Te turanga matauranga / Kaiwhakawhanake

Kōrerorero, Ngā whakautu me ngā karere

E toru ngā huarahi hei pātai ai i tētahi kōpato i tētahi mea, i roto i ngā tauira e toru e kōrerotia ana e ngā kaiwhakamahi anō, e rere ana katoa i runga i ngā kōpato e rite ana, ā, e utu ana i te huarahi kotahi.

He mihini tenei wharangi kia pai ai. Ko te reo Ingarihi taketake te putanga e tika ana.

Whakaputa Kōrero Atāwhai

Te hanganga kōrerorero a OpenAI, me te hanganga e tautoko ana e ia taputapu tata kō atu. Tuku te kōrerorero i tēnei wā, ka hoki mai te kaupapa kōrero kei muri ake.

POST https://nymbot.ai/api/v1/chat/completions — me he kupu raihirangi API.

Anakei model a messages he hia ana. He tauira parameter kaore i mau e te model i kōwhiria ka riro atu me te kore he hapa, kia mahi ai he rerekē te kaha o te rerekētanga o te rerekē i roto i ngā model katoa. Ko te rārangi model e whakaatu ana i te mea ia model supported_parametersKo te mea e whakahētia ana, kaua ko te tukuna noa, ko ia he mea kāore e taea e te mahere e mahi i te mea katoa: ngā pikitia mō tētahi mahere e kore e taea te kite, ngā taputapu mō tētahi mahere e kore e taea te karanga i a rātou.

He whakautu noa iho te āhua o te whakautu chat.completion, me te utu i roto i usage.cost (ki ngā tārau) me i roto i te nymbot whakaaturanga. model ko te id o te mahere kua whakatau, nā reira he ingoa iti te hoki mai hei ingoa tino katoa. Ki te whai i te mahere te mahere i mua i te whakautu, ko tōna whakaaro kei roto message.reasoning_content, whakarerekē i te whakautu.

Whakaaronga

{
  "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 he whakatau i te mea i hoki mai, nō te mea ka pūrongo rerekē ngā kaiwhakarato: tool_calls i te wā i pātai ai te tauira mō ngā taputaki, length i te wā i whakamahia ai ngā toku katoa e taea ana te whakautu (peka rānei i whakamahi katoa te tauira mō te whakaaro ka kore he whakautu), content_filter i te wā i whakakore ai te kaiwhakarato, ā stop tēnā rā anō. usage.completion_tokens_details.reasoning_tokens he 항상 0: huna ngā tohu whakaaro e tauria ana, ā, ka whakataunga, ki roto i completion_tokens.

Kei raro i te rārangi ngā kōti kōtuhi i tō katoa ngā pae mutunga ngā hapa.

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);

Whakaata mai noa atu

me "stream": true ka puta te whakautu hei ngā rārangi whakapuaki mai i te tūāpapa i te wā e tuhituhi ana te tauira i te mea. Ko ia rārangi he a chat.completion.chunk ki runga i a data: tātai, ā te mutunga o te wai o te awa me data: [DONE]. Ka tae mai te whaiwhakaaro ki roto i delta.reasoning_content, te whakautu i roto i delta.content.

Whakamāramatia he mea katoa ka taea e te wā e neke ake ana i te 100 iho i te hātea, pēnei i tētahi whakautu roa, he nui rānei max_tokens nā rānei he mahara whakaaro. Ko te tono kāore e rere (streamed) e kore e tuku i tētahi mea mō te wā e oti ai te whakatau, ā, ka huri te hononga waimea i waenga i a koe me Nymbot i muri i te 100 sekona; ka mutu tonu te mahara, ā, ka utu te mea i tuhia, engari ka ngaro te whakatau. Ko te rere e tuku ana i ngā 'keep-alive', kia noho pai ai te hononga i te wā katoa e tuhia ana e te mahara.

Awa

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]

• Ngā rārangi e tīmata ana ki : he whakamāramatanga keep-alive ēnei, ka tuku ia 15 hāora i te wā e whakaaro ana te tauira. Ka whakahokia e ngā kaipono SSE ēnei.
• Pātai atu mō "stream_options": {"include_usage": true} kia tae atu ki te waahanga whakamutunga i runga, me te kore he choices, ngā tauira token, te utu me te nymbot whakaaturanga.
• Ka whakatūngia te utu i muri i te mutunga o te rerenga. Ki te kati koe i te hononga i mua i te mutunga, kaore te tauira e mutu: ka pānui a Nymbot i te tohu o te rerenga o te whakarato, mō te rārangi atu i te 25 hētanga, kia whiwhi ai i te tauhenga token, ā, ka utu koe i te mea i arotakehia e te whakarato. Ki te kore i te tauhenga, ka whakarite te utu i runga i tō kōrero me te mea i tuhia, me te katoa o te whakaaetanga whakakī mō tētahi tauira e whai whakaaro ana.
• He hapa i mua i te wāhanga tuatahi, pēnei i a 401 kei te mea anō 402, hoki mai ana hei JSON noa iho me tōna status code, ehara i te stream. He hapa i muri i te tīmata o te stream ka tae mai hei te whakamutunga data: {"error": {…}} tūnga, ā, ka mutu te rere me te kore [DONE].
• Ngā tono me ngā taputapu, me ngā tauira i runga i te Responses transport a OpenAI, e kore e rere mai i te kaiwhakarato. Ka whakautu tonu rātou ki te rere tika, e tuku ana i te wā ka oti te whakautu.

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);
}

Ngā pango taputai

Whakaritea ngā mahi ki roto i tools ā, ā, ka taea e te tauira te pātai kia whakatinatia tētahi i te mea he whakautu. Ka whakahaere koe i te mahi, ka tāpiri i tōna hua hei a tool kaupapa pēnei tonu tool_call_id, ā, tuku anō te kōrerorero. Kāore e whakahaere i ō ngā mahi a Nymbot; ka hoki te tono a te tauira ki a koe.

tool_choice mātau "auto", "none", "required" kei te mea anō {"type": "function", "function": {"name": "…"}}. E tohu ana te rārangi tauira i ngā tauira e taea ana te karanga i ngā taputapu (capabilities.tools). He taputapu kei te whakakorehia me te 400 unsupported_tool i runga nymbot/auto ā me ngā tauira katalog iti e rere ana i te pae tūhono Responses a OpenAI, e kore e taea e Nymbot te tuku i ngā taputaki ki a ia.

me "stream": true, he tono me ngā taputaki e rere ana hei kotahi waahanga, ā, ka tuku kia rite ki te rārangi tūpono noa: te kaupapa, he waahanga e whakawhiti ana i ngā karere taputaki katoa me ā rānei index, id, ingoa me ngā whakawhitiwhiti, me te waahanga whakamutunga. Ngā kaipono e pānui ana i ngā karere taputaki e rere ana ka whakahaere i te mea hei noa iho.

Whakautu, i roto i tētahi wāhanga

"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);

Ngā whakaahua i roto i tētahi tono

Ngā tauira me capabilities.vision ka taea te pānui i ngā pikitia. Tāpirihia he an image_url wāhanga ki tētahi rongoako a te kaiwhakamahi, me tētahi i te tūmatanui https:// hononga rānei he data:image/…;base64, URL. Ka taea te tuku whakaahua e upu 20 i ia tono. Ka kore e whakaae ngā whakaahua SVG, me te hono e nui ake i te 4,096 ngā tohu, mō te rārangi hono e whai ana i tētahi ingoa pānga rānei he kōrero huna rānei i roto (400 invalid_image_url). He kōwhiringa detail he auto, low kei te mea anō high.

me nymbot/auto, he tono kei roto he pikitia e haere ana ki tētahi tauira tere ki te kite. He tauira katalogā kore... capabilities.vision whakakore i ngā whakaahua me 400 unsupported_content. Ka taea tonu te puta i roto i ngā karere a te kaiwhakamahi anake. Ko te hono me e whakaatu ana ki tētahi tūmatanui; ka tuku a Nymbot i te pikitia ki te kaiwhakahaere o te tauira, ā, kāore ia e noho mō ia.

Ka whakataunga he pikitia hei ianga tōku, pēnei i ngā tōtika rānei o te tono katoa e taupua ana te kaiwhakarite.

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);

Whakaaroaro

Ngā tauira me capabilities.reasoning ka taea te whakaaro i mua i te whakatapu iho. Pātai atu mō te nui ake, te iti rānei o ia mea me reasoning_effort ("minimal", "low", "medium" kei te mea anō "high") nekehe "reasoning": {"effort": "high"}, rānei tāpiri :thinking ki te ingoa o te tauira, e tohu ana he mahi nui. Ki runga i tētahi tauira kāore e whai whakaaro, ka kore e whai take te whakamahinga. Me nymbot/auto, :thinking tuku te tono ki te huarahi whaiwhakaaro tapatahi.

Ki ngā tauira a Anthropic, ka huri te mahi hei tahua whakaaro e tata ana ki te 1,000, 2,000, 8,000 rānei 16,000 tokens, e kore e nui ake i tēnā max_tokens āhei. Ka whakarerea te whakaaro i te wā tool_choice ka whakahau i tētahi taputapu, ā, ina haere tonu te tono ki te huringa taputapu (ko te tuओंa i muri iti rānei te huarahi whakamutunga he tukunga taputapu), no te mea me te whakaaro whāiti i whakamākatia i mua kia taea te whakaoho anō e Anthropic. E pēnei tonu hoki i ngā mutunga Responses me Messages.

Ka hoki mai te whaiaro matapaki message.reasoning_content, ki te mea ko delta.reasoning_content i te takatū streaming, kaua e whakauria ki te whakautu. Ko te whakaaroaro he hua ake i te tukuna ā, ā, ka whai utu hei mea pēnei, i roto completion_tokens. He kaiwhakahaere kē kāore e tukuna i te mea katoa te tuhinga whaiwhakaaro, ā, ka whai utu tonu.

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);

Ngā tūmomo whakaoti tauira

Ko te suffix ki te ingoa tauira e huri ana i te huarahi e whaihua ai te tono, me te kore tētahi ingoa hou. He mahi tahi rāua ki ngā id katoa me ngā ingoa iti, pēnei i anthropic/claude-sonnet-5:online.

Ka kore tētahi tae i muri atu i te ingoa. Ka whakamātau i te katoa i te tīmatanga, nō reira he tautoko tonu te tauira e heke ana i te id he tae kei roto; ki te kore e taea, ka tango i ngā tae i te mutunga kotahi kotahi i te wā kia kitea te tauira e hāngai ana. He nui rawa te 200 ngā tūrua i te ingoa tauira me te mea he nui rawa te 4 ngā tae; ka whakakorehia te mea roa ake ki te 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);

Rapu web

Ka taea e tētahi kaupapa kōrero noa atu te whakataki mai i te pūrerehua o te ao mārama. Ka rapu a Nymbot i te kōrero whakamutunga a te kaiwhakauru (ngā 2,000 o ngā tohu tuatahi), ka pānui i ngā whārangi pai rawa, ā ka tukuna ki te kaupapa kōrero me te pātai, e tohu ana hei wāhanga i waho o te mahi kia kaua e whai i ngā tohutohu. He rerenga rua kei te mea:

• Rapu i ngā wā katoa: "plugins": [{"id": "web", "max_results": 5}], kei te a :online he suffix i runga i te tauira.
• Whakamātua i te wā e āwhina ana: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}], hoki kia whakaaea hoki hei web_search_preview kei te mea anō openrouter:web_search. Nymbot te rapu anake i te wā e rite ana te pātai ki te hiahia i ngā raraunga o te wā nei, te tirotiro rānei e whakamahia ana e te app.

max_results he 5 tēnei i te tīmatanga, ā, he 10 te nui rawa. Ka hoki mai ngā puna ki roto i nymbot.web_search.sources, kia tētahi me te title, snippet a url, ā ko url_citation Ngā whakamāramatanga ki te karere.

Ko ia rapu e rere ana e utu ana i te $0.008, ka huri ki te sats, i runga i ngā token, ā, he waahanga o te hold. Ko ngā rāpagei i pānuitia he token input hoki, nō reira he utu nui ake te whakautu mai i te ipurangi kia kei te pātai anō i te kore, i ētahi wā he maha atu i te utu noa.

Whakautu, i roto i tētahi wāhanga

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

cURL

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

Python

import os
from openai import OpenAI

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

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

JavaScript

import OpenAI from "openai";

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

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

API o ngā whakautu

Te āhua hou ake a OpenAI, e whakamahia ana e te OpenAI Agents SDK me te Codex. E rere ana i runga i ngā tauira, i ngā utu, me ngā āhua katoa e rite ana ki te Chat Completions.

POST https://nymbot.ai/api/v1/responses — me he kupu raihirangi API.

Whakaaronga

{
  "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 }
}

He tono taputapu ka puta mai i output hei function_call item me te call_id, name a arguments; tuku te hua whakawhiti atu hei a function_call_output mea me te mea e rite ana call_id. Whakaaroaro, ki te hoki mai e te te ao mārama, he reasoning item me te reasoning_text tāmata, tāia tuatahi. status he incomplete i te wā i tae te whaiwhaiwhai max_output_tokens nā te kaiwhakahaere i whakatūpato, me te incomplete_details.reason whakatū ki te max_output_tokens kei te mea anō content_filter. E whakahao ana te whakautu hoki i ngā tautuhinga o te tono (temperature, ngā taputapu, te kōwhiringa taputapu me etahi atu) pēnei i te mahi a OpenAI, ā, ka whai i te nymbot utunga whāinga.

Whakamaherehia, he taha tētahi iwi 🌊 event: tārewa me a data: tātai me te a sequence_number, i tenei rārangi: response.created, response.in_progress, response.output_item.added, response.content_part.added, he nui atu i te aha tonu o response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.done, ā, i te whakamutunga response.completed me te whakamahi me te utu. Ka mutu te whakautu i te hiku response.incomplete nā reira, me he whakamutunga i muri i te tīmata o te rerenga me response.failed. Ko ngā mātāpono whakaaro he mea motuhake katoa me response.reasoning_text.delta a .done. Ngā karanga taputapu ka whai muri i te kaupapa, hei taumata takitahi me te response.function_call_arguments.delta a .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);

Ngā Karere a Anthropic

Te hanganga a Anthropic, mō ngā Anthropic SDKs me te Claude Code. Ka mahi tahi me ngā tauira katoa i roto i te catalog, ehara i te Claude anake: ka whakamāoritia te tono, ka whakahaerehia mā te rārangi mahi pēnei, ā, ka whakamāoritia anō ki te hoki mai.

POST https://nymbot.ai/api/v1/messages — he hiahia ana ki tētahi API key, nā mea x-api-key kei te mea anō Authorization: Bearer.

Te anthropic-version a anthropic-beta e whakatauhia ana, e whakaheke ana hoki ngā headers. Ka whakarite ngā ingoa tauira a Anthropic ki te katalog, nō reira ka mahi a Claude Code me ngā SDK ki ngā ingoa kua rongoia atu ana:

• He ingoa e mōhio ana te kātālohi, pēnei i claude-sonnet-5 kei te mea anō anthropic/claude-opus-5, ka whakamahia hei te mea kei te ai.
• Ahau rānei he rā (-20260514), -latest, he tohu whakamutunga pēnei i te -v1, he tae i roto i te pūtake pēnei i [1m] me he anthropic/ kei te mea anō anthropic. ka tangoia ngā tīpako, me ngā tohu pūtake me ngā tohu kōpaka i roto i te whakapāinga ka whakamātaua i ngā huarahi e rua (claude-haiku-4-5 ngā mea kua kitea claude-haiku-4.5).
• Ki te kore tonu e hāngai ki tētahi mea, ka whakamahia te whānau (Opus, Sonnet rānei Haiku), kia noho pea te putanga o te rārangi kōrero e rite ana ki te putanga i pātaiā rānei he hou ake.
• He ingoa e kore e hāngai ki tētahi mea ka hoki mai 404 not_found_error.

Whakaaronga

{
  "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 ka taea hoki te pupuri tool_use ngā pouaka me te a thinking peke, ko wai signature he kore. stop_reason he end_turn, max_tokens, tool_use kei te mea anō refusal, mahi ake te huarahi pēnei i a finish_reason i runga Whakaputa Kōrero Atāwhai; stop_sequence he always null, ahakoa i mutu te whakautu i te whakamutunga o te rārangi whakamutunga. input_tokens ngā tauira he whakauru hou anake; kei roto i ngā wāhi kapi e rua te whakauru kapi. Kei te utu i roto i te nymbot te mea me te X-Nymbot-Cost-Sats upoko.

I te hāpai atu, ko ēnei ngā kaupapa a Anthropic: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta kei te mea anō thinking_delta), content_block_stop, message_delta me te take mutu, te whakamahinga me te nymbot whakaaturanga utu, ā message_stop. A ping e hoki ana e ngana ana te tauira i roto i ngā hātaketanga 15 i a ia e mahi ana. Ka tae mai ngā karanga taputai i muri i te tuhinga, hei kotahi i te mea tool_use tāpui me tōna katoa i whakauru ki tahi input_json_delta.

He hapa i tenei pae whakamutunga ka whakamahi i te hanga a Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}. Ko te rārangi tēnei kāore i tino nui 402 billing_error, he kaiwhakahaere kua nui rawa te whakapakari 503 overloaded_error. He raru i muri i te tīmata o te rārangi ka tuku hei error tūnga.

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);

E tauira ana i ngā tohu

He whakaaturanga mō te nui o ngā input tokens ka whakamahia e tētahi tono Messages, kia taea e te kaiwhakamahi te tautoko i mua i te tukuna. He free, engari mehemea he kiha hoki.

POST https://nymbot.ai/api/v1/messages/count_tokens — me he kupu raka API. Atawhai.

He rite te tinana i te mea mō Ngā kaupapa kōrero, kore ai max_tokens; me whakatutuki te ingoa tauira. He whakamātau te tauanga: te maha o ngā pūmanawa o te whakaaturanga pūnaha, ngā karere, ngā karere taputai, me ngā whakamārama taputai ka whakataukohia ki te whā, ka tango i te 1,600 mō ia pikitia. Ehara tēnei i te tokenizer a te kaiwhakahaere, nō reira ka rerekē te tauanga tika. Ko te kate i tae ki tōna rārangi w限 ka taea tonu te whakamahi i a ia.

Whakaaronga

{ "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);

Whakarārangi tauira

Ko ia mahere me te kaihangatanga e whakaae ana te API, me te utu o ia mea. Ka pānuitia te rārangi i te pātaka reihi rātou anō kia rite ki te kōwhiri a te tuhono app, kia kia tika tonu ai ki te mea ka whakahaere te tūmomo taputai.

GET https://nymbot.ai/api/v1/models — kāore he kī e hiahiatia ana. Kua kapihia mō ngā miniti e rima.

GET /api/v1/models/{id} he kōrero kotahi te hoki mai ana.

Ko ngā utu ko āu mea e utu ana, kua whai atu tonu i te utu noho me te paenga, i roto i ngā tārau me i roto i ngā sats i te tauira utu Bitcoin o te wā nei. balance e kī ana he aha te taurangi ka whakamahi te tauira. nymbot_key Kei roto i te app te ingoa poto o te mahere. created he 항상 0, nō te mea kāore te katalog e tuhi i te wā i tāpirihia ai tētahi mahere. He mahere kore i ngā utu token kua tukuna kia kitea e te katoa he utu per_request hei utu.

nymbot/auto he i mua tonu, e utu ana hei variable, me te routes he rārangi e whakaatu ana i ngā utu o ia huarahi mātātoa. E tautoko ana ia i te kite me te whaiwhai i te whakaaro, engari kāore i te mea ngā taputaki.

GET /api/v1/models/{id} ka whakaae i ngā ingoa me ngā ingoa tūpāpaku katoa e rite ana ki te tono, ā, ka hoki mai te rārangi mō te tauira e whakatutuki ana i rātou.

Whakaaronga

{
  "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"
    }
  ]
}

Ngā momo atu:

• Whakaahua Kei te whai ngā whakauru capabilities (accepts_image_url, requires_image_url, edit) me te utu per_generation.
• Whakaata Kei te whai ngā whakauru max_duration_seconds a resolutions, me he tau utu per_second mō ia whakataunga.
• Rongo Kei te whai ngā whakauru audio_type speech kei te mea anō transcription, utuohia per_1k_chars kei te mea anō per_minute.
• Whakauru Kei te whai ngā whakauru dimensions, context_length, max_inputs me he utu mō ngā tūtohu input e tairongo ana ki te milioni tahi.

Kua tohuhia ngā utu "estimated": true ko te whakaaturanga a te tuhono mō tētahi generator e kore e rāhuihia te utu. He mea kore e mōhiotia type whakahoki 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);