API Reference - Hostlinku Docs

Base URL: https://api.hostlinku.com. Semua endpoint gateway berada di bawah /v1 dan menerima API key Hostlinku (sk-…) lewat header Authorization: Bearer atau x-api-key.

Rate Limiting

Untuk menjaga kualitas layanan bagi semua pengguna, gateway memberlakukan batas berikut per API key:

Limit Type	Quota	Description
RPM (Requests/Minute)	600 req/min	Per API key, dibagi untuk semua model
RPD (Requests/Day)	Tidak dibatasi	Dibatasi saldo akun & limit kredit per API key
TPM (Tokens/Minute)	Tidak dibatasi	`max_tokens` wajib ≤ batas output model (ditolak `400` bila melebihi)

Detail rate limit:

Jendela 60 detik per API key; request dari semua model dihitung bersama.
Request yang ditolak limiter tidak menyentuh saldo (tidak ada reservasi kredit).
Endpoint konsol & publik (/api/*) dibatasi 120 req/min per IP; endpoint autentikasi 30 percobaan / 15 menit per IP.

Saat terkena limit:

Mengembalikan HTTP 429 Too Many Requests.
Header Retry-After berisi jumlah detik yang disarankan sebelum mencoba lagi.
Header RateLimit-Limit / RateLimit-Remaining / RateLimit-Reset (format IETF) menunjukkan kuota RPM saat ini.

Anthropic Messages API Format

POST /v1/messages Panggil model dengan format native Anthropic. Header request harus memuat x-api-key: YOUR_API_KEY (atau Authorization: Bearer). Cocok untuk Anthropic SDK, Claude Code, Cursor, dan Cline — cukup set ANTHROPIC_BASE_URL=https://api.hostlinku.com. Dokumentasi lengkap: Anthropic Messages.

Request Body Parameters

Parameter	Type	Description	Required
`model`	string	Slug model Hostlinku, mis. `claude-sonnet-4-6`	true
`messages`	array	Array pesan percakapan (`role`: `user` \| `assistant`)	true
`max_tokens`	integer	Jumlah token output maksimum	true
`system`	string \| array	Prompt sistem (array blok mendukung `cache_control`)	false
`stream`	boolean	Streaming SSE, default `false`	false
`tools`, `tool_choice`, `thinking`, `temperature`, `top_p`, `top_k`, `stop_sequences`, `metadata`	—	Sesuai spesifikasi Anthropic	false

Example Request

curl --request POST \
  --url https://api.hostlinku.com/v1/messages \
  --header 'content-type: application/json' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'anthropic-version: 2023-06-01' \
  --data '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "system": "You are a professional coding assistant",
    "messages": [
      { "role": "user", "content": "Write a quicksort in Python" }
    ]
  }'

Response Example

{
  "id": "msg_mv5ujf05qf6ayfbx",
  "type": "message",
  "role": "assistant",
  "model": "claude-sonnet-4-6",
  "content": [
    { "type": "text", "text": "def quicksort(arr):\n    if len(arr) <= 1:\n        return arr\n    ..." }
  ],
  "stop_reason": "end_turn",
  "stop_sequence": null,
  "usage": {
    "input_tokens": 14,
    "output_tokens": 86,
    "cache_creation_input_tokens": 0,
    "cache_read_input_tokens": 0,
    "cache_creation": { "ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0 }
  },
  "hostlinku": { "cost": 0.0013, "currency": "🪙", "serviceMode": "performance", "latencyMs": 2410 }
}

Streaming Output

curl -N --request POST \
  --url https://api.hostlinku.com/v1/messages \
  --header 'content-type: application/json' \
  --header 'x-api-key: YOUR_API_KEY' \
  --header 'accept: text/event-stream' \
  --data '{
    "model": "claude-sonnet-4-6",
    "max_tokens": 1024,
    "messages": [{ "role": "user", "content": [{ "type": "text", "text": "Hello" }] }],
    "stream": true
  }'

Respons dikirim per potongan dalam format SSE:

event: message_start
data: {"type":"message_start","message":{"id":"msg_…","type":"message","role":"assistant","model":"claude-sonnet-4-6","content":[],"stop_reason":null,"usage":{"input_tokens":10,"output_tokens":1}}}

event: content_block_delta
data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"Hello"}}

event: message_delta
data: {"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":10,"output_tokens":5}}

event: message_stop
data: {"type":"message_stop"}

OpenAI Protocol (Chat Completions API)

POST /v1/chat/completions Panggil model apa pun dengan format OpenAI Chat Completions. Header request harus memuat Authorization: Bearer YOUR_API_KEY. SDK OpenAI cukup diarahkan ke base_url="https://api.hostlinku.com/v1". Dokumentasi lengkap: Chat Completions.

Request Body Parameters

Parameter	Type	Description	Required
`model`	string	Slug model Hostlinku, mis. `gpt-5-5`	true
`messages`	array	Array pesan percakapan (`system` \| `user` \| `assistant` \| `tool`)	true
`max_tokens`	integer	Jumlah token output maksimum	false
`stream`	boolean	Streaming SSE, default `false`	false
`temperature`, `top_p`, `tools`, `tool_choice`, `response_format`, `reasoning_effort`, `thinking`	—	Sesuai spesifikasi OpenAI (+ ekstensi thinking)	false

Example Request

curl https://api.hostlinku.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -d '{
    "model": "gpt-5-5",
    "messages": [
      { "role": "user", "content": "Write a quicksort in Python" }
    ],
    "stream": false
  }'

Example Response

{
  "id": "cmpl_mv5strfqh3zktr",
  "object": "chat.completion",
  "created": 1770000000,
  "model": "gpt-5-5",
  "choices": [
    {
      "index": 0,
      "message": { "role": "assistant", "content": "def quicksort(arr):\n    if len(arr) <= 1:\n        return arr\n    ..." },
      "finish_reason": "stop"
    }
  ],
  "usage": { "prompt_tokens": 12, "completion_tokens": 86, "total_tokens": 98 },
  "hostlinku": { "cost": 0.0009, "currency": "🪙", "serviceMode": "performance", "latencyMs": 1890 }
}

Streaming Output

curl -N https://api.hostlinku.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -d '{
    "model": "gpt-5-5",
    "messages": [{ "role": "user", "content": "Hello" }],
    "stream": true
  }'

data: {"id":"cmpl_…","object":"chat.completion.chunk","model":"gpt-5-5","choices":[{"index":0,"delta":{"role":"assistant","content":""}}]}

data: {"id":"cmpl_…","object":"chat.completion.chunk","model":"gpt-5-5","choices":[{"index":0,"delta":{"content":"Hello"}}]}

data: {"id":"cmpl_…","object":"chat.completion.chunk","model":"gpt-5-5","choices":[{"index":0,"delta":{},"finish_reason":"stop"}],"usage":{"prompt_tokens":5,"completion_tokens":12,"total_tokens":17}}

data: [DONE]

OpenAI Responses API Format

POST /v1/responses Format yang dipakai Codex CLI, OpenAI Agents SDK, dan client.responses.create(). Header request memuat Authorization: Bearer YOUR_API_KEY; base URL https://api.hostlinku.com/v1. Stateless: store selalu false, previous_response_id ditolak 400 — kirim riwayat penuh di input. Dokumentasi lengkap: Responses API.

Request Body Parameters

Parameter	Type	Description	Required
`model`	string	Slug model Hostlinku, mis. `gpt-5-5`	true
`input`	string \| array	Teks, atau array item `message` / `function_call` / `function_call_output` / `reasoning`	true
`instructions`	string	Prompt sistem	false
`max_output_tokens`	integer	Jumlah token output maksimum	false
`stream`	boolean	Streaming SSE (`event: response.*`), default `false`	false
`tools`, `tool_choice`, `reasoning`, `include`, `text`, `temperature`, `top_p`, `metadata`	—	Sesuai spesifikasi OpenAI Responses	false

Example Request

curl https://api.hostlinku.com/v1/responses \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-YOUR_API_KEY" \
  -d '{
    "model": "gpt-5-5",
    "instructions": "Be concise.",
    "input": "Write a quicksort in Python",
    "max_output_tokens": 512
  }'

Example Response

{
  "id": "resp_mv5xpsggbnpc4x7g",
  "object": "response",
  "created_at": 1791850828,
  "status": "completed",
  "model": "gpt-5-5",
  "output": [
    { "id": "rs_…", "type": "reasoning", "summary": [], "encrypted_content": "…" },
    { "id": "msg_…", "type": "message", "status": "completed", "role": "assistant",
      "content": [{ "type": "output_text", "text": "def quicksort(arr): …", "annotations": [] }] }
  ],
  "usage": { "input_tokens": 20, "output_tokens": 95, "total_tokens": 115,
             "input_tokens_details": { "cached_tokens": 0 }, "output_tokens_details": { "reasoning_tokens": 12 } },
  "previous_response_id": null,
  "store": false,
  "hostlinku": { "cost": 0.0011, "currency": "🪙", "serviceMode": "performance", "latencyMs": 1420 }
}

Streaming Output

event: response.created
data: {"type":"response.created","sequence_number":0,"response":{"id":"resp_…","status":"in_progress","model":"gpt-5-5","output":[]}}

event: response.output_text.delta
data: {"type":"response.output_text.delta","sequence_number":4,"item_id":"msg_…","output_index":0,"content_index":0,"delta":"def quicksort"}

event: response.completed
data: {"type":"response.completed","sequence_number":8,"response":{"id":"resp_…","status":"completed","output":[…],"usage":{"input_tokens":20,"output_tokens":95,"total_tokens":115}}}

Error Codes

Envelope error mengikuti protokol endpoint yang dipanggil: /v1/chat/completions → { "status": "error", "error": { "code", "message" } }; /v1/messages → { "type": "error", "error": { "type", "message" } }; /v1/responses → { "error": { "message", "type", "param", "code" } }.

HTTP Status Code	Description	Example Error Message
400	Body tidak valid, `max_tokens` melebihi batas output model, atau model tidak tersedia di Service Mode API key.	`max_tokens (20000) melebihi batas output model 'claude-haiku-4-5' (16000).`
401	API key tidak dikirim, tidak valid, dicabut, atau kedaluwarsa.	`API key tidak valid atau sudah dicabut.`
402	Saldo tidak cukup untuk estimasi biaya request, atau limit kredit API key tercapai.	`Saldo tidak mencukupi.`
403	Akun ditangguhkan / akses ditolak.	`Kamu tidak punya akses ke resource ini.`
404	Slug model tidak ada di katalog.	`Model 'xxx' tidak ditemukan.`
413	Body request melebihi ukuran maksimum.	`Payload terlalu besar.`
422	Validasi body gagal (hanya `/v1/chat/completions`; `/v1/messages` & `/v1/responses` memakai 400).	`Request body tidak valid.`
429	Rate limit terlampaui.	`Rate limit terlampaui. Tingkat plan untuk limit lebih tinggi.`
503	Model/upstream sedang tidak tersedia — aman untuk di-retry dengan backoff.	`Model sedang tidak tersedia. Coba lagi nanti.`

Pesan error tidak pernah memuat identitas atau teks mentah provider upstream. Daftar kode lengkap format OpenAI ada di Error.

429 Response Headers

Response Header	Description
`Retry-After`	Waktu tunggu yang disarankan sebelum mencoba lagi (detik)
`RateLimit-Limit`	Batas RPM
`RateLimit-Remaining`	Sisa request pada jendela berjalan
`RateLimit-Reset`	Detik sampai jendela berikutnya dimulai

Query Available Models

GET /v1/models Mengembalikan model yang tersedia untuk Service Mode API key yang dipakai, beserta harga per 1M token pada mode tersebut.

Example Request

curl --request GET \
  --url https://api.hostlinku.com/v1/models \
  --header 'Authorization: Bearer YOUR_API_KEY'

Response Example

{
  "object": "list",
  "service_mode": "performance",
  "data": [
    {
      "id": "claude-haiku-4-5",
      "object": "model",
      "created": 1760000000,
      "owned_by": "hostlinku",
      "context_window": 200000,
      "capabilities": ["text", "tool-calling", "json-mode", "streaming", "long-context"],
      "service_mode": "performance",
      "pricing": { "input": 0.8, "output": 4, "cache_read": 0.08, "cache_write": 1, "unit": "1M_tokens", "currency": "🪙" }
    },
    {
      "id": "claude-sonnet-4-6",
      "object": "model",
      "created": 1760000000,
      "owned_by": "hostlinku",
      "context_window": 1000000,
      "capabilities": ["text", "vision", "tool-calling", "json-mode", "streaming", "reasoning", "long-context"],
      "service_mode": "performance",
      "pricing": { "input": 2.4, "output": 12, "cache_read": 0.24, "cache_write": 3, "unit": "1M_tokens", "currency": "🪙" }
    }
  ]
}

​Rate Limiting

​Anthropic Messages API Format

​Request Body Parameters

​Example Request

​Response Example

​Streaming Output

​OpenAI Protocol (Chat Completions API)

​Request Body Parameters

​Example Request

​Example Response

​Streaming Output

​OpenAI Responses API Format

​Request Body Parameters

​Example Request

​Example Response

​Streaming Output

​Error Codes

​429 Response Headers

​Query Available Models

​Example Request

​Response Example

Rate Limiting

Anthropic Messages API Format

Request Body Parameters

Example Request

Response Example

Streaming Output

OpenAI Protocol (Chat Completions API)

Request Body Parameters

Example Request

Example Response

Streaming Output

OpenAI Responses API Format

Request Body Parameters

Example Request

Example Response

Streaming Output

Error Codes

429 Response Headers

Query Available Models

Example Request

Response Example