Tushen ilimi / Wasanni

Chat, Yanzu da Messages

Three ways to ask a model something, a cikin uku format da abokan ciniki ya ce, duk da ke aiki a kan samfurori da aka sayar da sama.

An fassara wannan shafin na inji don dacewa. Asalin Ingilishi shine sigar da ke aiki.

Tsarin Chat

The OpenAI chat format, kuma daya da fiye da kowane kayan aiki goyon bayan shi. Send the conversation so far da kuma samun gaba da sabuntawa.

POST https://nymbot.ai/api/v1/chat/completions - Yana bukatar wani API key.

hanya model kuma messages A sampling parameters da aka zabi model ba za a rage ba tare da wani gabatarwa, don haka daya request body aiki tsakanin models. The model list ya ba da kowane model supported_parametersYawan da aka ba da yaushe fiye da yaushe ne abin da model ba za a iya yi: hotuna ga wani model wanda ba za a iya ganin, kayan aiki ga wani model wanda ba za a iya kira su.

Yanzu ne mai ban mamaki chat.completion, tare da farashin a usage.cost (a cikin dollar) da kuma a cikin nymbot Ƙididdiga model The model is the resolved model id, don haka wani short name ya zo a matsayin full one. Idan model ya rage kafin ce, ya rage a cikin message.reasoning_contentƘara daga Ƙararrawa

Yanzu

{
  "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 da aka gyara daga abin da aka gabatar da, kamar yadda masana'antu sanar da shi daban-daban: tool_calls lokacin da model ya ba da kayan aiki, length a lokacin da matsaloli ya amfani da kowane token karkashin (ko model ya kullum su ra'ayi da kuma ba ya rubuta wani matsaloli), content_filter a lokacin da abokan ciniki ya ba da, da stop ko da. usage.completion_tokens_details.reasoning_tokens is always 0: hidden reasoning tokens suna sayarwa, kuma karfe, a cikin completion_tokens.

status codes kowane endpoint shigo suna listed a karkashin Tuntube mu.

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);

Wasanni

Ƙaddamar "stream": true Yanzu ya zo a matsayin matsaloli na server yayin da model ya rubuta shi. Kowane matsaloli ne wani matsaloli chat.completion.chunk a data: line, da tsari ya fara tare da data: [DONE]Ƙararrawa ya zo a cikin delta.reasoning_contentYanzu a cikin delta.content.

Stream wani abu da za a iya dace fiye da kusa da 100 seconds, kamar yadda wani tsawon bayani, wani babban max_tokens ko wani ra'ayoyi model. A tambayoyi da ba ya sauke ba zai ba su sauke abin da ya fi dace, kuma cibiyar tsakanin ka da Nymbot za a iya shigar wani haƙĩƙa hadin gwiwa bayan game da 100 seconds; da model yana da yaushe da kuma abin da ya rubuta ne da aka sauke, amma shawarar da aka sauke. A stream ya sauke keep-alives, don haka yana da aka haifar da lokacin da model ya sauke.

Ƙananan

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 fara da : SSE na'ura mai aiki da karfin ruwa mai aiki da karfin ruwa mai aiki da karfin ruwa mai aiki da karfin ruwa mai aiki da karfin ruwa mai aiki da karfin ruwa
• Yadda za "stream_options": {"include_usage": true} to get the last chunk above, tare da wani m choices, da token sayar, da farashin da kuma nymbot Ƙididdiga
• Yadda ka shigar sadarwa a karshe, model ba zauna: Nymbot ya karanta rest na samarwa ta hanyar, zuwa 25 seconds, don samun daukewa na token, kuma za ka bayar da abin da samarwa ya gabatar da. Babu da wannan sayarwa, daukewa da aka sayarwa daga sa'o'i da abin da aka rubuta, har da cikakken sa'o'i don samfurin da haka.
• Yanzu kafin farko, kamar yadda 401 ko 402, ya fara a matsayin m JSON tare da status code, ba tare da alama. A gabatarwa bayan alama ya fara ya zo a matsayin karshe data: {"error": {…}} Event, kuma stream ya fara ba [DONE].
• Ma'aikata tare da kayan aiki, da kuma samfurori a kan OpenAI's Responses kayan aiki, ba zauna daga samarwa. Duk da haka, su zo tare da wani daidaitacce, saita a lokacin da yanayin da aka kammala.

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);
}

Takardar kebantawa

Shafin shafi: Functions in tools kuma model za a iya ba da wani za a ba da kira a gudu. Za ka yi aiki, sa da matsaloli a matsayin tool Tuntubewa tare da wannan tool_call_idNymbot ba zai yi aiki tare da ayyukanku; shi zai gabatar da baƙi na model zuwa ku.

tool_choice Ƙara "auto", "none", "required" ko {"type": "function", "function": {"name": "…"}}Model list maras cewa models za a iya kira kayan aiki (capabilities.tools) Instruments suna ba tare da 400 unsupported_tool ya nymbot/auto kuma a kan wasu catalog models da ke aiki a kan OpenAI's Responses transport, wanda Nymbot ba zai iya ba da kayan aiki ga.

Ƙaddamar "stream": true, wani baƙin tare da kayan aiki yana aiki a cikin wani kudi da kuma an saita kamar yadda a normal chunk sequence: da ruwan, wani chunk tare da kowane kayan aiki baƙi tare da index, id, sunan da arguments, da kuma finish chunk. Clients wanda ya karanta Streamed kayan aiki baƙi shi kamar yadda zauna.

Yanar Gizo

"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);

Hotuna a cikin baƙi

Models da capabilities.vision za a iya karanta hotuna. Add a image_url share zuwa mai amfani bayanin, tare da ko da wani jama'a https:// Link ko a data:image/…;base64, URL. Up to 20 images per request. SVG images suna rike, da kuma wannan ne a kan wani rubutu fiye da 4,096 characters ko daya tare da user name ko password a cikin shi (400 invalid_image_urla. Ayyuka detail Ya auto, low ko high.

Ƙaddamar nymbot/auto, wani baƙin tare da hotuna a cikin shi ne ta hanyar zuwa wani standard model da za a iya ganin. A catalog model ba tare da capabilities.vision Ƙirƙirar hotuna tare da 400 unsupported_content. Pictures za a iya zama kawai a cikin masu amfani messaging. A link za a magana zuwa wani jama'a hosting; Nymbot ya ba da hotuna da hotuna don samar da model kuma ba ya sa shi.

A hotuna da aka kira a matsayin input tokens na samar da shi, kamar yadda sauran bukatun.

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);

Tuntube mu

Models da capabilities.reasoning Yadda za a iya yiwuwa kafin su yiwuwa. Yadda za a yiwuwa da mafi ko mafi reasoning_effort ("minimal", "low", "medium" ko "high"a. "reasoning": {"effort": "high"}, ko Add :thinking to model name, wanda ya ce high effort. A kan wani model ba tare da ra'ayoyi, setup ne ba tare. tare da nymbot/auto, :thinking ya sa shawarar da shawarar zuwa Standard reasoning route.

A kan anthropic samfurori, sha'awar ya zama wani zane-zane na kusa da 1,000, 2,000, 8,000 ko 16,000 tokens, ba zai zama fiye da max_tokens Yadda za a yiwuwa? Yadda za a yiwuwa tool_choice Shawarar wani kayan aiki, kuma a lõkacin da baƙi yana da wani kayan aiki (ya'akari na farko ne wani kayan aiki), saboda Anthropic yana da bukatun da aka haifar da yaushe shi. Sama shi ne a kan haɗin yanar gizo da Messages.

Ra'ayoyi ya zo a cikin message.reasoning_contentko delta.reasoning_content a lokacin streaming, ba tare da shawara a cikin bayani. Reasoning ne output da aka kira a matsayin wannan, a cikin completion_tokensDuk da wasu masana'antu ba su ƙirƙirar ra'ayin a kowace, kuma shi ne ko da yaushe.

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);

Sabuwar Sabuwar Sabuwar

A matsaloli a kan model name ya canza kamar yadda sarrafawa, ba tare da wani yanki. Suna aiki a kan full ids da short names, kamar yadda a cikin anthropic/claude-sonnet-5:online.

Duk wani sauran sufifi ne ba tare. A cikakken sunan da aka ci gaba da farko, don haka wani model wanda ID yana da gaskiya yana da aiki; ba tare da wannan, sufifi suna dauka daga gudu daya a lokaci don wani model dauka. A model sunan za a iya zama a kowace 200 characters tsawon tare da a kowace 4 sufixes; a tsawon daya ne ba tare da 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);

Wasanni

Duk wani chat model zai iya magana daga yanar gizon. Nymbot zai search for latest user message (ya'akari 2,000 na farko), ya karanta mafi kyau pages da kuma ba su zuwa model tare da tambayoyi, da aka karanta a matsayin yanar gizo na yanar gizo ba za a yi magana daga. akwai biyu yanayin:

• Daidaitacce: "plugins": [{"id": "web", "max_results": 5}], ko a :online suffix a kan model.
• Zama a lokacin da yana taimakawa: "tools": [{"type": "web_search", "parameters": {"max_results": 5}}]Har ila yau, da aka samu a matsayin web_search_preview ko openrouter:web_search. Nymbot searches kawai a lokacin da tambayoyi yana da matsala da ya kamata a yanzu bayanai, da sama gwaji da app amfani.

max_results 5 kamar yadda yaushe, kuma a cikin mafi girma 10. A kayayyakin zauna a nymbot.web_search.sourcesKowane tare da a title, snippet kuma urlda kuma as url_citation Ayyukan bayanai a kan bayanai.

Kowane bincike da ke aiki da kudi $ 0.008, da aka canza zuwa sats, a kan tokens, kuma shi ne wani sassa. Sunan da ya karanta ne input tokens kuma, don haka yanayin daga yanar gizon yana da kudi fiye da wannan tambayoyi da aka ba da kowace, wasu lokacin da yawa fiye.

Yanar Gizo

"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);

Yanar Gizo

OpenAI ne mai sabon format, da aka amfani da OpenAI Agents SDK da Codex. Yana aiki a kan samfurin, sayarwa da siffofin kamar Chat Completions.

POST https://nymbot.ai/api/v1/responses - Yana bukatar wani API key.

Yanzu

{
  "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 ya nuna a output a matsayin function_call takardar shaida call_id, name kuma argumentsSaduwa bayanai a matsayin a function_call_output Mataki tare da wannan call_idReasoning, a lõkacin da model ya sa shi, shi ne a reasoning takardar shaida reasoning_text content, listed farko. status Ya incomplete Kuma a lokacin da matsaloli ya sa max_output_tokens ko abokan ciniki ya ba da, tare da incomplete_details.reason Yadda max_output_tokens ko content_filterYanzu yana da faruwa da ƙirƙirar baƙi (temperature, kayan aiki, kayan yanar gizo, da dai sauransu) kamar yadda OpenAI ya yi, da kuma ƙirƙirar nymbot Ƙararrawa Objects.

Streamed, kowane event ne wani event: line da a data: line tare da a sequence_numbera cikin wannan tsari: response.created, response.in_progress, response.output_item.added, response.content_part.addedDuk wani yawan response.output_text.delta, response.output_text.done, response.content_part.done, response.output_item.doneKuma a karshe response.completed tare da amfani da kuma kudin. A bayani cut short ends tare da response.incomplete maimakon, da kuma wani matsaloli bayan matsa lamba ya fara da response.failed. Reasoning streams kamar yadda wani abu tare da response.reasoning_text.delta kuma .done. Aikace-aikace-aikace-aikace suna bayan bayan bayanai, kowane a matsayin abubuwa tare da response.function_call_arguments.delta kuma .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);

Anthropic sabuntawa

The format na Anthropic, ga Anthropic SDKs da Claude Code. Yana aiki tare da kowane model a cikin katako, ba kawai Claude: tambayoyi da aka fassara, ta hanyar sama pipeline, da kuma fassara.

POST https://nymbot.ai/api/v1/messages — bukatar wani API key, kamar yadda x-api-key ko Authorization: Bearer.

da anthropic-version kuma anthropic-beta Anthropic model names suna daidaita tare da catalog, don haka Claude Code da SDKs aiki tare da namu da suka yi amfani:

• wani sunan da aka sani, kamar yadda claude-sonnet-5 ko anthropic/claude-opus-5Yana amfani da shi kamar yadda shi ne.
• Yana da wani takardar (-20260514), -latest, wani version tag kamar yadda -v1, wani bracketed tag kamar yadda [1m] a cikin anthropic/ ko anthropic. prefix suna daukawa, kuma dots da dashes a cikin version suna daidaita biyu (claude-haiku-4-5 Kasa claude-haiku-4.5).
• Shin da haka ba za a yi amfani da al'ada (Opus, Sonnet ko Haiku), duk da cewa version na catalog ne sama ko sabon daga wanda aka ce.
• A sunan da ba ya dace ba tare da wani abu 404 not_found_error.

Yanzu

{
  "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 Za ka iya samun tool_use Blocks da A thinking Blocks, wanda signature Yadda za a iya. stop_reason Ya end_turn, max_tokens, tool_use ko refusal, aiki tare da sama kamar yadda finish_reason ya Tsarin Chat; stop_sequence Yana da null, har ila yau, a lokacin da wani stop sequence ya haifar da matsaloli. input_tokens hanya tsari tsari; tsari tsari ne a cikin biyu kayan tsari. The kudade ne a cikin nymbot Object da kuma X-Nymbot-Cost-Sats takardun

Streamed, abubuwa ne Anthropic's: message_start, content_block_start, ping, content_block_delta (text_delta, input_json_delta ko thinking_delta), content_block_stop, message_delta tare da matsaloli, amfani da kuma nymbot Cost Object, kuma message_stopa ping tambaya a kowace 15 seconds yayin da model yana aiki. Aikace-aikace-aikace-aikace ya zo bayan lissafi, kowane a matsayin tool_use block tare da cikakken input a cikin daya input_json_delta.

Errors a kan wannan endpoint amfani da format na Anthropic: {"type": "error", "error": {"type": "not_found_error", "message": "…"}}A short Balance ne 402 billing_error, wani overloaded provider 503 overloaded_error. A matsaloli bayan matsa lamba da aka fara ne a matsayin error Yanar Gizo

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);

Takardar kebantawa

A ƙaddamar da yawa input tokens wani Messages ba za a yi amfani, don haka da abokan ciniki za a iya duba kafin ya sa. Yana ba tare da free, amma yana da bukatar key.

POST https://nymbot.ai/api/v1/messages/count_tokens — bukatar API key. Free.

Wasanni ne daidai da za a takardar kebantawaƘananan max_tokens; model sunan da za a gyara. A sayarwa ne wani sayarwa: alama na tsarin tsari, takardun shaida, kayan aiki tsari da kayan aiki mai sanyaya, plus 1,600 don kowane hotuna. Yana ba shi ne ba da tayin tokenizer, don haka da kyakkyawan sayarwa za a iya zama daban-daban. A key da aka samu da ƙarfi zai iya yin amfani da shi.

Yanzu

{ "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);

Lissafi da model

Kowane model da generator da API ta karɓar, tare da abin da ya dace. A list an saita daga cikin wannan live catalog da app na picker, don haka shi ne kowace server za a yi aiki.

GET https://nymbot.ai/api/v1/models — No key needed. Closed a kan 5 minti.

GET /api/v1/models/{id} Sauke wani entry.

The farashin ne abin da ka bayar, tare da farashin da marufi a, a dolara da kuma a sats a cikin yanzu Bitcoin farashin. balance ya ce abin da balans da model ya yi amfani. nymbot_key shi ne short name na model a cikin app. created da yaushe 0 kamar yadda catalog ba ya rubuta a lokacin da wani model da aka ƙunshi. A model ba tare da aka gabatar da token farashin ne priceed per_request maimakon haka.

nymbot/auto da yawa na farko, price as variableKuma tare da a routes listing da cewa kowane standard lalata farashin. Yana lists vision da ra'ayi, amma ba kayan aiki.

GET /api/v1/models/{id} dace da samfurori da alama a matsayin baƙi, da kuma ya ba da alama ga model da suka rufe a.

Yanzu

{
  "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"
    }
  ]
}

Ƙananan Ƙananan:

• Wasanni Yanar Gizo capabilities (accepts_image_url, requires_image_url, edit) kuma wani farashin per_generation.
• Wasanni Yanar Gizo max_duration_seconds kuma resolutionsKuma wani farashin per_second ga kowane hotunan.
• Sauke Yanar Gizo audio_type speech ko transcriptionƘananan per_1k_chars ko per_minute.
• Ƙaddamar Yanar Gizo dimensions, context_length, max_inputs kuma wani farashin per miliyan input tokens.

Tarihi Marking "estimated": true ne takardun shaida na app ga wani generator wanda ya ba da farashin. type Kira 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);