Bażi ta 'għarfien / Żviluppaturi

Chat, Risposti u Messaggi

Tliet modi biex tistaqsi mudell xi ħaġa, fis-tliet formats li l-klijenti jużaw wisela, kollha taħt l-istess mudelli u b'l-istess mod ta' fatturazzjoni.

Din il-paġna hija tradotta bil-magni għall-konvenjenza. L-oriġinal bl-Ingliż huwa l-verżjoni li tapplika.

Chat Completions

Il-format ta' chat tal-OpenAI, u dak li kważi kull għodda tappoġġa. Ibgħat il-konversazzjoni sa('%) issa u iqteddan l-aħjar messaġġ.

POST https://nymbot.ai/api/v1/chat/completions — jeħtieġ ċav API.

Chekk model u messages reqjiet. Parametru ta' kampjunazzjoni li l-mudell magħżul ma jieħu xejn huwa mħassir mingħajr żball, għalhekk korpus ta' petizzjoni wieħed jaħdem fuq mudelli differenti. Il-lista tal-mudelli tagħti għal kull mudell il- supported_parametersHuwa li jiġi rfidut minn qabel li jidħol f'kull xi ħaġa li l-mudell ma jistax jagħmel għal kollox: ritratti għal mudell li ma jistax jara, għodod għal mudell li ma jistax isejjaħhom.

Ir-risposta hija ordinarja chat.completion, bil-kost f' usage.cost (fid-dollars) u fil- nymbot oġġett. model huwa l-ID tal-mudell irrisolut, għalhekk ismi qasir jiġi rritornat bħala dak sħiħ. Jekk il-mudell ħażen qabel ma jwieġeb, ir- raġunament tiegħu jinsab f' message.reasoning_content, separat mill-risposta.

Rispons

{
  "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 ġie kalkulat minn dak li ġie rritornat, poiché l-fornituri jirrapportawha differmenti: tool_calls meta l-mudell talep għal għodod, length meta l-ispett siegħed uża kull token permess (jew il-mudell ħallas kollha u mwiexi xejn ispett), content_filter meta l-fornitur irrefuża, u stop otherwise. usage.completion_tokens_details.reasoning_tokens dejjem huwa 0: moħbi it-token tal-moħħa qed jiġu kontati, u rritratati, f' completion_tokens.

Il-kodiċi tal-istatus li kull endpoint jaqsam huma elenkti taħt errogi.

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);

Streaming

Ma' "stream": true l-ispettar jasal bħala server-sent events waqt li l-mudell jiktbu hija. Kull avveniment huwa a chat.completion.chunk fuq a data: linja, u l- istrim jintemm b' data: [DONE]. Ir-raġunament jasal f' delta.reasoning_content, it-tweġiba f' delta.content.

Istrajja kull xi ħaġa li tista' tieħu aktar minn madwar 100 sekond, bħal tweġiba twila, xi ħaġa kbira max_tokens jew mudell ta' ragionament. Rieqwesta li mhix imstreamata ma tibgħatx xejn sakemm it-tweġiba tkun kompleta, u n-netwerk bejn inti u Nymbot jista' jagħlaq konezzjoni inattiva wara madwar 100 sekonda; il-mudell ikompli u dak li kitbet jiġi ċċarġat, iżda t-tweġiba tintilef. Stream jibgħat 'keep-alives', għalhekk jibqa' miftuħ skont kemm il-mudell jikteb.

Sajla

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]

• Linji li tibda b' : xkom kummenti keep-alive, ims Barbija kull 15 sekonda waqt li l-mudell qed jaħseb. Il-klienti SSE jgħodlu fuqhom.
• Ħares għal "stream_options": {"include_usage": true} biex tikseb il-parti l-aħħar fuq, b'wieħed voj empty choices, il-konti tat-token, il-kost u l- nymbot oġġett.
• Il-charge jissettja wara li tispiċċa l-streaming. Jekk tagħlaq il-konnessjoni prematurament, il-mudell mhuwiex iwaqqaf: Nymbot jaqra s-strażijiet tal-fornitur, għal massimArr hum 25 sekondi, biex jilqas il-kont tax-token tiegħu, u int tħallas dak li jirrapporta l-fornitur. Mingħajr dak il-kont, il-charge jiġi stima mill-input tiegħek u minn dak li kien miktub, plus l-għan kollu tal-output għal mudell li janalizza.
• Error qabel l-ewwel parti, bħal 401 jew 402, jirritorna bħala JSON ordinarju bil-kodiċi status tiegħu, mhux bħala stream. Error wara li l-stream tibda jiġi rċevut bħala l-aħħar data: {"error": {…}} avveniment, u l-istrim jintemm mingħajr [DONE].
• Ir-requestijiet b'għodod, u l-mudelli fuq it-trasport Risponsijiet ta' OpenAI, ma jagħtux streaming mill-fornitur. Xorta jwieġdu b'streaming validu, li jiġi trażmetti minn meta l-tweġiba tkun kompleta.

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);
}

Appelli ta' strumenti

Deskrivi l-funzjonijiet f' tools u l-mudell jista' jitlob li wieħed jiċċempel minflok iwieġeb. Int tiġri l-funzjoni, iżżid ir-riżultat tagħha bħala a tool messagg fuq l-istess tool_call_id, u erġa' ibgħat il-konversazzjoni. Nymbot qatt ma jexxi l-funzjonijiet tiegħek; huwa jgħaddi l-istaqsija tal-mudell lura għalik.

tool_choice tieħu "auto", "none", "required" jew {"type": "function", "function": {"name": "…"}}Il-lista tal-modelli timmarka liXI mudelli jistgħu jċċempelaw għodod (capabilities.tools). L-għodod huma rifiġut b' 400 unsupported_tool fuq nymbot/auto u fuq il-ftit mill-modelli tal-katalogu li jaħdmu fuq it-trasport ta' Responses ta' OpenAI, li Nymbot ma jistax jgħaddi għalihom għodod.

Ma' "stream": true, talba b'għodod taġixxi f'part ieħda u mbagħad tintiexi bħala sekwenza normali ta' partijiet: ir-rwol, part ieħda li ġġib kull appel għall-għodda b'l-index, id, ismi u argumenti tagħha, u l-part tal-finijiet. Il-klijenti li jaqraw tcalls tal-għodda streamed jittrattawha bħalxxejn.

Risposta, parzjalment

"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);

Ritratti f'rikwistjoni

Modelli ma' capabilities.vision jista' jaqra ritratti. Żid ... image_url parti ta' messaġġ għall-utenti, b'wieħed jew pubbliku https:// link jew a data:image/…;base64, URL. Sal‐inteдж 20 tal-istampa għal kull talba. L-istampi SVG huma rifiżati, u l-istess għal link li jgħaddi minn 4,096 karakteri jew wieħed li għandu username jew password fih (400 invalid_image_url). Fakultattiv detail huwa auto, low jew high.

Ma' nymbot/auto, talba b'ritratt fiha hija mowna għal mudell standard li なestà jista' jara. Mudell tal-katalogu mingħajr capabilities.vision jirrifjuta ritratti b' 400 unsupported_content. Ir-ritratti jistgħu jkunru biss fil-messaġġi tal-utenti. Link għandu jaggiċi għal host pubbliku; Nymbot jgħaddi r-ritratt lill-fornitur tal-mudell u machekkijux.

Immaġni tiġi ċċarġata bħala l-tokens tal-input li l-fornitur jgħod għaliha, bħal il-bqija tar- requistjoni.

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);

Razzonament

Modelli ma' capabilities.reasoning jistgħu jaħsbu qabel ma jwieġbu. Istaqsi għal aktar jew mniej minnu b' reasoning_effort ("minimal", "low", "medium" jew "high") jew "reasoning": {"effort": "high"}, jew żid :thinking għall-isem tal-mudell, li jfisser sforz għoli. Fuq mudell mingħajr raġunament l-issettjar jiġi injorat. B' nymbot/auto, :thinking issends ix- talba għar-route tal-logika standard.

Fuq il-modelli ta' Anthropic, l-isforz isir budget ta' ħsieb ta' madwar 1,000, 2,000, 8,000 jew 16,000 tokens, qatt aktar minn max_tokens tippermetti. Il-ħsieb jitwaqqaf meta tool_choice iġbed għal tool, u meta l-ijaħbet il-joniest ikompli loop ta' tool (l-aħħar messaġġ tiegħu huwa riżultat ta' tool), għax Anthropic għandha bżonn il-ħsieb imsigillat preċedenti biex tkompli. L-istess japplika fuq l-endpoints tal-Responses u tal-Messages.

Ir-raġunament jerġa' jidħol message.reasoning_content, jew delta.reasoning_content meta tistradmi, qatt ma nothing imħallat fl-istampa. Ir-raġunament huwa output u huwa miżwergħ fuq dan, ġewwa completion_tokensXi provdejers ma jirritornawx affatto t-test tal-raġunament, u madankollu jiġi ċċarġjat.

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);

Sufissi tal-mudell

Suffissi fuq isem il-mudell jibdel kif tiġi mmaniġjata r-requesta, mingħajr kamp mill-ieħor. Huma jaħdmu fuq ID's sħaħ u fuq ismi qosra bl-istess mod, bħal f' anthropic/claude-sonnet-5:online.

​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​​&# 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);

Ispazju tal-web

Iċ-ċavrat kull mudell ta' chat jista' jwieġeb mill-web live. Nymbot ifittex l-aħħar messaggio tal-utent (l-ewwel 2,000 karatteri tiegħu), jaqra l-aqwa paġni u jagħtihom lill-mudell madal mistoqsija, immarkati bħala kontenut estern li l-mudell ma għandux jieħu instruzzjonijiet minnu. Hemm żewġ modi:

• Ippressi dejjem bil-ħsieb ta' tfittixija: "plugins": [{"id": "web", "max_results": 5}], jew a :online suffissu fuq il-mudell.
• Irfek meta jgħin: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}], ukoll aċċettat bħala web_search_preview jew openrouter:web_search. Nymbot ibbażża sħar biss meta l-mistoqsija tidher li għandha bżonn informazzjoni kurrenti, l-istess test li tuża l-app.

max_results huwa 5 b'mod awtomatiku u massimum 10. L-sorsi jiġu rritornati f' nymbot.web_search.sources, kull wieħ b' title, snippet u url, u bħal url_citation annotazzjonijiet fuq il-messaġġ.

Mhux kull bilanċ ta' tfriġa li jiġri jikkostja $0.008, konvertit għal sats, fuq it-tokens, u huwa parti minn l-hold. Il-paġni li qara huma tokens tal-input ukoll, għalhekk tweġiba mill-web tikkostja aktar minn l-istess mistoqsija mitluba mingħajr xejn, kult volte ftit xejn aktar.

Risposta, parzjalment

"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 tal-Risponsijiet

Il-format aktar ġdid ta' OpenAI, użat mill-OpenAI Agents SDK u mill-Codex. Jiddefina fuq l-istess mudelli, fatturazzjoni u karatteristiċi bħal Chat Completions.

POST https://nymbot.ai/api/v1/responses — jeħtieġ ċav API.

Rispons

{
  "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 }
}

Ġara tal-applikazzjoni ta' għodda tidher f' output bħala function_call oġġett b' call_id, name u arguments; ibgħat ir-riżultat lura bħala a function_call_output item b'listess call_id. Rażonament, meta l- mudell jirritorna dan, huwa a reasoning oġġett b' reasoning_text kontenut, imsemmija l-ewwel. status huwa incomplete meta l-imposta taħbat max_output_tokens jew il-fornitur irrifjuta, b' incomplete_details.reason ijiet għal max_output_tokens jew content_filterIr-risposta tirrifletti wkoll is-settings tal-appell (temperature, tools, tool choice u oħrajn) kif tagħmel OpenAI, u ġġib il- nymbot prezz oġġett.

Miż流 (Streamed), kull avveniment huwa an event: linja u a data: linja b'a sequence_number, f'ordni bħal din: response.created, response.in_progress, response.output_item.added, response.content_part.added, kwalunkwejn numru ta' response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, u fl-aħħar response.completed bil- użu u l-kost. Twegliba qasira tispiċċa b' response.incomplete minflok, u falliment wara li l-istrim inibda b' response.failed. Il-istrimmi tal-ħsieq bħala item proprju miegħu b' response.reasoning_text.delta u .done. Is-sejħiet tal-aċċjoniż jiġu wara l-messaġġ, kull waħda bħala oġġett b' response.function_call_arguments.delta u .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);

Messaġġi ta' Anthropic

Il-format ta' Anthropic, għall-SDKs ta' Anthropic u Claude Code. Jaħdem ma' kull mudell fil-katalogu, mhux biss Claude: it-talba tiġi tradotta, tiġi proċessata permezz tal-istess pipeline, u tiġi tradotta lura.

POST https://nymbot.ai/api/v1/messages — għandu bżonn chiave API, bħallhekk x-api-key jew Authorization: Bearer.

Il- anthropic-version u anthropic-beta headers huma aċċettati u jiġu mibdew. Isemmien tal-modelli ta' Anthropic huma mqabbja mal-katalogu, għalhekk Claude Code u l-SDKs jaħdmu mal-isemmien li jużaw diġà:

• Isem li l-katalogu jaf, bħal claude-sonnet-5 jew anthropic/claude-opus-5, huwa użat kif huwa.
• Altrimenti data (-20260514), -latest, tag ta' verżjoni bħal -v1, tag bracketed bħal [1m] u wieħed anthropic/ jew anthropic. il-prefixijiet jitneħħu, u l-punti u d-daħal fil-verżjoni jintrievu bil-mod eżattist\}$claude-haiku-4-5 tifsirien claude-haiku-4.5).
• Jekk dak għadu ma jaqbilx ma' xejn, jiġi użata l-familja (Opus, Sonnet jew Haiku), dital ma tkunx il-verżjoni tal-katalogu hija l-istess jew aktar ġdida mill-verżjoni mitluba.
• Isem li ma jtaqqa'x ma' xejn jirritorna 404 not_found_error.

Rispons

{
  "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 jista' też heldi wkoll tool_use blokki u a thinking blokk, ta' min signature huwa voj: stop_reason huwa end_turn, max_tokens, tool_use jew refusal, ħdem b'listess mod bħal finish_reason fuq Chat Completions; stop_sequence dejjem huwa null, anke meta sekwenza ta' waqf kemlet it-tweġiba. input_tokens kontijiet input frisk biss; l-input imħażen qiegħed fil-żewġ kampi tal-cache. Il-kost huwa fil- nymbot oġett u l- X-Nymbot-Cost-Sats header.

Istraumjati, l-avvenimenti huma ta' Anthropic: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta jew thinking_delta), content_block_stop, message_delta bil-raġuni tal-waqf, l-użu u l- nymbot objett tal-kost, u message_stop. A ping jitbaħat ukoll kull 15 segond waqt li l-mudell qed jaħdem. Il-kalli tal-istrumenti jaslu wara t-test, kull wieħ bħala a tool_use blokk b'l-input kollu tiegħu f'dak wieħed input_json_delta.

L-erruri fuq dan l-endpoint jużaw il-format ta' Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}. A bażi qasir huwa 402 billing_error, providur ipprovokat b'tagħrif żejjed 503 overloaded_error. Ftal wara li l-istrim inibda jitbagħat bħala error avveniment.

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);

Kontar ta' tokens

Stima ta kemm input tokens tal-joniċija ta' talba Messages tużi, biex il-klijent jista' jiċċekkja qabel meta jibgħatha. Huwa gratis, iżda għadu jeħtieġijiet avvanzat.

POST https://nymbot.ai/api/v1/messages/count_tokens — għandu bżonn API key. Gratwi.

Il-ġisem huwa l-istess bħal għal Messages, mingħajr max_tokens; isem il-mudell għandu jkun resolut. Il-kont huwa stima: il-karatteri tal-prompt tas-sistema, l-messages, it-tool calls u d-definizzjonijiet tal-tool diviżi għal erbgħa, plus 1,600 għal kull ritratt. Mhuwiex it-tokenizer proprju tal-fornitur, għalhekk il-kont reali jista' jiddifferiċja. Klavi li laqgħet il-limitu tagħha għadha tista' tużah.

Rispons

{ "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);

Lista tal-modelli

Kull mudell u ġeneratur li l-API taċċetta, flimkien ma' dak li jikkostaw. Il-lista tiqra mill-istess katalog tal-live kif dik tal-għażla tal-app, għalhekk hija dejjem dak li se jkun sejjer il-server.

GET https://nymbot.ai/api/v1/models — m'hemmx bżonn ċav. Kaxjat għal ħmist imins.

GET /api/v1/models/{id} jirritorna entry waħda.

Il-prezzijiet huma dak li tħallas, bil-ħarfien u l-margini inklużi diġà, fid-dollri u fis-sats fuq il- prezz attwali ta' Bitcoin. balance għid li għandux il-bażi li l-mudell juża. nymbot_key jiżda l-isem qasir tal-mudell fl-app. created huwa sempre 0, poiché l-katalogu ma jirreġistax meta kienet mudell iżda. Mudell mingħajr tmiem ta' telfa ppubblikat jiġi pprizza per_request minflok.

nymbot/auto dejjem huwa l-ewwel, ipprezzat bħala variable, b' routes lista li tagħti r-rati ta' kull ruta standard. Hi telista l-taħalluf u r-raġunament, iżda mhix it-tooli.

GET /api/v1/models/{id} taċċetta l-istess ismi u l-alias bħal tal-joniġ, u jirritorna l-entry għall-mudell li jirreżolwuh.

Rispons

{
  "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"
    }
  ]
}

It-tipi l-oħra:

• Imaġni dħoliet għandhom capabilities (accepts_image_url, requires_image_url, edit) u prezzu per_generation.
• Vidjow dħoliet għandhom max_duration_seconds u resolutions, u prezz per_second għal kull riżoluzzjoni.
• Audio dħoliet għandhom audio_type speech jew transcription, ipprezzat per_1k_chars jew per_minute.
• Embediment dħoliet għandhom dimensions, context_length, max_inputs u prezzu għal kull miljun token imbarrat.

Prezzijiet immarkati "estimated": true huma l-istima tal-app għal ġeneratur li l-prezz tiegħu mhuwiex ippubblikat. Xi mhux magħruf type ritorni 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);