swiyonge hi endleni ka mahala ya Responses na Messages.

Ku n'wi tlhantlha ku ta ku tsena. message.reasoning_content, kumbe delta.reasoning_content loko u tshama u tshama u vutlhariya, u nga wu endli ku tlakana na mbulavulo wa mphendulo. Ku hlamusela i swilo leswi u swi humisaka naswona swi xupheteleka hi ndlela leyo, eka... completion_tokensHi xikongomisi xin’wana xin’wana xi nga tshikoni ku khomisela xitsalwana xa ku hlamusela, kambe ku tshama ku ri ni mali.

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);

Switlhanyi swa muhlala

Xandza eka vito ra model swi cinca ndlela xicelo xi lavulelaka xona, bila ku ri na xiyenge xin'wana. Swi tirha eka ma-id lawa ma heleleke na mavito lawa ma komiaka, ku fana na anthropic/claude-sonnet-5:online.

Xikongetelo xin'wana xin'wana xi tshikiswa. Xivito hinkwasvo xi lulamisiwa ku sungula, hi ku va xihlamuselo lexi nga ni idzi ta nkarhi (colon) xi tshama xi tirhisa; loko swi nga khomi, xin'wana na xin'wana xa xin'gabetelo xi tshikiswa ku suka ematolo ku fika loko xihlamuselo xi kumaka ku fana na xona. Xivito xa xihlamuselo xi nga va ni madyondjo ya 200 hi ku tala ni xin'gabetelo xa 4 hi ku tala; xin'wana lexi neneleyeke xi nyikiwa ku nyima hi ku va na 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);

Ku xavisa eka webu

Ximo ya nkarhi hinkwayo yi nga kota ku hlamula eka we nkarhi wa le ku sichi. Nymbot yi tsaratela mbulavulo wa vuxavisi bya le ku xin서 (swikarumata swa 2,000 swa le ku sungula), yi hlaya mapheji ya le hansi ya ntumbuluko ya ma, ya va nyika eka ximo na xivutiso, yi va yi veke hi ndlela leyi kombisaka leswaku i swilo swo teka ehandle leswaku ximo yi nga tlangi swikombiso eka swona. Ku na mindhavuko ya mivimbeko ya mivimbeko ya le hansi:

• Funa nkarhi hinkwawo: "plugins": [{"id": "web", "max_results": 5}], ka hi a :online suffix eka model.
• Lava loko swi pfuna: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}], nakambe hakuri na web_search_preview kumbe openrouter:web_search. Nymbot wu tshama wu khumba siku ntsena loko xiphiqo xi vonaka xi lava vutshila bya sweswi, xitshiketo lexi xi tshamaka xi xi tirhisa kona.

max_results i 5 hi xitalo naswona hi ntlango i 10. Tindhawulo ti ta humelela hi nymbot.web_search.sources, xin’wana na xin’wana xi ri na a title, snippet na url, naswona hi ta ku ta url_citation swivuriso eka xiyimbeletelo

Xilenge xinhi xin'wana xin'wana lexi hlekiwaka xi xupaxa $0.008, lexi hundzuluxeriweke eka sats, eka ti-tokens, naswona i nkarhi wa ku tshama. Mahelisi yo hlaya i ti-input tokens na yena, naswona mbululo eka web i xupaxa ku tlula mhala-mhala ya xivutiso lexi hi ku tisa hi ku nga ri na nkarhi, nthandzi nkarhi lowu hundlulaka.

Muxwayelo, hi xiphanze

"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);

Swivutiso swa API

Xihundzuluxaka lexi tsavanaka ka OpenAI, lexi tirhisiwaka hi OpenAI Agents SDK na hi Codex. Xi tshama xi tirhisa mivutiso, ximalembelelo na swiphiqeti leswi fanaka na Chat Completions.

POST https://nymbot.ai/api/v1/responses — e hlayiwa hi API key.

Mpfuxeto

{
  "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 }
}

Xitirho xa ku kombela xitirhisi xi humelela eka output hi ku ri function_call xihloko hi call_id, name na arguments; tshama phatliyeni ntsena ku fana na a function_call_output xihundla xa loyi a nga fanaka na xona call_id. Ku hlamusela, loko model yi ku khomisa, i a reasoning xihloko hi reasoning_text nchumu, lowu sunguluxiweke khale. status i incomplete loko ximhutlo xi hundzukile max_output_tokens kumbe muhumuyi u kombitele ku nga pfumeli, na incomplete_details.reason setelaka e ku max_output_tokens kumbe content_filterXiphesbetelo xi tlula na swona swiyimo swa xikwembo (temperature, switirhi, nchiyiselo swa switirhi na swinyana-nyana) hi ku fana na leswi OpenAI yi swi endaka, naswona xi rhendzelela... nymbot xigebelo swilo.

Ku fambisiwa, nchumu ngun'wana na un'wana i... event: xihlangu ni a data: xivunyi xa a sequence_number, hi nkarhi lowu: response.created, response.in_progress, response.output_item.added, response.content_part.added, ntsena xiyenge xa response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, naswona hi ku pfumala response.completed hi ku tirhisa ka na mali. Mbalkulu wa mh回答 wu fika eka response.incomplete exikarhi, naswona ku pfulamiwa hi lexi xikiniki xi sungulaka na response.failed. Ku hlamusela swi fambela hi xiyenge xa vona hi ku na response.reasoning_text.delta na .done. Swikombiso swa switirhisiwa swi ta landza ntshumayelo, xin’we xin’we hi ndlela ya xitemu lexi nga na response.function_call_arguments.delta na .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);

Swivulwa swa Anthropic

Xihundzuluxi xa Anthropic, ekatsongo ka Anthropic SDKs na Claude Code. Swi tirhisa na model hinkwaswo eka catalog, a swi Claude ntsena: xicelo xi hundzululwa, xi famba eka pipeline yin’we, naswona xi hundzululwa swindzaku.

POST https://nymbot.ai/api/v1/messages — e hlovotela API key, hi ku ri, as x-api-key kumbe Authorization: Bearer.

Leyi anthropic-version na anthropic-beta mitlhantlo yi amukeriwa naswona yi nga tikarhelwa. Swivongo swa Anthropic swi hlamuseleriwa eka xichaviso, hi kuva Claude Code na SDK swi tirhisa minhlawa leyi ti tivaka:

• Vito lexi xikatalogi xi ri tivaka, hi xikombiso claude-sonnet-5 kumbe anthropic/claude-opus-5, yi tirhisiwa njhani hi xiyimo xa wona.
• Loko ku ri ri nkarhi (-20260514), -latest, xinghenisiwa xa vuxokoxoko hi ku fana na -v1, xitiki xa ku lulamisa xi kombisiwaka hi ku tshama eka xikamu xa... [1m] naswona na anthropic/ kumbe anthropic. switsundzu swi tekiwa, naswona mitsapfu na mitsatuna exavulweni swi lwiwa hi tindlela hinkulu yo hadi (claude-haiku-4-5 swilo leswi kumaka keiwe claude-haiku-4.5).
• Loko swi nga ha kumekanga xin'wana na xin'wana, mivito (Opus, Sonnet kumbe Haiku) yi tirhisiwa, handle ka leswaku vuxokoxoko bya katalog i xin'we kumbe byi vaxile lexi kombetiweke na xona.
• Vito le le nga riki nchumu xin’we xi vuyile 404 not_found_error.

Mpfuxeto

{
  "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 a nga khona ku tshama na ku helda tool_use ti-blocks na a thinking xigumba, loyi a nga signature i nkarhi lowu a ri na nchumu. stop_reason i end_turn, max_tokens, tool_use kumbe refusal, swi endliwe hi ndlela yin’we hi ta finish_reason ya hi Ku fambisela ka ku tswala ku vulavula; stop_sequence swi hi ku tshama null, hambi loko ndzhaku-makhombo wa ku kumisa wu xedze mhrespondzo. input_tokens swihl counted swihl eka mianu ya valaharhi فحسب; swihl eka cache swi ri eka swa cache swimbirhi. Xikongomelo xi ri eka nymbot xihlamuselo na X-Nymbot-Cost-Sats nhlamuselo.

Loko swi vhekiwa hi ku fambisela, swilo swi ri swa Anthropic: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta kumbe thinking_delta), content_block_stop, message_delta hi ntsako wa ku miya, vukosi na ku nymbot xiga xa xiholongorisi, naswona message_stop. A ping yi tsariwa swi fika ka masiku ya 15 loko xitshuri xi tshama xi tshamela ku kanza. Switirho swa switoolo swi fika hi ku landza mavungetsana, xin'wana na xin'wana xi ri nga tool_use minketa hi xin'wana eka xin'wana xin'we lexi nga ni xin'wana xin'we hinkwaswo input_json_delta.

Swipuku eka endpoint leyi swi tirhisa xiyimberiso xa Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}. A minkarhi yo koma i 402 billing_error, muhengi loyi a hlayisiweke 503 overloaded_error. Ku tshovukela hi ku landza loko mutsariwo wu sunguluxiweke ku tumiwa hi ku ri error ndzhukanyana.

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);

Ku hlayisa tibala ta tokens

Xikombiso xa ku kulu ka tokens ta ku nghena leswi xikombiso xa Messages xi nga swi tirhisa, leswaku mutirheleli a nga swi hlamusela u n'wi tsandza. Swi mahala, kambe swi lava khodi (key).

POST https://nymbot.ai/api/v1/messages/count_tokens — e hlok cần API key. Mahala.

Xitshuri xi fana ni hi Miyekeletelo, nga ku ri na max_tokens; vito ra model yi fanele ku kumeka. Xikauko i xihlamuselo: mavuṋwana ya system prompt, miyalele, ku tirhisiwa ka switirhisiwa ni ku hlamuseleriwa ka swona ku hlukaniwa hi nirhemano wa mane, u kombisa 1,600 ku knuckles ka xifaniso xinye xinye. A hi tokenizer ya n'wini ya muhengeti, hi leswi xikauko xa ntiyiso xi nga va xi hlayeriwe hi ndlela leyi rilengeke. Khavishi leyi fikeleke ekusuveni yi nga ha kuma ku tirhisiwa.

Mpfuxeto

{ "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);

Ku veka mihavero

Xihlanganiso xa migomo ni makhonisi hinkwaswo leswi API yi nga swi amukelaka, na xikwembu xa swona. Xihlanganiso xi hlariwa eka katalogo leyi tshama yi ri kona yi fanana na leyi app yi tirhisaka eka xihlawulelo, hi kuva hi nkarhi wun’wana na wun’wana i leswi server yi nga swi tirhisaka.

GET https://nymbot.ai/api/v1/models — a nga ha dyondzwiki xaka. Swi hlayisiwe ku fika mintanu ya manejeni.

GET /api/v1/models/{id} swi khutla nchumu un’we.

Mitirheyi i leswi u ri payaxaka, hi swikhala na nkarhi lowu nga riki eka, hi madolara ni hi sats eka ndzhaka ya Bitcoin leyi nga riko şuŋku. balance u vula leswaku i mali yaaki leyi model yi yi tirhisaka. nymbot_key xivi xa xigandzela xa model hi le ka app. created hi nga rhenu 0, hikuva katalogi a yi tshini loko xiphemu xi enetiweke. Xiphemu lexi nga riki na mitsheketo ya mitala leyi tshimbileke yi tlangiwa hi per_request ematshan'wini.

nymbot/auto i yo hlayisa hi ku landza, yi tlhaselelwa hi ku fana na variable, hi na a routes xindhavuko lexi nyikaka xiyero hinkwaswo ka xindhavuko lexi tshamaka xi ri kona. Xi kombisa vumona na ku tsundzuka, kambe xi nga kombisi tiendlo.

GET /api/v1/models/{id} u amukela mavito ni mavito ya nchumu yo fanaka na xikwembu, naswona u tshimbileta vutloti bya xihloko lexi va fambelaka na xona.

Mpfuxeto

{
  "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"
    }
  ]
}

Swindlela swin’wana:

• Xifaniso swilo swi nga ni capabilities (accepts_image_url, requires_image_url, edit) na vuxavisi per_generation.
• Xihlanganiso swilo swi nga ni max_duration_seconds na resolutions, naswona xikongomelo per_second hi ku xavisiwa hi xin’wana hi xin’wana.
• Madzana swilo swi nga ni audio_type speech kumbe transcriptionyi nga ni mali per_1k_chars kumbe per_minute.
• Ku veka exi swilo swi nga ni dimensions, context_length, max_inputs kumile xihlavu xa mihlolo ya matshini ya input tokens.

Mitindzinga yi kombiwe "estimated": true swakanyana wa app hi generator leyi nga riki na xihlamuselo xa xihlovo xa yona. XihlamuselaLEXI xingoti... type ndzhaka 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);