HubotEng – AI Model Gateway

Genel Bakış

HubotEng birleştirilmiş bir yapay zeka API geçidi sunar. OpenAI, Anthropic, Google, Mistral, Meta, DeepSeek, Groq, xAI, Perplexity ve Cohere modellerine — OpenAI uyumlu tek bir endpoint üzerinden erişin. Entegrasyon kodunuza dokunmadan modelleri değiştirin.

🔗

Temel URL

https://huboteng.com/api/v1

🔑

Kimlik Doğrulama

Bearer hb-...

📦

Format

OpenAI-compatible JSON

⚡

Streaming

Server-Sent Events

Kimlik Doğrulama

API anahtarınızı Authorization başlığında Bearer token olarak gönderin. Anahtarınızı huboteng.com/keys.

Header

Authorization: Bearer hb-your-api-key-here

⚠️ API anahtarınızı asla istemci (client) tarafındaki koda veya herkese açık depolara (repository) koymayın.

Hızlı Başlangıç

HubotEng, OpenAI SDK'si ile %100 uyumludur. Sadece baseURL ve anahtarınızı değiştirmeniz yeterli.

Python

quickstart.py

from openai import OpenAI

client = OpenAI(
    base_url="https://huboteng.com/api/v1",
    api_key="hb-your-api-key",
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of Turkey?"}
    ],
    max_tokens=256,
)

print(response.choices[0].message.content)

Node.js / TypeScript

quickstart.ts

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://huboteng.com/api/v1',
  apiKey: 'hb-your-api-key',
})

const response = await client.chat.completions.create({
  model: 'google/gemini-2.0-flash',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of Turkey?' },
  ],
  max_tokens: 256,
})

console.log(response.choices[0].message.content)

cURL

curl

curl https://huboteng.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer hb-your-api-key" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

POST /api/v1/chat/completions

Yapay zeka metin üretimi için temel endpoint. OpenAI Chat Completions API'si ile uyumlu.

İstek Parametreleri

modelstringzorunlu

Model ID'si, örn. "anthropic/claude-3-5-sonnet". Tam liste için GET /api/v1/models kullanın.

messagesarrayzorunlu

{role, content} objelerinden oluşan dizi. role "system", "user" veya "assistant" olmalıdır.

streamboolean

Token'ları SSE olarak yayınla. Varsayılan: false.

max_tokensinteger

Maksimum çıkış token sayısı. Varsayılan: 1024.

temperaturenumber

Örnekleme sıcaklığı 0–2. Yüksek = daha yaratıcı. Varsayılan: 1.0.

Yanıt

Non-streaming response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1720000000,
  "model": "anthropic/claude-3-5-sonnet",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Ankara is the capital of Turkey."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 9,
    "total_tokens": 37
  }
}

Streaming

Token'ları Server-Sent Events (SSE) ile geldikleri an almak için stream: true kullanın.

streaming.py

stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku about Istanbul"}],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

streaming.ts

const stream = await client.chat.completions.create({
  model: 'meta/llama-3.3-70b',
  messages: [{ role: 'user', content: 'Tell me a joke' }],
  stream: true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}

Ham SSE formatı:

SSE wire format

data: {"choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"choices":[{"delta":{"content":" there"},"index":0}]}

data: [DONE]

GET /api/v1/models

Mevcut tüm modelleri döndürür.

bash

curl https://huboteng.com/api/v1/models \
  -H "Authorization: Bearer hb-your-api-key"

Response (excerpt)

{
  "object": "list",
  "data": [
    { "id": "anthropic/claude-3-5-sonnet", "object": "model", "owned_by": "anthropic" },
    { "id": "openai/gpt-4o",              "object": "model", "owned_by": "openai" },
    { "id": "google/gemini-2.0-flash",    "object": "model", "owned_by": "google" }
  ]
}

Hata Kodları

Standart HTTP kodları. Gövdeler OpenAI hata formatına uyar.

Status	type	Description
401	`authentication_error`	Missing or invalid API key.
402	`insufficient_credits`	Account has run out of credits.
404	`invalid_request_error`	Model not found.
422	`invalid_request_error`	Missing or malformed request body.
429	`rate_limit_error`	Rate limit exceeded for this API key.
500	`api_error`	Internal or upstream provider error.

Error body format

{ "error": { "message": "Invalid or inactive API key.", "type": "authentication_error" } }

Hız Sınırları

Her API anahtarı için 1 dakikalık kayan pencerede uygulanır. Limitleri 🔑 API Anahtarları sayfasından ayarlayabilirsiniz. Bir 429 hatası şu başlıkları içerir:

`Retry-After`	Pencerenin sıfırlanmasına kalan saniye.
`X-RateLimit-Limit`	Bu anahtar için dakikada maksimum istek.
`X-RateLimit-Remaining`	Mevcut pencerede kalan istekler.
`X-RateLimit-Reset`	Pencerenin sıfırlanacağı Unix timestamp.

SDK Örnekleri

LangChain (Python)

langchain_example.py

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="anthropic/claude-3-5-sonnet",
    openai_api_base="https://huboteng.com/api/v1",
    openai_api_key="hb-your-api-key",
)

response = llm.invoke("Explain attention in one paragraph.")
print(response.content)

Vercel AI SDK (Next.js)

app/api/chat/route.ts

import { createOpenAI } from '@ai-sdk/openai'
import { streamText } from 'ai'

const huboteng = createOpenAI({
  baseURL: 'https://huboteng.com/api/v1',
  apiKey: process.env.HUBOTENG_API_KEY!,
})

export async function POST(req: Request) {
  const { messages } = await req.json()
  const result = streamText({
    model: huboteng('deepseek/deepseek-r1'),
    messages,
  })
  return result.toDataStreamResponse()
}

Vanilla fetch

fetch_example.js

const res = await fetch('https://huboteng.com/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer hb-your-api-key',
  },
  body: JSON.stringify({
    model: 'mistral/mistral-large',
    messages: [{ role: 'user', content: 'Hello!' }],
  }),
})
const data = await res.json()
console.log(data.choices[0].message.content)

Model Fiyatları

Fiyatlar 1 milyon token başına USD cinsindendir. Yalnızca kullanılan token'lar (Giriş + Çıkış) için ödeme yaparsınız.

Modelleri Listele	Sağlayıcı	Bağlam	Giriş /1M	Çıkış /1M
GPT-4o gpt-4o	🟢OpenAI	128K	$5	$15
GPT-4o Mini gpt-4o-mini	🟢OpenAI	128K	$0.15	$0.6
GPT-4 Turbo gpt-4-turbo	🟢OpenAI	128K	$10	$30
GPT-4 gpt-4	🟢OpenAI	8K	$30	$60
GPT-3.5 Turbo gpt-3.5-turbo	🟢OpenAI	16K	$0.5	$1.5
o1 o1	🟢OpenAI	200K	$15	$60
o1 Mini o1-mini	🟢OpenAI	128K	$3	$12
o3 Mini o3-mini	🟢OpenAI	200K	$1.1	$4.4
Claude 3.5 Sonnet claude-3-5-sonnet-20241022	🟠Anthropic	200K	$3	$15
Claude 3.5 Haiku claude-3-5-haiku-20241022	🟠Anthropic	200K	$0.8	$4
Claude 3 Opus claude-3-opus-20240229	🟠Anthropic	200K	$15	$75
Claude 3 Sonnet claude-3-sonnet-20240229	🟠Anthropic	200K	$3	$15
Claude 3 Haiku claude-3-haiku-20240307	🟠Anthropic	200K	$0.25	$1.25
Gemini 2.0 Flash gemini-2.0-flash	🔵Google	1M	$0.075	$0.3
Gemini 1.5 Pro gemini-1.5-pro	🔵Google	2M	$3.5	$10.5
Gemini 1.5 Flash gemini-1.5-flash	🔵Google	1M	$0.075	$0.3
Gemini 1.5 Flash 8B gemini-1.5-flash-8b	🔵Google	1M	$0.0375	$0.15
Mistral Large mistral-large-latest	🟣Mistral	131K	$3	$9
Mistral Small mistral-small-latest	🟣Mistral	33K	$0.2	$0.6
Codestral codestral-latest	🟣Mistral	33K	$1	$3
Mixtral 8x22B mixtral-8x22b-instruct	🟣Mistral	66K	$2	$6
Mixtral 8x7B mixtral-8x7b-instruct	🟣Mistral	33K	$0.6	$0.6
Llama 3.3 70B llama-3.3-70b-versatile	🔴Groq	131K	$0.59	$0.79
Llama 3.1 70B llama-3.1-70b-versatile	🔴Groq	131K	$0.59	$0.79
Llama 3.1 8B Instant llama-3.1-8b-instant	🔴Groq	131K	$0.05	$0.08
Llama 3 70B llama3-70b-8192	🔴Groq	8K	$0.59	$0.79
Llama 3 8B llama3-8b-8192	🔴Groq	8K	$0.05	$0.08
Gemma 2 9B gemma2-9b-it	🔴Groq	8K	$0.2	$0.2
DeepSeek R1 Distill 70B deepseek-r1-distill-llama-70b	🔴Groq	131K	$0.75	$0.99
DeepSeek V3 deepseek-chat	🩵DeepSeek	66K	$0.27	$1.1
DeepSeek R1 deepseek-reasoner	🩵DeepSeek	66K	$0.55	$2.19
Command R+ command-r-plus	🩶Cohere	128K	$2.5	$10
Command R command-r	🩶Cohere	128K	$0.15	$0.6
Command command	🩶Cohere	4K	$1	$2

Genel Bakış

🔗

Temel URL

https://huboteng.com/api/v1

🔑

Kimlik Doğrulama

Bearer hb-...

📦

Format

OpenAI-compatible JSON

⚡

Streaming

Server-Sent Events

Kimlik Doğrulama

API anahtarınızı Authorization başlığında Bearer token olarak gönderin. Anahtarınızı huboteng.com/keys.

Header

Authorization: Bearer hb-your-api-key-here

⚠️ API anahtarınızı asla istemci (client) tarafındaki koda veya herkese açık depolara (repository) koymayın.

Hızlı Başlangıç

HubotEng, OpenAI SDK'si ile %100 uyumludur. Sadece baseURL ve anahtarınızı değiştirmeniz yeterli.

Python

quickstart.py

from openai import OpenAI

client = OpenAI(
    base_url="https://huboteng.com/api/v1",
    api_key="hb-your-api-key",
)

response = client.chat.completions.create(
    model="anthropic/claude-3-5-sonnet",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the capital of Turkey?"}
    ],
    max_tokens=256,
)

print(response.choices[0].message.content)

Node.js / TypeScript

quickstart.ts

import OpenAI from 'openai'

const client = new OpenAI({
  baseURL: 'https://huboteng.com/api/v1',
  apiKey: 'hb-your-api-key',
})

const response = await client.chat.completions.create({
  model: 'google/gemini-2.0-flash',
  messages: [
    { role: 'system', content: 'You are a helpful assistant.' },
    { role: 'user', content: 'What is the capital of Turkey?' },
  ],
  max_tokens: 256,
})

console.log(response.choices[0].message.content)

cURL

curl

curl https://huboteng.com/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer hb-your-api-key" \
  -d '{
    "model": "openai/gpt-4o-mini",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

POST /api/v1/chat/completions

Yapay zeka metin üretimi için temel endpoint. OpenAI Chat Completions API'si ile uyumlu.

İstek Parametreleri

modelstringzorunlu

Model ID'si, örn. "anthropic/claude-3-5-sonnet". Tam liste için GET /api/v1/models kullanın.

messagesarrayzorunlu

{role, content} objelerinden oluşan dizi. role "system", "user" veya "assistant" olmalıdır.

streamboolean

Token'ları SSE olarak yayınla. Varsayılan: false.

max_tokensinteger

Maksimum çıkış token sayısı. Varsayılan: 1024.

temperaturenumber

Örnekleme sıcaklığı 0–2. Yüksek = daha yaratıcı. Varsayılan: 1.0.

Yanıt

Non-streaming response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1720000000,
  "model": "anthropic/claude-3-5-sonnet",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Ankara is the capital of Turkey."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 28,
    "completion_tokens": 9,
    "total_tokens": 37
  }
}

Streaming

Token'ları Server-Sent Events (SSE) ile geldikleri an almak için stream: true kullanın.

streaming.py

stream = client.chat.completions.create(
    model="openai/gpt-4o",
    messages=[{"role": "user", "content": "Write a haiku about Istanbul"}],
    stream=True,
)

for chunk in stream:
    content = chunk.choices[0].delta.content
    if content:
        print(content, end="", flush=True)

streaming.ts

const stream = await client.chat.completions.create({
  model: 'meta/llama-3.3-70b',
  messages: [{ role: 'user', content: 'Tell me a joke' }],
  stream: true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}

Ham SSE formatı:

SSE wire format

data: {"choices":[{"delta":{"content":"Hello"},"index":0}]}

data: {"choices":[{"delta":{"content":" there"},"index":0}]}

data: [DONE]

GET /api/v1/models

Mevcut tüm modelleri döndürür.

bash

curl https://huboteng.com/api/v1/models \
  -H "Authorization: Bearer hb-your-api-key"

Response (excerpt)

{
  "object": "list",
  "data": [
    { "id": "anthropic/claude-3-5-sonnet", "object": "model", "owned_by": "anthropic" },
    { "id": "openai/gpt-4o",              "object": "model", "owned_by": "openai" },
    { "id": "google/gemini-2.0-flash",    "object": "model", "owned_by": "google" }
  ]
}

Hata Kodları

Standart HTTP kodları. Gövdeler OpenAI hata formatına uyar.

Status	type	Description
401	`authentication_error`	Missing or invalid API key.
402	`insufficient_credits`	Account has run out of credits.
404	`invalid_request_error`	Model not found.
422	`invalid_request_error`	Missing or malformed request body.
429	`rate_limit_error`	Rate limit exceeded for this API key.
500	`api_error`	Internal or upstream provider error.

Error body format

{ "error": { "message": "Invalid or inactive API key.", "type": "authentication_error" } }

Hız Sınırları

Her API anahtarı için 1 dakikalık kayan pencerede uygulanır. Limitleri 🔑 API Anahtarları sayfasından ayarlayabilirsiniz. Bir 429 hatası şu başlıkları içerir:

`Retry-After`	Pencerenin sıfırlanmasına kalan saniye.
`X-RateLimit-Limit`	Bu anahtar için dakikada maksimum istek.
`X-RateLimit-Remaining`	Mevcut pencerede kalan istekler.
`X-RateLimit-Reset`	Pencerenin sıfırlanacağı Unix timestamp.

SDK Örnekleri

LangChain (Python)

langchain_example.py

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="anthropic/claude-3-5-sonnet",
    openai_api_base="https://huboteng.com/api/v1",
    openai_api_key="hb-your-api-key",
)

response = llm.invoke("Explain attention in one paragraph.")
print(response.content)

Vercel AI SDK (Next.js)

app/api/chat/route.ts

import { createOpenAI } from '@ai-sdk/openai'
import { streamText } from 'ai'

const huboteng = createOpenAI({
  baseURL: 'https://huboteng.com/api/v1',
  apiKey: process.env.HUBOTENG_API_KEY!,
})

export async function POST(req: Request) {
  const { messages } = await req.json()
  const result = streamText({
    model: huboteng('deepseek/deepseek-r1'),
    messages,
  })
  return result.toDataStreamResponse()
}

Vanilla fetch

fetch_example.js

const res = await fetch('https://huboteng.com/api/v1/chat/completions', {
  method: 'POST',
  headers: {
    'Content-Type': 'application/json',
    'Authorization': 'Bearer hb-your-api-key',
  },
  body: JSON.stringify({
    model: 'mistral/mistral-large',
    messages: [{ role: 'user', content: 'Hello!' }],
  }),
})
const data = await res.json()
console.log(data.choices[0].message.content)

Model Fiyatları

Fiyatlar 1 milyon token başına USD cinsindendir. Yalnızca kullanılan token'lar (Giriş + Çıkış) için ödeme yaparsınız.

Modelleri Listele	Sağlayıcı	Bağlam	Giriş /1M	Çıkış /1M
GPT-4o gpt-4o	🟢OpenAI	128K	$5	$15
GPT-4o Mini gpt-4o-mini	🟢OpenAI	128K	$0.15	$0.6
GPT-4 Turbo gpt-4-turbo	🟢OpenAI	128K	$10	$30
GPT-4 gpt-4	🟢OpenAI	8K	$30	$60
GPT-3.5 Turbo gpt-3.5-turbo	🟢OpenAI	16K	$0.5	$1.5
o1 o1	🟢OpenAI	200K	$15	$60
o1 Mini o1-mini	🟢OpenAI	128K	$3	$12
o3 Mini o3-mini	🟢OpenAI	200K	$1.1	$4.4
Claude 3.5 Sonnet claude-3-5-sonnet-20241022	🟠Anthropic	200K	$3	$15
Claude 3.5 Haiku claude-3-5-haiku-20241022	🟠Anthropic	200K	$0.8	$4
Claude 3 Opus claude-3-opus-20240229	🟠Anthropic	200K	$15	$75
Claude 3 Sonnet claude-3-sonnet-20240229	🟠Anthropic	200K	$3	$15
Claude 3 Haiku claude-3-haiku-20240307	🟠Anthropic	200K	$0.25	$1.25
Gemini 2.0 Flash gemini-2.0-flash	🔵Google	1M	$0.075	$0.3
Gemini 1.5 Pro gemini-1.5-pro	🔵Google	2M	$3.5	$10.5
Gemini 1.5 Flash gemini-1.5-flash	🔵Google	1M	$0.075	$0.3
Gemini 1.5 Flash 8B gemini-1.5-flash-8b	🔵Google	1M	$0.0375	$0.15
Mistral Large mistral-large-latest	🟣Mistral	131K	$3	$9
Mistral Small mistral-small-latest	🟣Mistral	33K	$0.2	$0.6
Codestral codestral-latest	🟣Mistral	33K	$1	$3
Mixtral 8x22B mixtral-8x22b-instruct	🟣Mistral	66K	$2	$6
Mixtral 8x7B mixtral-8x7b-instruct	🟣Mistral	33K	$0.6	$0.6
Llama 3.3 70B llama-3.3-70b-versatile	🔴Groq	131K	$0.59	$0.79
Llama 3.1 70B llama-3.1-70b-versatile	🔴Groq	131K	$0.59	$0.79
Llama 3.1 8B Instant llama-3.1-8b-instant	🔴Groq	131K	$0.05	$0.08
Llama 3 70B llama3-70b-8192	🔴Groq	8K	$0.59	$0.79
Llama 3 8B llama3-8b-8192	🔴Groq	8K	$0.05	$0.08
Gemma 2 9B gemma2-9b-it	🔴Groq	8K	$0.2	$0.2
DeepSeek R1 Distill 70B deepseek-r1-distill-llama-70b	🔴Groq	131K	$0.75	$0.99
DeepSeek V3 deepseek-chat	🩵DeepSeek	66K	$0.27	$1.1
DeepSeek R1 deepseek-reasoner	🩵DeepSeek	66K	$0.55	$2.19
Command R+ command-r-plus	🩶Cohere	128K	$2.5	$10
Command R command-r	🩶Cohere	128K	$0.15	$0.6
Command command	🩶Cohere	4K	$1	$2