Model DeepSeek | Dokumentasi API

# DeepSeek Models

DeepSeek V4 Flash, V4 Pro, and V4.1 Flash model IDs and Chat Completions availability.

POST https://api.apihop.ai/v1/chat-completions

DeepSeek models use the Common Chat Completions endpoint. To switch models, change only the `model` value; the endpoint and authentication stay the same.

```text
POST https://api.apihop.ai/v1/chat-completions
```

## Available Models

| `model` value | Positioning | Non-streaming | SSE streaming |
| --- | --- | --- | --- |
| `deepseek-v4-flash` | Flash tier and a practical starting point for routine chat or batch evaluations | Yes | Yes |
| `deepseek-v4-pro` | Pro tier for evaluations that prioritize complex reasoning and output quality | Yes | Yes |
| `deepseek-v4.1-flash` | DeepSeek V4.1 Flash; a distinct model ID, not a V4 Flash alias | After deployment and enablement | After deployment and enablement |

V4.1 Flash becomes available only after its routing configuration is deployed and enabled. Use it only when `GET https://api.apihop.ai/v1/models` returns `deepseek-v4.1-flash` for your API Key. This reference entry does not confirm a production rollout or a successful inference test. Existing V4 Flash and V4 Pro IDs remain unchanged.

This positioning helps you choose an initial model to test; it is not a latency, throughput, or quality SLA. Compare available models with your own prompts, output lengths, and concurrency before production use.

## Authentication

```http
Authorization: Bearer YOUR_API_KEY
Content-Type: application/json
```

## Non-streaming Request

The endpoint returns one complete Chat Completions response by default. The example includes `stream: false` explicitly so its behavior remains obvious when copied.

```json
{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a precise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain three benefits of event-driven architecture."
    }
  ],
  "stream": false
}
```

To use the Pro model, change only the model field:

```json
{
  "model": "deepseek-v4-pro"
}
```

## Streaming Request

Set `stream: true` explicitly for streaming and process the response as SSE events until `[DONE]`.

```json
{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Create a checklist for a reversible database migration."
    }
  ],
  "stream": true
}
```

## Request Fields

### `model` (string, required)

Use `deepseek-v4-flash`, `deepseek-v4-pro`, or `deepseek-v4.1-flash`, as returned by `GET https://api.apihop.ai/v1/models`.

### `messages` (object[], required)

OpenAI Chat Completions style messages. Each message contains `role` and `content`.

### `stream` (boolean, Default: false)

`true` returns SSE; `false` returns one complete JSON response.

### `max_tokens` (integer)

Optional maximum output tokens, as a positive integer. Omit this field to use the upstream default for the selected model. Depending on the model, the budget may include reasoning tokens as well as final text. A small budget can truncate the answer or be exhausted before final text; increasing it may increase cost.

### `max_completion_tokens` (integer)

Optional compatibility alternative to `max_tokens`, with the same budget considerations. The selected model determines support; omit both fields to use the upstream default.

See [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions) for shared fields such as `temperature`, `top_p`, `frequency_penalty`, `presence_penalty`, `stop`, and `n`. Support and semantic effects may vary by model; this guide does not establish V4.1 Flash support for every optional field.

## Success Response

```json
{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. Services can remain loosely coupled..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 96,
    "total_tokens": 127
  }
}
```

Responses may contain additional usage details; treat them as optional.

## Usage Notes

- The current public contract is Chat Completions, including non-streaming and SSE streaming.
- These models are not currently available through OpenAI Responses or Claude Messages.
- Set the request body's `model` field to the exact ID: `deepseek-v4-flash`, `deepseek-v4-pro`, or `deepseek-v4.1-flash`.
- Use only model IDs returned by `GET https://api.apihop.ai/v1/models`.
- Use `GET https://api.apihop.ai/v1/models` for the models visible to the current API Key, and use the console for current pricing.

## Related Docs

- [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions)
- [Model Catalog](https://apihop.ai/en/docs/api-reference/models)

Model DeepSeek menggunakan endpoint Chat Completions bersama. Untuk beralih model, cukup ubah nilai model; endpoint dan autentikasi tetap sama.

text

POST https://api.apihop.ai/v1/chat-completions

Model yang Tersedia

Nilai `model`	Peruntukan	Tanpa streaming	Streaming SSE
`deepseek-v4-flash`	Tingkat Flash dan pilihan awal praktis untuk percakapan rutin atau evaluasi massal	Ya	Ya
`deepseek-v4-pro`	Tingkat Pro untuk evaluasi yang mengutamakan penalaran kompleks dan kualitas output	Ya	Ya
`deepseek-v4.1-flash`	DeepSeek V4.1 Flash; ID model tersendiri, bukan alias V4 Flash	Setelah deployment dan pengaktifan	Setelah deployment dan pengaktifan

V4.1 Flash baru tersedia setelah konfigurasi peruteannya di-deploy dan diaktifkan. Gunakan hanya jika GET https://api.apihop.ai/v1/models mengembalikan deepseek-v4.1-flash untuk kunci API Anda. Entri referensi ini tidak mengonfirmasi peluncuran produksi atau keberhasilan uji inferensi. ID V4 Flash dan V4 Pro yang ada tetap sama.

Peruntukan ini membantu Anda memilih model awal untuk diuji; ini bukan SLA latensi, throughput, atau kualitas. Bandingkan model yang tersedia dengan prompt, panjang output, dan konkurensi Anda sendiri sebelum digunakan dalam produksi.

Autentikasi

http

Authorization: Bearer YOUR_API_KEY
Content-Type: application/json

Permintaan Tanpa Streaming

Secara bawaan, endpoint mengembalikan satu respons Chat Completions lengkap. Contoh menyertakan stream: false secara eksplisit agar perilakunya tetap jelas saat disalin.

json

{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are a precise technical assistant."
    },
    {
      "role": "user",
      "content": "Explain three benefits of event-driven architecture."
    }
  ],
  "stream": false
}

Untuk menggunakan model Pro, cukup ubah kolom model:

json

{
  "model": "deepseek-v4-pro"
}

Permintaan Streaming

Tetapkan stream: true secara eksplisit untuk streaming dan proses respons sebagai peristiwa SSE hingga [DONE].

json

{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Create a checklist for a reversible database migration."
    }
  ],
  "stream": true
}

Kolom Permintaan

modelstringwajib

Gunakan deepseek-v4-flash, deepseek-v4-pro, atau deepseek-v4.1-flash, sesuai yang dikembalikan oleh GET https://api.apihop.ai/v1/models.

messagesobject[]wajib

Pesan bergaya OpenAI Chat Completions. Setiap pesan berisi role dan content.

streambooleanBawaan: false

true mengembalikan SSE; false mengembalikan satu respons JSON lengkap.

max_tokensinteger

Batas maksimum token output opsional, berupa bilangan bulat positif. Hilangkan kolom ini untuk menggunakan nilai bawaan penyedia hulu bagi model yang dipilih. Bergantung pada model, anggaran ini dapat mencakup token penalaran dan teks akhir. Anggaran kecil dapat memotong jawaban atau habis sebelum teks akhir dihasilkan; menaikkannya dapat meningkatkan biaya.

max_completion_tokensinteger

Alternatif kompatibilitas opsional untuk max_tokens, dengan pertimbangan anggaran yang sama. Dukungan ditentukan oleh model yang dipilih; hilangkan kedua kolom untuk menggunakan nilai bawaan penyedia hulu.

Lihat Chat Completions Bersama untuk kolom bersama seperti temperature, top_p, frequency_penalty, presence_penalty, stop, dan n. Dukungan dan dampak semantik dapat berbeda menurut model; panduan ini tidak menetapkan bahwa V4.1 Flash mendukung setiap kolom opsional.

Respons Berhasil

json

{
  "id": "chatcmpl_...",
  "object": "chat.completion",
  "created": 1787200000,
  "model": "deepseek-v4-flash",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "1. Services can remain loosely coupled..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 31,
    "completion_tokens": 96,
    "total_tokens": 127
  }
}

Respons dapat berisi detail penggunaan tambahan; perlakukan sebagai data opsional.

Catatan Penggunaan

Kontrak publik saat ini adalah Chat Completions, termasuk mode tanpa streaming dan streaming SSE.
Model ini saat ini tidak tersedia melalui OpenAI Responses atau Claude Messages.
Isi kolom model dalam isi permintaan dengan ID yang persis: deepseek-v4-flash, deepseek-v4-pro, atau deepseek-v4.1-flash.
Gunakan hanya ID model yang dikembalikan oleh GET https://api.apihop.ai/v1/models.
Gunakan GET https://api.apihop.ai/v1/models untuk melihat model yang tersedia bagi kunci API saat ini, dan gunakan konsol untuk harga terkini.