> ## Documentation Index > Fetch the complete documentation index at: https://docs.hostlinku.com/llms.txt > Use this file to discover all available pages before exploring further. # Model > Endpoint GET /v1/models, bentuk data katalog, dan cara memilih model yang tepat Hostlinku menyediakan satu katalog model terpusat. Setiap model punya **slug** unik yang dipakai di parameter `model` pada [Chat Completions](https://docs.hostlinku.com/chat-completions.md), lengkap dengan ukuran konteks, kapabilitas, dan harga per token. ## `GET /v1/models` Mengembalikan semua model yang berstatus `available`, belum deprecated, dan tersedia untuk **Service Mode API key** yang dipakai (Performance atau Low-Cost), beserta harga kredit per 1M token pada mode tersebut. ```http theme={null} GET https://api.hostlinku.com/v1/models Authorization: Bearer sk-isi-api-key-kamu ``` Contoh: ```bash theme={null} curl https://api.hostlinku.com/v1/models \ -H "Authorization: Bearer sk-isi-api-key-kamu" ``` Respons (contoh dipotong; nilai persis untuk akun kamu diambil dari endpoint ini): ```json theme={null} { "object": "list", "service_mode": "performance", "data": [ { "id": "claude-haiku-4-5", "object": "model", "created": 1791380432, "owned_by": "hostlinku", "context_window": 200000, "capabilities": ["text", "tool-calling", "function-calling", "structured-outputs", "json-mode", "streaming", "code-generation", "long-context", "multilingual"], "service_mode": "performance", "pricing": { "input": 0.8, "output": 4, "cache_read": 0.08, "cache_write": 1, "unit": "1M_tokens", "currency": "🪙" } } ] } ``` | Field | Arti | | - | - | | `service_mode` (level list & item) | Service Mode API key yang dipakai: `performance` atau `low_cost`. Daftar model berbeda per mode. | | `id` | Slug model, nilai yang dipakai di field `model` pada `/v1/chat/completions`, `/v1/messages`, dan `/v1/responses`. | | `created` | Waktu model ditambahkan ke katalog (Unix epoch, detik). | | `owned_by` | Selalu `"hostlinku"` - penanda bahwa model dikelola oleh katalog Hostlinku. | | `context_window` | Ukuran konteks maksimum dalam token (input + output). | | `capabilities` | Daftar kapabilitas, mis. `vision`, `tool-calling`, `json-mode`, `reasoning`, `long-context`. | | `pricing` | Objek harga pada Service Mode tersebut; `null` bila model belum punya harga di mode itu. `pricing.unit` selalu `"1M_tokens"` dan `pricing.currency` berisi simbol kredit (1 kredit = \$1). | | `pricing.input` / `pricing.output` | Harga per **1M token** (bukan per 1 token atau per 1K) untuk token prompt / token jawaban. | | `pricing.cache_read` / `pricing.cache_write` | Harga per 1M token untuk cache read / cache write 5 menit (lihat [Prompt Caching](https://docs.hostlinku.com/prompt-caching.md)); `null` bila model tidak mendukung. | Pricing di respons adalah harga customer Angka `pricing` adalah harga yang kamu bayar pada Service Mode API key tersebut; margin platform sudah termasuk di dalamnya. Biaya aktual setiap request selalu muncul di blok `hostlinku.cost` pada respons dan di log console. ## Katalog publik (tanpa autentikasi) Untuk situs marketing atau eksplorasi tanpa API key, tersedia katalog publik: ```http theme={null} GET https://api.hostlinku.com/api/public/models ``` Katalog publik hanya menampilkan model Hostlinku beserta slug, nama, konteks, capability, dan harga publiknya. Query yang didukung: `q` (pencarian nama/deskripsi), `capability`, `family`, `sort` (`popular`, `newest`, `price-asc`, `price-desc`, `context-desc`, `name-asc`), `page`, dan `pageSize` (maks 100). Respons `data` memuat `items`, `total`, `page`, `pageSize`, dan `totalPages`. ## Daftar model 45 model tersedia saat ini. Klik nama model untuk melihat konteks, kapabilitas, harga, dan endpoint yang didukung. | Model | Provider | Konteks | Output maks | Input /1M | Output /1M | | - | - | - | - | - | - | | [Qwen 3.6 Plus](https://docs.hostlinku.com/models/qwen3-6-plus.md) | Alibaba | 1,000,000 | - | \$0.294 | \$1.765 | | [Qwen 3.7 Max](https://docs.hostlinku.com/models/qwen3-7-max.md) | Alibaba | 1,000,000 | - | \$1.765 | \$5.294 | | [Model Baize](https://docs.hostlinku.com/models/model-baize.md) | Anonymous | 1,000,000 | - | \$1.177 | \$4.118 | | [Claude Fable 5](https://docs.hostlinku.com/models/claude-fable-5.md) | Anthropic | 1,000,000 | 128,000 | \$10 | \$50 | | [Claude Fable 5.1](https://docs.hostlinku.com/models/claude-fable-5-1.md) | Anthropic | 1,000,000 | 128,000 | - | - | | [Claude Haiku 4.5](https://docs.hostlinku.com/models/claude-haiku-4-5.md) | Anthropic | 200,000 | 64,000 | \$1 | \$5 | | [Claude Opus 4.6](https://docs.hostlinku.com/models/claude-opus-4-6.md) | Anthropic | 1,000,000 | 32,000 | \$5 | \$25 | | [Claude Opus 4.7](https://docs.hostlinku.com/models/claude-opus-4-7.md) | Anthropic | 1,000,000 | 32,000 | \$5 | \$25 | | [Claude Opus 4.8](https://docs.hostlinku.com/models/claude-opus-4-8.md) | Anthropic | 1,000,000 | 128,000 | \$5 | \$25 | | [Claude Opus 5](https://docs.hostlinku.com/models/claude-opus-5.md) | Anthropic | 1,000,000 | 64,000 | \$5 | \$25 | | [Claude Opus 5.5](https://docs.hostlinku.com/models/claude-opus-5-5.md) | Anthropic | 1,000,000 | 128,000 | \$4 | \$20 | | [Claude Sonnet 4.6](https://docs.hostlinku.com/models/claude-sonnet-4-6.md) | Anthropic | 1,000,000 | 64,000 | \$3 | \$15 | | [Claude Sonnet 5](https://docs.hostlinku.com/models/claude-sonnet-5.md) | Anthropic | 1,000,000 | 64,000 | \$2 | \$10 | | [Claude Sonnet 5.5](https://docs.hostlinku.com/models/claude-sonnet-5-5.md) | Anthropic | 1,000,000 | 128,000 | - | - | | [DeepSeek V4 Flash](https://docs.hostlinku.com/models/deepseek-v4-flash.md) | DeepSeek | 1,000,000 | - | \$0.15 | \$0.6 | | [DeepSeek V4 Pro](https://docs.hostlinku.com/models/deepseek-v4-pro.md) | DeepSeek | 1,000,000 | 64,000 | \$0.662 | \$1.985 | | [DeepSeek-V4.1-Flash](https://docs.hostlinku.com/models/deepseek-v4-1-flash.md) | DeepSeek | 1,000,000 | 384,000 | \$0.15 | \$0.6 | | [DeepSeek-V4.1-Flash Hyper](https://docs.hostlinku.com/models/deepseek-v4-1-flash-hyper.md) | DeepSeek | 1,000,000 | 384,000 | - | - | | [DeepSeek-V4.1-Flash Hyper Chat](https://docs.hostlinku.com/models/deepseek-v4-1-flash-hyper-chat.md) | DeepSeek | 1,000,000 | 384,000 | - | - | | [DeepSeek-V4.1-Flash Turbo](https://docs.hostlinku.com/models/deepseek-v4-1-flash-turbo.md) | DeepSeek | 1,000,000 | 384,000 | - | - | | [MiniMax M3](https://docs.hostlinku.com/models/minimax-m3.md) | MiniMax | 1,000,000 | 64,000 | \$0.309 | \$1.235 | | [Kimi K2.6](https://docs.hostlinku.com/models/kimi-k2-6.md) | Moonshot | 256,000 | 32,000 | \$0.956 | \$3.971 | | [Kimi K2.7 Code](https://docs.hostlinku.com/models/kimi-k2-7-code.md) | Moonshot | 256,000 | - | \$0.956 | \$3.971 | | [Kimi K3](https://docs.hostlinku.com/models/kimi-k3.md) | Moonshot | 1,000,000 | 64,000 | \$2.941 | \$14.706 | | [Kimi K3 Hyper](https://docs.hostlinku.com/models/kimi-k3-hyper.md) | Moonshot | 1,000,000 | 64,000 | - | - | | [Kimi K3 Hyper Chat](https://docs.hostlinku.com/models/kimi-k3-hyper-chat.md) | Moonshot | 1,000,000 | 64,000 | - | - | | [Kimi K3 Turbo](https://docs.hostlinku.com/models/kimi-k3-turbo.md) | Moonshot | 1,000,000 | 64,000 | - | - | | [GPT 5.3 Codex](https://docs.hostlinku.com/models/gpt-5-3-codex.md) | OpenAI | 400,000 | 128,000 | \$1.75 | \$14 | | [GPT-5.5](https://docs.hostlinku.com/models/gpt-5-5.md) | OpenAI | 1,000,000 | 128,000 | \$5 | \$30 | | [GPT-5.6 Luna](https://docs.hostlinku.com/models/gpt-5-6-luna.md) | OpenAI | 1,050,000 | 64,000 | \$0.2 | \$1.2 | | [GPT-5.6 Sol](https://docs.hostlinku.com/models/gpt-5-6-sol.md) | OpenAI | 1,050,000 | 64,000 | \$4 | \$20 | | [GPT-5.6 Terra](https://docs.hostlinku.com/models/gpt-5-6-terra.md) | OpenAI | 1,050,000 | 64,000 | \$2 | \$12 | | [GPT-6 Astra](https://docs.hostlinku.com/models/gpt-6-astra.md) | OpenAI | 1,050,000 | 128,000 | \$10 | \$50 | | [GPT-6 Luna](https://docs.hostlinku.com/models/gpt-6-luna.md) | OpenAI | 1,050,000 | 128,000 | \$0.1 | \$0.5 | | [GPT-6 Sol](https://docs.hostlinku.com/models/gpt-6-sol.md) | OpenAI | 1,050,000 | 128,000 | \$2 | \$10 | | [GPT-6.1 Sol](https://docs.hostlinku.com/models/gpt-6-1-sol.md) | OpenAI | 1,050,000 | 128,000 | \$2 | \$10 | | [MiMo V2.5 Pro](https://docs.hostlinku.com/models/mimo-v2-5-pro.md) | Xiaomi | 1,000,000 | 32,000 | \$0.441 | \$0.882 | | [GLM 5](https://docs.hostlinku.com/models/glm-5.md) | Zhipu | 200,000 | - | \$0.588 | \$2.647 | | [GLM 5.1](https://docs.hostlinku.com/models/glm-5-1.md) | Zhipu | 200,000 | 128,000 | \$0.882 | \$3.529 | | [GLM 5.2](https://docs.hostlinku.com/models/glm-5-2.md) | Zhipu | 1,000,000 | 64,000 | \$1.177 | \$4.118 | | [GLM 5.3](https://docs.hostlinku.com/models/glm-5-3.md) | Zhipu | 1,000,000 | 64,000 | \$1.177 | \$4.118 | | [GLM 5.3 Hyper Chat](https://docs.hostlinku.com/models/glm-5-3-hyper-chat.md) | Zhipu | 1,000,000 | 64,000 | - | - | | [GLM-5.3 Flash](https://docs.hostlinku.com/models/glm-5-3-flash.md) | Zhipu | 1,000,000 | 64,000 | - | - | | [GLM-5.3 Flash Hyper](https://docs.hostlinku.com/models/glm-5-3-flash-hyper.md) | Zhipu | 1,000,000 | 64,000 | - | - | | [GLM-5.3 Flash Hyper Chat](https://docs.hostlinku.com/models/glm-5-3-flash-hyper-chat.md) | Zhipu | 1,000,000 | 64,000 | - | - | ## Cara memilih model 1. **Tentukan kebutuhan**: chat biasa, penalaran (*reasoning*), vision/multimodal, tool calling, atau output JSON terstruktur. Cek field `capabilities`. 2. **Perhatikan ukuran konteks**: pastikan `context_window` cukup untuk prompt + output kamu. 3. **Bandingkan harga**: `pricing.input` untuk token prompt dan `pricing.output` untuk token jawaban; model reasoning umumnya lebih mahal di output. 4. **Mulai dari model kecil**: untuk pengembangan, model kelas ringan (mis. `gpt-6-luna`, `deepseek-v4-1-flash`, `qwen3-6-plus`) jauh lebih murah; naikkan kelas model hanya bila kualitas kurang. 5. **Lihat konsol**: menu **Model** di [console.hostlinku.com](https://console.hostlinku.com) menampilkan katalog dengan harga dan kapabilitas yang sama, plus halaman detail per model. Alias slug Gunakan slug persis seperti yang dikembalikan `GET /v1/models`. Slug tidak case-sensitive di sisi tampilan, tetapi selalu salin apa adanya dari katalog untuk menghindari salah ketik. Slug yang tidak ada di katalog mengembalikan `404 MODEL_NOT_FOUND`; model yang sudah deprecated atau sedang tidak tersedia mengembalikan `503 MODEL_UNAVAILABLE` beserta saran slug penggantinya bila tersedia. ## Routing dan failover Hostlinku mengatur sendiri jalur internal yang melayani tiap model. Jika terjadi gangguan pada jalur yang sedang dipakai (5xx/timeout), request otomatis dicoba lagi lewat jalur lain sebelum menyerah. Kamu tetap memakai slug model yang sama dan tidak perlu mengubah apa pun; detail internal ini tidak ditampilkan di respons. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.