Batayan ti pannakaammo / Developer iti

Napateg dagiti mensahe.

Agipatpatarus kadagiti 3 a paraan a maaddaan iti modelo iti dadduma, iti 3 a format a nagtalinaedan dagiti kliente, ti adu a nairuar iti sama a model ken nairuar iti sama a way.

Daytoy a panid ket naipatarus babaen ti makina para iti kombeniente. Ti Ingles nga orihinal ti bersion nga agaplikar.

Napateg ti completion

Ti OpenAI chat format, ken ti nagpateg a tool ti nagpateg. Ipadala ti konversasion agingga iti dayta ket saan ti next message back.

POST https://nymbot.ai/api/v1/chat/completions Naaddaankami iti API Key.

ti model ken messages Ti maysa a sampling a parameter a ti napateg a model ket saan a nailawlawag ket saan a nailawlawag, tapno maaddaan iti maysa a request body iti adu a model. supported_parametersTi naudi ket ti naudi ket ti naudi ket ti naudi ket ti naudi ket ti naudi ti naudi ket ti naudi ket ti naudi ket ti naudi.

Addaan iti ordinary chat.completionAddaan iti cost in usage.cost (Dollars) ken dagiti dadduma. nymbot Objektona iti model Daytoy ket addaan iti kaaduan kadagitoy no kalgaw.Ket ti kaaduan kadagitoy no kalgaw ket ti kaaduan kadagitoy no kalgaw. message.reasoning_contentNaaddaankami iti reaksion.

Reaksiona

{
  "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 Kas pagarigan, saan a ti sumagmamano a saan a datayo, saan a saan a datayo a datayo: tool_calls Ngem idi inaramid ti instrumento, length Isu ket pimmusay idiay asideg ti Edinburgh, ken kadua met idi ti pamiliana. content_filter Ngem ibabaonnatayo ni Apo Dios a birukentayo isuna. stop Addaan iti usage.completion_tokens_details.reasoning_tokens 0: Napatpateg a token ti panangmatmat iti argumento ket naidumduma, ken naidumduma iti completion_tokens.

Ti status code ti tunggal endpoint a aksion ket listado iti Addaan iti.

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 iti

ti "stream": true Daytoy ket addaan iti maysa nga addaan iti maysa nga addaan iti maysa nga addaan iti dua a daga.[1] chat.completion.chunk ti a data: Naaddaankami iti ruar, saan a nagturong iti data: [DONE]Naaddaankami iti reasoning. delta.reasoning_contentIsu ti reaksion iti delta.content.

Agipatpatarus kadagiti adu a tattao nga agpatingga iti nasurok a 100 a segundo, kas iti maysa a lang a reaksion, iti maysa a max_tokens Daytoy ket addaan iti kaaduan kadagitoy no kalgaw ti kaaduan kadagitoy no kalgaw.Idi linuktan ti kaaduan kadagitoy no kalgaw.Idi linuktan ti kaaduan kadagitoy no kalgaw.

Umadaw

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]

• Naaddaankami iti : Kas 15 a sekreto, agipatpatarus ti panagturay iti panagturay.
• Adu ti "stream_options": {"include_usage": true} Napalalo ti ulidan iti ulidan, iti nakalugan a choicesAdda pay laeng ti sumagmamano a makisarita. nymbot Objektona iti
• Ti pagbalinan ket naidumduma idi agtawen iti 25 a segundo, tapno maaddaanna ti token count ti provider, ken ti makabayad ti sumagmamano nga inlawlawag ti provider.
• Isu ket pimmusay idiay asideg ti Edinburgh. 401 ti 402Napateg a JSON, saan a naaddaan iti normal a JSON ken ti status code, ket saan a naaddaan iti stream. data: {"error": {…}} Ngem saan a nagpatingga ti stream ket saan a [DONE].
• Daytoy ket addaan iti kaaduan kadagitoy no kalgaw ti kaaduan kadagitoy no kalgaw.

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);
}

Inlawlawag ti

Agipatpatarus kadagiti funksiona tools Ngem saan a naaddaan ti sumagmamano a maaw-awagan ti funksion, saan a maaw-awagan. tool Kitaen dagiti ladawan. tool_call_idTi Nymbot ket saan a nairekord iti funksion ti model.

tool_choice Napateg "auto", "none", "required" ti {"type": "function", "function": {"name": "…"}}Nalawag ti kuna ti Biblia: “Asinoman a mangay-ayat iti kinaranggas pudno unay a guraen [ni Jehova].”capabilities.toolsTi instrumento ket naaddaan iti 400 unsupported_tool ti nymbot/auto Daytoy ket addaan iti maysa nga addaan iti maysa nga addaan iti maysa nga addaan iti dua a sebbangan.

ti "stream": true, maysa a request iti tool ket nairuar iti maysa a bit ket nairuar iti normal a chunk sequency: ti role, maysa a chunk a mangrugi ti tunggal tool call iti indeks, id, nagan ken argumento, ken ti finish chunk.

Addaan iti reaksion

"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);

Kitaen dagiti ladawan.

Modelo iti capabilities.vision Ngem saan a naaddaan iti foto. Add a image_url Napateg ti user a mensahe, iti publiko. https:// link iti a data:image/…;base64, Ti maysa a pagarigan ket ni Eliezer a nakaitalkan ti adu a sanikua ni David. (400 invalid_image_urlAddaan iti opsion. detail ti auto, low ti high.

ti nymbot/auto, ti request iti maysa a picture iti maysa a standard model a makita. capabilities.vision Imbagana iti pictures with 400 unsupported_contentTi link ket addaan iti maysa a publiko a host; ti Nymbot imbagana ti imbagana iti provider ti model ket saan a maipaay iti dayta.

Ti imbagana ket nairuar iti input token ti provider, kas iti rest ti request.

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);

Argumento ti

Modelo iti capabilities.reasoning Ngem saan a maipakitatayo ti inaramidko, saanko a maipakitatayo ti inaramidko? reasoning_effort ("minimal", "low", "medium" ti "high"ti "reasoning": {"effort": "high"}Agbiruk iti add :thinking Isu ket pimmusay idiay Malakanyang idiay Malakanyang idiay Malakanyang idiay Malakanyang. nymbot/auto, :thinking Naaddaankami iti standard reasoning route.

Iti Anthropic models, ti pagbalinan ket naaddaan iti agarup 1,000, 2,000, 8,000 wenno 16,000 a token, saan a maipaay iti nasurok a 1,000 a token. max_tokens Imbagana. – Imbagana ti imbagana iti tool_choice Napateg a tool, ken kada ti requests ti panagturay iti tool loop (ti naudi a mensahe ket maysa a tool result), gapu ta ti Anthropic nangisubli ti naimbag a panagtalek a mangisubli iti dayta a panagturay.

Napateg ti argumento iti message.reasoning_contentti delta.reasoning_content Isu ket pimmusay idiay asideg ti Edinburgh, ken kadua met idi ti pamiliana. completion_tokensTi dadduma a provider ket imbagana ti argumento a teksto, ket saan pay pay laeng.

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);

Impanna iti suffix

Ti sumagmamano iti nagan ti modelo ti panagtrabaho iti panagtrabaho iti solicitation, saan a saan a campo. anthropic/claude-sonnet-5:online.

Ti intero a nagan ket nailugan iti umuna, tapno maaddaan ti modelo a ti ID a nagkauna a nagkauna a nagkauna; no saan a, ti sufixium ket naidumduma iti umuna a panawen agingga a maaddaan iti maysa a modelo. 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 iti Search

Ti Nymbot searches para iti maudi a user nga mensahe (ti umuna a 2,000 a karakter), makisarita ti best nga panid ket mangted kadagiti model iti question, a maragsakan iti external content a model ket saan a maaddaan kadagiti instruksion iti.

• Naaddaankami iti: "plugins": [{"id": "web", "max_results": 5}]ti a :online Naaddaankami iti model.
• Napukawanna iti tulong: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}]Kitaen dagiti ladawan. web_search_preview ti openrouter:web_searchNymbot searches laeng idi ti isu ti nangisubli iti aktuara nga impormasion, ti maysa a test a nausar ti app.

max_results 5 Kasano a nagkauna a nagkauna a nagkauna iti daga? nymbot.web_search.sourcesAddaan iti a title, snippet ken urlti AS url_citation Kitaen dagiti ladawan.

Ti maysa a search a maaddaan iti $0.008, a konverted iti sats, iti top ti token, ket maysa a paset ti hold. The pages it reads are input tokens too, sa a reply from the web costs more than the same question asked cold, sometimes several times more.

Addaan iti reaksion

"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);

Agbiruk iti API.

Ti nauuna a format ti OpenAI, a nausar iti OpenAI Agents SDK ken iti Codex. Nairuar iti sama a model, billing, ken features ti Chat Completions.

POST https://nymbot.ai/api/v1/responses Naaddaankami iti API Key.

Reaksiona

{
  "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 }
}

Napateg ti instrumento a naaddaan iti output ti a function_call Kitaen dagiti call_id, name ken argumentsKitaen dagiti ladawan. a. function_call_output Kitaen dagiti ladawan. call_idKas pagarigan, idi inaramid ti modelo, adda iti reasoning Kitaen dagiti reasoning_text Napategda iti listahan ti umuna. status ti incomplete Ngem idi ti reaksionna max_output_tokens Ngem ibabaonnatayo ni Apo Dios a birukentayo isuna. incomplete_details.reason Addaan iti max_output_tokens ti content_filterTi reaksion ket naaddaan kadagiti setting ti request (temperatura, tool, tool choice, etc.) kas ti OpenAI, ken mangrugi ti nymbot Nagpintas ti objekto.

Nagpintas, ad-adu pay laeng ti evento event: ti line a data: Addaan iti a sequence_numberKitaen dagiti ladawan. response.created, response.in_progress, response.output_item.added, response.content_part.addedAddaan iti numero response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.doneNapateg ti response.completed Adda pay laeng ti sumagmamano a sumagmamano a mangngeg iti korte end. response.incomplete Ngem saan a nagpateg a nagpateg ti stream. response.failedNgem saan a nagpateg a kas iti tema ti response.reasoning_text.delta ken .doneDaytoy ket addaan iti kaaduan kadagitoy no kalgaw. response.function_call_arguments.delta ken .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);

Naaddaankami iti mensahe.

Ti format ti Anthropic, para kadagiti Anthropic SDKs ken Claude Code. Naaddaan iti tunggal model iti katalog, saan a naaddaan ti Claude: ti solicitation ti nailawlawag, ti nairuar iti maysa a pipeline, ken ti nailawlawag.

POST https://nymbot.ai/api/v1/messages Naaddaankami iti API key. x-api-key ti Authorization: Bearer.

ti anthropic-version ken anthropic-beta Ti antropoid a nagan ti modelo ket maaddaan iti katalogo, tapno maaddaan ni Claude Code ken dagiti SDK kadagiti nagan a maawagan:

• Napateg dagiti katalogo, kas claude-sonnet-5 ti anthropic/claude-opus-5Naaddaankami iti dayta a tao.
• (Tumaudto dagiti dadduma.-20260514), -latestKitaen dagiti ladawan. -v1Isu ket pimmusay idiay asideg ti Edinburgh. [1m] ti an anthropic/ ti anthropic. Daytoy ket addaan iti kaaduan kadagitoy no kalgaw. (claude-haiku-4-5 Nalpasakon claude-haiku-4.5).
• No saan a maadaltayo, maadaltayo ti familia (Opus, Sonnet, Haiku) no saan a maadaltayo ti bersion ti catalogo.
• Daytoy ket addaan iken ti dadduma. 404 not_found_error.

Reaksiona

{
  "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 Pimmanaw ti tool_use Blokko iti a thinking Blokko ti signature Naaddaankami iti vacuum. stop_reason ti end_turn, max_tokens, tool_use ti refusalNapukawanna iti sama a finish_reason ti Napateg ti completion; stop_sequence ti always null, uray no ti stop a sequency ti panagturay ti reaksion. input_tokens Ipapaupana ketdi ti kaaduan kadagitoy no kalgaw. nymbot Objektona iti X-Nymbot-Cost-Sats Addaan iti header.

Daytoy ket addaan iti Anthropic’s: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta ti thinking_delta), content_block_stop, message_delta Isu ket pimmusay idiay asideg ti Edinburgh, ken kadua met idi ti pamiliana. nymbot Adda pay laeng objekto, ken message_stopa ti ping Naaddaankami iti 15 a sekundada a nagbaetan ti instrumento a nairekord iti teksto. tool_use Napateg a blok iti intero a input iti maysa input_json_delta.

Error iti daytoy a terminal nausar ti format ti Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}Addaan iti short balance. 402 billing_errorAddaan iti Supplier. 503 overloaded_errorNgem saan a nagpateg ti inaramidna, inaramidna ti inaramidna. error Nagturong iti event.

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);

Agbiruk iti token.

Ti panangmatmat ti innem a token a mangusar iti mensahe a request, tapno maaw-awagan ti client tapno maaw-awagan ti mensahe. It’s free but still needs a key.

POST https://nymbot.ai/api/v1/messages/count_tokens Naaddaankami iti API Key.

Kas pagarigan, adda makaay-ayo iti Kitaen dagiti ladawan.Isu ket max_tokensDaytoy ket addaan iti kaaduan kadagitoy no kalgaw ti kaaduan kadagitoy no kalgaw.Idi linuktan ti kaaduan kadagitoy no kalgaw.Idi linuktan ti kaaduan kadagitoy no kalgaw.

Reaksiona

{ "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);

Modelo ti

Kas iti model ken generator ti API, saantayo a makisarita. Ti lista ket naaddaan iti sama a live catalog ken ti app nga picker, tapno maaddaan iti server.

GET https://nymbot.ai/api/v1/models No isu ti inaramidna, lima a minuto ti inaramidna.

GET /api/v1/models/{id} Agbiruk iti 1 entry.

Ti presyo ket ti pagbayad, babaen ti fee ken margin nga adda, iti dollar, ken iti sats iti current Bitcoin price. balance Addaan iti balanse ti gasto ti modelo. nymbot_key Daytoy ket addaan iti short name iti app. created Dayta ti 0. idi ti katalog ket saan a na-record kada ti model ket naiduma. per_request saan ketdi a.

nymbot/auto Ngem saan a nagpateg a nagpateg a kas variableti a routes Napateg a ruar ti ruar ti ruar ti tunggal standard. Napateg a ruar ti vision ken argumento, ngem awan ti instrumento.

GET /api/v1/models/{id} Napateg dagiti dadduma a nagan ken alias a nangikabil iti peticion, ken imbagana ti impormasion para iti modelo a nangikabilda.

Reaksiona

{
  "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"
    }
  ]
}

Ti dadduma a tipo:

• Imbagana Addaan iti capabilities (accepts_image_url, requires_image_url, editAddaan iti price per_generation.
• Video ti Addaan iti max_duration_seconds ken resolutionsAddaan iti price per_second Para iti resolution.
• Audio iti Addaan iti audio_type speech ti transcriptionNagpateg a per_1k_chars ti per_minute.
• Agbiruk Addaan iti dimensions, context_length, max_inputs Adda pay laeng iti milion a input token.

Impanna iti markup "estimated": true Daytoy ket addaan iti maysa a generator, a ti maysa a generator ket addaan iti maysa a generator. type Pimmanaw 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);