Basis kawruh / Pembangunan

Chat, respon lan pesan

Tiga cara kanggo nggoleki model apa-apa, ing tiga format klien wis ngobrol, kabeh mbukak ing model padha lan dihitung ing cara padha.

Kaca iki diterjemahake mesin kanggo penak. Asli Inggris minangka versi sing ditrapake.

Katrangan lengkap

Ing format chatting OpenAI, lan sing sawetara alat ndhukung. Ngirim ngobrol iki lan njaluk pesan liyane.

POST https://nymbot.ai/api/v1/chat/completions Kita kudu nggunakake kunci api.

Sadurunge model lan messages Parameter sampling sing model sing dipilih ora njaluk ditinggalake tanpa kesalahan, supaya siji telinga perminta kerja antarane model. supported_parametersApa sing ditolak lan ora ditinggalake iku apa model ora bisa nindakake: gambar kanggo model sing ora bisa nindakake, alat kanggo model sing ora bisa nindakake.

Jawaban iku biasa. chat.completionKanthi biaya ing usage.cost (Ing dolar) lan ing nymbot Objek iku. model Model iku id model sing diselesaikan, supaya nama sing sing sing sing sing sing sing sing lengkap. message.reasoning_contentSeparasi saka jawaban.

Jawaban

{
  "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 iki dikelompokake saka apa sing balik, amarga penyedia melaporkan sing beda: tool_calls Nalika model ngarepake alat, length nalika jawaban nggunakake saben token diperkenanake (utawa model nggunakake kabeh argumen lan ngandika ora jawaban), content_filter Dheweke bakal nindakake rejeki, lan stop Uga iku. usage.completion_tokens_details.reasoning_tokens iku selalu 0: token argumen tersembunyi dihitung, lan dibayarkan, ing completion_tokens.

Kode status saben saham endpoint sing disenaraake ing Gampangipun.

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);

Ngluwihi

Dheweke "stream": true Jawaban iki diwenehi minangka acara sing dikirim dening server nalika model nyimpen. chat.completion.chunk lan a data: garis, lan aliran ngakhiri karo data: [DONE]Argumentasi iku ing delta.reasoning_contentJawaban ing delta.content.

Stream apa-apa sing bisa luwih saka kira-kira 100 detik, kayata jawaban panjang, max_tokens utawa model argumen. Panggonan sing ora ditransmisikake ora ngirim apa-apa nganti jawaban wis lengkap, lan jaringan antarane sampeyan lan Nymbot bisa ngluwihi koneksi kosong setelah kira-kira 100 detik; model uga diakhiri lan apa sing ditulis ditransmisikake, nanging jawaban wis hilang.

Tembung

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]

• Lines dimulai karo : Komentar-komentar terus-terusan, dikirimake saben 15 detik nalika model sedang berpikir.
• Panggonan kanggo "stream_options": {"include_usage": true} kanggo njaluk chunk pungkasan ing ndhuwur, karo kosong choicesIng ngisor iki, biaya lan nymbot Objek iku.
• Nymbot njaluk sisih provider, kanggo nganti 25 detik, kanggo njaluk hitungan token, lan sampeyan mbayar apa provider melaporkan. Tanpa iki hitungan biaya dianggarake saka input lan apa sing ditulis, ditambah kabutuhan output kabeh kanggo model sing alasan.
• Sampeyan ora bisa nggunakake salah saka pirang-pirang, kaya 401 lan 402, mbukak minangka JSON biasa karo kode status, ora minangka stream. data: {"error": {…}} acara, lan aliran diwenehi tanpa [DONE].
• Panggonan karo alat, lan model ing OpenAI's Responses transport, ora stream saka provider.

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);
}

Alat kanggo panggilan

Tindakake fungsi ing tools lan model bisa njaluk siji kanggo diwenehi saka nganggur. Sampeyan mbukak fungsi, njaluk hasil minangka tool Panggonan sing padha tool_call_idNymbot ora mbukak fungsi sampeyan; iku ngirim permintaan model menyang sampeyan.

tool_choice nggawé "auto", "none", "required" lan {"type": "function", "function": {"name": "…"}}Panjenenganipun ora bisa nggunakake model (capabilities.tools) Alat iki ditolak karo 400 unsupported_tool Dheweke nymbot/auto lan ing sawetara model katalog sing mbukak ing transport Responses OpenAI, kang Nymbot ora bisa ngirim alat kanggo.

Dheweke "stream": true, permintaan karo tool berjalan ing siji bagian lan banjur dikirim minangka urutan chunk normal: peran, siji chunk nglakoni saben call tool karo indeks, id, jeneng lan argumen, lan chunk finish.

Jawaban, ing sawetara

"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);

Foto ing permintaan

Model karo capabilities.vision Bisa nggunakake gambar. tambahkan image_url part kanggo pesan pangguna, karo siji publik https:// Link lan a data:image/…;base64, URL. Hingga 20 gambar per permintaan. gambar SVG diwenehi, lan iku link luwih saka 4096 karakter utawa siji karo nama pangguna utawa password ing iku (400 invalid_image_urlIng opsi detail Dheweke auto, low lan high.

Dheweke nymbot/auto, permintaan karo gambar ing iku diaruter menyang model standar sing bisa nonton. capabilities.vision Ngluwihi gambar karo 400 unsupported_contentGambar bisa mung ing pesan pangguna. Link kudu ngandhingake kanggo host umum; Nymbot ngirim gambar kanggo provider model lan ora nyimpen.

A gambar dibayarkan minangka token input provider nghitung kanggo iku, kaya sisih permintaan.

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);

Argumentasi

Model karo capabilities.reasoning Bisa nggawé nggawé nggawé nggawé nggawé nggawé nggawé nggawé nggawé nggawé reasoning_effort ("minimal", "low", "medium" lan "high") utawa "reasoning": {"effort": "high"}Dheweke bakal nambah :thinking ing jeneng model, sing nyebabake upaya dhuwur. Ing model tanpa alasan setelan diabaikan. nymbot/auto, :thinking ngirim permintaan menyang rute argumentasi standar.

Ing model Anthropic upaya dadi anggaran berpikir saka kira-kira 1,000, 2,000, 8,000 utawa 16,000 token, ora luwih saka max_tokens Piyambakipun. ing ngendi iku ngendi. tool_choice Nggunakake tool, lan nalika permintaan terus tool loop (message pungkasan iku hasil tool), amarga Anthropic kudu pemikiran sing ditandatangani sadurunge kanggo ngulangake.

Argumen iku balik ing message.reasoning_contentDheweke delta.reasoning_content Nalika streaming, ora digabungake ing jawaban. Reasoning iku output lan dibayar minangka kaya, ing completion_tokensSawetara penyedia ora ngundhuh teks argumen, lan iku uga dibayarkan.

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);

Model saka suffixes

Sufi ing jeneng model ngganti cara permintaan diproses, tanpa bidang liyane. Mereka nggunakake id lengkap lan jeneng sing pendek, minangka ing anthropic/claude-sonnet-5:online.

Apa-apa suffix liyane diwenehi. Nama kabeh diusahake sadurunge, supaya model kang id nyata ngandhut kolon masih kerja; tanpa iki, suffixes diwenehi saka ujung siji ing wektu nganti model cocok. Nama model bisa ing maksimum 200 karakter panjang karo ing paling 4 suffixes; siji liyane ditolak karo 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);

Web lan search

Nymbot njaluk pesan user pungkasan (sebut 2000 karakter utamane), njaluk halaman paling apik lan ngirimake menyang model karo pertanyaan, ditandani minangka konten luar model ora kudu njaluk instruksi saka.

• Tiyang iku: "plugins": [{"id": "web", "max_results": 5}]Nanging a :online Sampeyan cukup ing model.
• Panggonan nalika iku membantu: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}]Dheweke uga diwenehi minangka web_search_preview lan openrouter:web_searchNymbot njaluk mung nalika pitakonan tampaknya njaluk informasi saiki, test sing padha nggunakake aplikasi.

max_results iku 5 ing default lan ing maksimum 10. sumber mbukak ing nymbot.web_search.sourcesDhèwèké kanthi a title, snippet lan urlDheweke lan as url_citation Anotasi ing pesan.

saben pencarian sing mbukak biaya $ 0.008, diwenehi kanggo sats, ing ndhuwur token, lan iku bagian saka mbukak. kaca sing dibaca minangka token input uga, supaya jawaban saka web biaya luwih saka pertanyaan sing padha pitakonan dingin, kadang-kadang sawetara kali luwih.

Jawaban, ing sawetara

"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);

Jawaban saka api

OpenAI format anyar, digunakake dening OpenAI Agents SDK lan dening Codex. Dheweke mbukak model, tagihan lan fitur padha karo Chat Completions.

POST https://nymbot.ai/api/v1/responses Kita kudu nggunakake kunci api.

Jawaban

{
  "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 }
}

A tool request muncul ing output lan a function_call Punika ing call_id, name lan arguments; ngirimake hasil minangka a function_call_output Tiyang ingkang sama call_idArgumen, nalika model ngirimake iku, iku a reasoning Punika ing reasoning_text Ing ngisor iki, daftar ing pisanan. status Dheweke incomplete Dheweke bakal nindakake respon max_output_tokens Dheweke bakal nindakake adoh-adoh. incomplete_details.reason Tiyang max_output_tokens lan content_filterJawaban uga mbukak setelan permintaan (temperatur, alat, pilihan alat lan liyane) minangka OpenAI nggunakake, lan mbukak nymbot Uga nggawé obyek.

Tiyang-tayang, saben acara iku event: Line lan a data: Line karo a sequence_numberIng urutan iki: response.created, response.in_progress, response.output_item.added, response.content_part.addedApa-apa ing nomer response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.doneLan ing pungkasan response.completed Ing ngisor iki, jawaban sing disusun karo response.incomplete ing ndhuwur, lan kegagalan nalika aliran dimulai karo response.failedRasioning aliran minangka item dhewe karo response.reasoning_text.delta lan .donePanggonan alat iki teka sawise pesan, saben minangka item karo response.function_call_arguments.delta lan .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);

Panggonan antropik

Format Anthropic, kanggo SDK Anthropic lan Claude Code. Bekerake karo kabeh model ing katalog, ora mung Claude: permintaan diterjemahake, mbukak liwat pipeline sing padha, lan diterjemahake.

POST https://nymbot.ai/api/v1/messages — perlu kunci API, minangka x-api-key lan Authorization: Bearer.

lan anthropic-version lan anthropic-beta Nama model anthropic digabungake karo katalog, supaya Claude Code lan SDK-s bekerja karo jeneng sing wis digunakake:

• Katrangan sing ngerti, kayata claude-sonnet-5 lan anthropic/claude-opus-5Dheweke digunakake minangka iku.
• Ing ngisor iki (-20260514), -latestVersi iki minangka -v1Tiyang-Tiyang lan Tiyang-Tiyang minangka [1m] Dheweke ana anthropic/ lan anthropic. Ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki (claude-haiku-4-5 Tembung claude-haiku-4.5).
• Yen iku uga ora cocog, keluarga (Opus, Sonnet utawa Haiku) digunakake, nalika versi katalog iku padha utawa luwih anyar saka versi sing diminta.
• Nama sing cocog apa-apa mbukak 404 not_found_error.

Jawaban

{
  "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 Dheweke uga bisa nyimpen tool_use Blok lan a thinking Blok ing ngendi signature Lan iku kosong. stop_reason Dheweke end_turn, max_tokens, tool_use lan refusalDheweke nggunakake cara padha minangka finish_reason Dheweke Katrangan lengkap; stop_sequence Iku iku null, malah nalika urutan stop ngakhiri jawaban. input_tokens Ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki, ing ngisor iki. nymbot Objek lan X-Nymbot-Cost-Sats lan header.

Ing ngisor iki, acara iki antropik: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta lan thinking_delta), content_block_stop, message_delta Sampeyan ora bisa ngetokake alasan, penggunaan, lan nymbot Biaya obyek, lan message_stopA iku ping iki uga ngirimake saben 15 detik nalika model wis kerja. panggilan alat kedhaftar teks, saben minangka tool_use blok karo kabeh input ing siji input_json_delta.

Errors ing endpoint iki nggunakake format Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}Keseimbangan sing pendek iku 402 billing_errorPiyambakipun nyebataken. 503 overloaded_errorA gagal nalika stream wis dimulai dikirim minangka error Event iku.

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);

Menghitung token

Estimasi saka sawetara token input permintaan Messages bakal nggunakake, supaya klien bisa ngetokake sadurunge ngirim.

POST https://nymbot.ai/api/v1/messages/count_tokens — butuh kunci API. gratis.

Tubuh iku padha karo PanggonanDheweke ora max_tokens; jeneng model kudu nguripake. hitungan iku estimasi: watesan panggilan sistem, pesan, panggilan tool lan definisi tool dibagi dening empat, ditambah 1,600 kanggo saben gambar. Iki ora tokenizer dhewe provider, supaya hitungan nyata bisa beda.

Jawaban

{ "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);

Model lan model

Kabeh model lan generator API njaluk, karo apa biaya. daftar dibaca saka katalog langsung padha karo picker aplikasi, supaya iku uga apa server bakal mbukak.

GET https://nymbot.ai/api/v1/models — ora dibutuhake kunci. disimpen kanggo lima menit.

GET /api/v1/models/{id} Ngirim ing 1 entri.

Harga iku apa sampeyan mbayar, karo biaya lan margin wis ing, ing dolar lan ing sats ing harga Bitcoin saiki. balance Ngandika apa balanse model nggunakake. nymbot_key iku jeneng pendek model ing app. created iku uga 0 amarga katalog ora ngrekam nalika model ditambahake. per_request tinimbang.

nymbot/auto Ing ngisor iki, harga minangka variableDheweke karo a routes Daftar sing ngandhani tarif saka saben rute standar. Ngandhingake visi lan argumen, nanging ora alat.

GET /api/v1/models/{id} nampa jeneng lan alias padha minangka permintaan, lan ngirim entri kanggo model sing padha ngatur kanggo.

Jawaban

{
  "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"
    }
  ]
}

Ing tipe liyane:

• gambar Ing ing ing capabilities (accepts_image_url, requires_image_url, edit) lan harga per_generation.
• Video lan Ing ing ing max_duration_seconds lan resolutionsDheweke duwe harga per_second Kanggo saben resolusi.
• Audio iku Ing ing ing audio_type speech lan transcriptionIng harga per_1k_chars lan per_minute.
• Ngluwi Ing ing ing dimensions, context_length, max_inputs lan harga per yuta input token.

Harga ditandatangani "estimated": true iku estimasi aplikasi kanggo generator sing harga ora diterbitake. type Kembali 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);