Nheyo yezivo / Vanakovaka micheto

Kukurukurirana, Mhinduro nemashoko

Nzira nhatu dzekubvunza mufananidzo chimwe chinhu, mumapeji matatu anozivikanwa nevatengi anogara vachishandisa mamodeli amwe chete uye kubhadharwa nenzira imwe chete.

Peji ino yakaturikirwa nemuchina kuti zvirerukire. ChiRungu chepakutanga ndiyo shanduro inoshanda.

Kugadziridzwa kweMakurukuri

Format yemubvunzo yeOpenAI, uye rimwe rinogona kuwanikwa pane zvishandiso zvakafanana nezvinhu zvose. Tumira nyaya yataive nayo kusvikira zvino uye uwana shoko rinotevera.

POST https://nymbot.ai/api/v1/chat/completions — inoda API key.

Chete model uye messages ...zvinodiwa. Parameter yekusarudza imudhorofu yakasarudzwa isingazviitiri inobviswa pasina chiongo, saka request body imwe chete inoshanda pamudhorofu ose. Cherechedzo yemudhorofu inopa yega yega... supported_parametersZvinomirwa pane kusiya chinhu chipi zvacho: zvose zvinoshandiswa nechipuremodhi zvingave zvisingakwanisi kuita zvachose: mifananidzo kune chipuremodhi chisingakwanisi kuona, zvishandiso kune chipuremodhi chisingakwanisi kuzvishandisa.

Mhinduro ndeyemhando yakajairika chat.completion, nemutengo uri mu usage.cost (muma dhora) uye mu nymbot chinhu. model ndiyo idhi yemudanamu yakagadziriswa, kuti zita jena rinodzoka rakazara. Kana mudanamu akafunga pamberi pekupindura, kufunga kwacho kuri mu message.reasoning_content, yakasiyana nemhinduro.

Mhinduro

{
  "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 zvakabuda pakubva pane zvakadzoka, sezvo vanopa zvinhu zvakasiyana: tool_calls panguva yaive model ichikumbira zvishandiso, length panguva pashandiswa mashoko ose akabvumidzwa (kana kuti model yakashandisa ose achifunga zvakawanda ikasazozosvitsa mhinduro), content_filter panguva mupaipi akaramba, uye stop zvisingamirire. usage.completion_tokens_details.reasoning_tokens ichi iguva rinogara riri 0: zvinovanzika tokens dzekufungidzira dzinoverengwa, uye dzinobhadharwa, muna completion_tokens.

Ma code estatus anopiwa neendpoint dzese ari pasi pe zvikanganiso.

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);

Kuteverera

Nekuda kwe "stream": true mhinduro inouya semaserve-sent events uku model ichiñora iyo. Chidimbu chimwe nechimwe i chat.completion.chunk pamusoro pe data: mutsetse, uye mushando unopera ne data: [DONE]. Kufunga kunouya mu delta.reasoning_content, mhinduro iri mu delta.content.

Stream zvinhu zvose zvinogona kutora kupfuura masekondi anoda kusvika 100, sezvakaenzaniswa mhinduro refu, kana imwe huru max_tokens kana reasoning model. Chikumbiro chisiri chekuti chitaridzwe zvishoma nezvishoma (streamed) hachididisi chinhu kusvikira mhinduro yapera, uye network iri pakati penyu naNymbot inogona kuvhara kudyidzana kusashanda pakare iine masekondi anoda kusvika 100; model inopedza basa uye zvazvanyora zvinobhadharwa, asi mhinduro inorasika. Stream inotuma zvinhu zvinochengetedza kudyidzana kusimbe, saka inorarama kwenguva yese yekuti model inonyora.

Flow

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]

• Mitsetse inotanga ne : maonero ekugadzira (keep-alive comments) anotumirwa masekondi gumi nemashanu acho ose panguva iyo model iri kufunga. MaSSE clients anovasiya.
• Kubvunza kana kukumbira "stream_options": {"include_usage": true} kuti uwane chikamu chekupedzisira pamusoro, nechisina chinhu choices, nhamba dze-token, mutengo uye... nymbot chinhu.
• Mari inobhadharwa kana kumberi kwemanyorerwo (stream) kwapera. Kana ukavhara hukama nekukasira, model haimiriswi: Nymbot inoverenga chikamu chakasara cheprovider's stream, kusvika masekondi makumi maviri nemashanu, kuti iwane nhamba yemashoko (token count), uye unobhadhara zvinotaurwa neprovider. Pasina nhamba iyoyo, mari inokombanzirwa kubva pane zvawanyora nezvazvo zvakanyorwa, pamwe chete nemubhadharo wese weoutput wemodel inofunga.
• Error kusati kwechikamu chekutanga, semuenzaniso 401 kana 402, inodzoka se JSON yakabatidzwa nemavara ayo ekugamuchira status code, kwete semasimu. Error inouya mushure mekunge simu yakatanga sechinangwa chekupedzisira data: {"error": {…}} chitukadzo, uye mtsvairi unopera asina [DONE].
• Zvikumbirwa zvine zvishandiso, uye mamodeli ari paOpenAI's Responses transport, haasi kuenderera mberi nekutumira mhinduro (stream) kubva kumushandisi. Anogara achipindura ne-stream yakakodzera, inotumirwa kana mhinduro yopedza.

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);
}

Kukoka zvishandiso

Tsanangura mabasa mu tools uye mudanhanho unogona kukumbira kuti mumwe uchengetedzwe pane kupindura. Unodzadza function, uchiwedzera mhedzisiro yayo se tool shoko rakadai tool_call_id, uye tuma hurukuro iyoyo zvakare. Nymbot haina kumbofambisa mafunction ako; inoisa chikumbiro chemodel pachako.

tool_choice anotora "auto", "none", "required" kana {"type": "function", "function": {"name": "…"}}. Cherechedzo yedata inoratidza mamodeli anogona kushandisa zvishandiso (capabilities.tools). Zvishandiso zvakanzi zviratidzwa nezvazvo 400 unsupported_tool pamusoro nymbot/auto uye pane mamodeli mashoma emuchati anofamba neOpenAI's Responses transport, ayo Nymbot asingakwanisi kupasisa zvishandiso kuzvo.

Nekuda kwe "stream": true, chikumbiro chine zvishandiso chinofamba sechinhu chimwe chete uye unozopedzisira kutumirwa semaseries yemabhuku zvakajairika: basa (role), chikamu chimwe chinotakura kuedza kwechishandiso chega chega chine index yacho, id, zita nezvinhu zvakapiwa (arguments), uye chikamu chekupedzisira. Vashandisi vanoverenga kuedza kwezvishandiso zvakafambiswa vanozvikwanisa sezvavanoita sezvakajairika.

Mhinduro, nemutauro wepanzi

"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);

Mifananidzo muchikumbiro

Mamonjekeredzo ane capabilities.vision anogona kuverenga mifananidzo. Wedzera an image_url chikamu chemashoko emushandisi, kune imwe yaererano inozivikanwa nevanhu wose https:// link kana a data:image/…;base64, URL. Mifananidzo inosvika 20 paku chiedzo chimwe nechimwe. Mifananidzo yeSVG inorambidzwa, pamwe chete nelink yakareba kupfuura pasi ye4,096 characters kana ine zita remushandisi kana password mukati mayo (400 invalid_image_url). Chinogona kusarudzwa detail ndiko auto, low kana high.

Nekuda kwe nymbot/auto, chikumbiro chine mifananidzo chinoendeswa kumudhomu yepedyisero inokwanisa kuona. Mudhomu yemakatalogu isina capabilities.vision anobata mifananidzo ne 400 unsupported_contentMifananidzo inogona kuva mumameseji emushandisi chete. Link inofanira kunge ichiratidza kune vanhu vose; Nymbot inopa mufananidzo kune anoshandisa model uye haichaisviri.

Mufananidzo unobhadharwa sematoken ekupinda anoverengwa nemugovisi, sezvak

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);

Kufunga nenzira inobatsira

Mamonjekeredzo ane capabilities.reasoning vanogona kufunga vasati vapedza kupindura. Kumba zvakawanda kana zvishoma chesheya ne reasoning_effort ("minimal", "low", "medium" kana "high") kana "reasoning": {"effort": "high"}, kana kuti wedzera :thinking kuna zita remudhoroni, izvo zvinoreva kushanda zvakanyanya. Pamudhoroni usina kufunga mupfundo uyu unonyengedwa. Nekuda kwe nymbot/auto, :thinking anoisa kubvunza kune nzira yakajairika yekufungidzira.

Pamakomiti eAnthropic kushanda kunova kwemari yeungwaru inosanganisira tokens dzinenge 1,000, 2,000, 8,000 kana 16,000, kusvika pakupedzisira kwete kupfuura max_tokens zvinobvumira. Kufunga kunosimira kana tool_choice anopa simba kuutano, uye kana chikumbiro chichiramba chichitevedza mutambo weutano (shoko racho rakapedzisira izvibatsiro zveutano), nekuti Anthropic inoda kufunga kwakanyorwa kare kuti irambe ichienderera mberi. Zvakafananawo pane ma endpoints eResponses neMessages.

Kufunga kwadzoka mupedyo message.reasoning_content, kana delta.reasoning_content Pakuburitsa (streaming), usazviisire mhinduro. Kufunga (reasoning) kuri kupururwa uye zvinobhadharwa sezvazvinenge zvacho mukati. completion_tokensVamwe nevadzivadzi havambobudisi zvakare zvirevo zvechikonzero, asi zvichiri kubhadharwa.

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);

Mazvikisidzo emuenzaniso

Zvikamu zviri kumagumo pazita remudanho zvinoshandura mashandiro ekuishandisa, pasina chimwe chikamu chimwe. Zvinoshanda pazvikamu zvizere nezvikamu zvakaderera zvakare, sezvinofambidzana ne anthropic/claude-sonnet-5:online.

Mavharidzo (suffixes) emamwe ose haatorwi. Zita rese rinowanzoedzwa kutanga, saka model ine id inenge ine colon inoramba ichishanda; kana izvozvo zvisina kubudirira, mavharidzo anobviswa kumagumo mumwe nemumwe kusvikira pane model inonyatsoenderana. Zita remodel rinogona kuva necharacters mazana maviri chete, uyezve uine mavharidzo mana chete; rimwe rakareba rinorambidzwa ne 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);

Kutsvaga pawebhu

Mubvunzo wese wechat model unogona kupindura kubva pawebhu yakavhurika. Nymbot inotsvaga meseji yekupedzisira yemushandisi (micherechedzo yayo yekutanga inoti 2,000), inoverenga mapeji akanaka uye inopa kumuchina (model) pamwe chete nemubvunzo, yakanyorwa sezvinhu zvekunze zvine kuti model isatambira mirayiro kubva nazvo. Pane nzira mbiri:

• Gara uchitsvaga: "plugins": [{"id": "web", "max_results": 5}], kana a :online chishure pamudhomu.
• Tsvaga kana zvichibatsira: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}], zvakare zvakagamuchirwa se web_search_preview kana openrouter:web_search. Nymbot kunotsvaga chete kana mubvunzo uchiita seuri kuda ruzivo rwezvino, onovorero imwe chete iyo app inoshandisa.

max_results iri i5 nekushandiswa kwemanyorerwo uye chinogona kusvika ku10. Mibvunzo inouya mune nymbot.web_search.sources, imwe neimwe ine title, snippet uye url, uye sezvo url_citation tsananguro pamusoro pe shoko

Mushandisirwo wekutsvaga wega wega unodhura $0.008, yakashandurwa kuenda ku sats, pamusoro pe ma tokens, uye inzvimbo yemubhadharo. Mapheji aakaverenga iwowo ma input tokenswo, saka mhinduro kubva pawebhu inodhura kupfuura mubvunzo uyu ukafumbira, dzimwe nguva inodhura zvakanyanya kudarika zvakare.

Mhinduro, nemutauro wepanzi

"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);

Mhinduro API

Chimiro chitsva cheOpenAI, chinoshandiswa neOpenAI Agents SDK neCodex. Chinomhanya pamamodeli, mari, nezvinhu zvakafanana nezveChat Completions.

POST https://nymbot.ai/api/v1/responses — inoda API key.

Mhinduro

{
  "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 }
}

Chikumbiro chechishandiso chinouya mu output se... function_call chinhu chine call_id, name uye arguments; tumira mhedzisiro yacho kumashure sezviri a function_call_output chinhu chine cheita nacho call_id. Kufungidzira, kana mudi (model) achiunza, imhando ye reasoning chinhu chine reasoning_text zvinhu, zvakarudza kutanga. status ndiko incomplete panguva painoziva mhinduro max_output_tokens kana muenzanisi akazvidzivirira, ne incomplete_details.reason isa ku max_output_tokens kana content_filterMhinduro inodzokorora zvakare zviziviso zvekuvhumbidza (temperature, zviridzwa, kusarudzwa kwechishandiso nezvakawanda) sezvinoita OpenAI, uye inotakura nymbot mutengo wobjekti.

Yakafambiswa, chiitiko chimwe nechimwe chiri event: Mutsetse uye imwe data: mutsetse une a sequence_number, mukutevedzano uyu: response.created, response.in_progress, response.output_item.added, response.content_part.added, nhamba yaibva response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, uye pakupedzisira response.completed nekushandiswa nekudharama. Mhinduro yakagadzwa kupera inopera ne response.incomplete panzvimbo pazvo, uye kushaya pashure pekuti stream yakatanga ne response.failed. Pfungwa dzinobuda sezvinhu zvakatsvinda nezvacho response.reasoning_text.delta uye .done. Kuita zvinhu zvinoshandiswa nemichina kunouya mushure memashoko, chimwe nechimwe chiri chinhu chine response.function_call_arguments.delta uye .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);

Meseji dzeAnthropic

Chirongwa chaAnthropic, chemaSDK eAnthropic neClaude Code. Chinoshanda nemamodeli ose ari mubhuku racho, kwete Claude chete: chikumbiro chinoshandurwa, chinofambiswa nemuchina mumwe chete, uye chinoshandurwa zvakare.

POST https://nymbot.ai/api/v1/messages — inoda API key, sezvo x-api-key kana Authorization: Bearer.

The anthropic-version uye anthropic-beta maheaders anogamuchirwa uye anofereka. Mazita emamodeli eAnthropic anosanganiswa necatalog, saka Claude Code neSDK dzinoshanda nemazita adzo arikozati:

• Zita rinozivikanwa nebhuku remazita, semuenzaniso claude-sonnet-5 kana anthropic/claude-opus-5, inoshandiswa sezviri.
• Zvisinei nezvo zuva (-20260514), -latest, chimango cheversion semuenzaniso -v1, tag yakavharirwa yakadai se [1m] uye an anthropic/ kana anthropic. mapurofayitsi anobviswa, uye mapoinzi nematashu muchikamu ichi anedzwa nemazwi maviri ose (claude-haiku-4-5 anowana claude-haiku-4.5).
• Kana zvichiri kusaw
• Zita risingatsigirwi nechimwe chinhu rinodzoka 404 not_found_error.

Mhinduro

{
  "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 inogona kubatawo tool_use mabhloci nea thinking bhuroki, weana signature zvakashome. stop_reason ndiko end_turn, max_tokens, tool_use kana refusal, yakaitwa nenzira imwe chete yakafanana ne finish_reason pamusoro Kugadziridzwa kweMakurukuri; stop_sequence kazhinji ndezvekuti null, kunyangwe nguva yapera kuitira kuti mhinduro ipe. input_tokens kuverenga mushandisirwo mutsva chete; mushandisirwo wakachengetwa uri mumamiriro maviri ekuchengetedza. Mutengo uri mu nymbot chinhu ne X-Nymbot-Cost-Sats musoro.

Zvakatsanangurwa, zvinhu zvinenge zveAnthropic: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta kana thinking_delta), content_block_stop, message_delta nekuda kwezvikonzero zvekumira, kushandiswa uye nymbot chinhu chemutengo, uye message_stop. A ping inozivikanwawo inosendwa masekonzi gumi nemashanu ega ega panguva iyo model iri kushanda. Tool calls dzinouya mushure metext, imwe neimwe se tool_use chikamu chine zvose zvakapiwa nazvo pachimwe chete input_json_delta.

Zvikanganiso pane endpoint iyi zvino kushandisa format yeAnthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}. Mari shoma yakasara ndeye 402 billing_error, muenzaniso wemushandisi akadhinda nezvinhu zvakawanda 503 overloaded_errorKukanganisa mushure mekunge kusimudzirwa kweflow kwatanga kunotumirwa sezvakaita error chiitiko.

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);

Kuverenga ma-token

Kufungidzira kwezvikamu zvemazwi (input tokens) zvinoshandiswa nekuvhura Messages, kuitira kuti muvhiri akwanise kuongorora musati aituma. Hazvibhadharwi, asi rinoda kiyi.

POST https://nymbot.ai/api/v1/messages/count_tokens — inoda API key. Zvakachipa.

Muviri uri zvakafanana neuri wekuti Meseji, isina max_tokens; zita remodeli rinofanira kuzivikanwa. Nhamba iri kutaridza kufungidzira: mashoko emusimboti wecomputer, mameseji, kubvunza zvishandiso nezvikamu zvezvishandiso zvakakamurwa nezvikamu zvina, pamwe chete ne1,600 kuwedzera pamuchidimbu chepfoto imwe chete. Ihwo hausi tokenizer yemuenzaniso uyo akashandiswa, saka nhamba yeku真实 inogona kusiyana. Chii chakasvika pamugumo chekushandiswa chinogona kuramba chichishandiswa.

Mhinduro

{ "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);

Kuratidza mhando dzemichina

Modhiro iye rimwe nerimwe nemagenerator API inogamuchira, pamwe chete nekudhara kwazvo. Cherechedzo iyi inoverengwa kubva kuкатаira yakafanana neiyo inoshandiswa neapp picker, saka inzvimbo inogara iri yezvinotenderwa neserver.

GET https://nymbot.ai/api/v1/models — hapana kiyi inodiwa. Yakachengetwa kwemaminitsi mashanu.

GET /api/v1/models/{id} kunodudza chimwe chinhu.

Mitengo ndiyo yamuri kubhadhara, ichina mari yekubhadhara nemargin kare, muna madhora nemuna sats pacheri remutengo weBitcoin wanhasi. balance inotaura kuti model inopedza mari ipi. nymbot_key zita diki remudhori riri mubhuku reapp. created ihwo imhando ya 0, sezvo catalog isina kuita rekurekodha kuti model yakaiswa rini. Model isina kukwanisa kuonekwa ne rates dzinodhura per_request pachinzvimbo.

nymbot/auto inhamba yekutanga nguva dzese, ichiyirwa se variable, ne routes orodha inopa mahara emudzira wega wega. Inonyora nezvekuona nekuvhunza, asi haidari nezvemapfekceso.

GET /api/v1/models/{id} inogamuchira mazita nemazita emuchimiro akafanana nechikumbiro, uye inodzorera chinyorwa chemudeli izvo zvinoenderana nazvo.

Mhinduro

{
  "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"
    }
  ]
}

Mamwe mhando dzakasiyana:

• Mufananidzo zvinowanikwa ne capabilities (accepts_image_url, requires_image_url, edit) uye mutengo per_generation.
• Vhidhiyo zvinowanikwa ne max_duration_seconds uye resolutions, uye mutengo per_second kwese mhando yeunzeve.
• Madzimai zvinowanikwa ne audio_type speech kana transcription, ine mutengo per_1k_chars kana per_minute.
• Kusimbisa zvinowanikwa ne dimensions, context_length, max_inputs uye mutengo weimwe milioni yemashoko anopinda.

Mitengo yakanyorwa "estimated": true ndezve kutarisa kweapp pane generator imwe chete isina kupa mutengo. Isingazivikanwi type Anodzoka 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);