模型目錄 | API 文件

# Model Catalog

List the models available to the current API Key and their public protocols.

GET https://api.apihop.ai/v1/models

`GET https://api.apihop.ai/v1/models` returns the models available to the current API Key. Availability can change with model configuration, service health, and API Key permissions, so the live API response is the final source of truth.

Claude Sonnet 4.6 (`claude-sonnet-4-6`) is supported by the upstream supplier but is not currently published on RequestBeam. It is not an active integration default. Before calling any model, confirm access with your own `GET https://api.apihop.ai/v1/models` response.

```text
GET https://api.apihop.ai/v1/models
```

## Authentication

All requests require a Bearer Token.

```http
Authorization: Bearer YOUR_API_KEY
```

## Request Example

```bash
curl --request GET \
  --url https://api.apihop.ai/v1/models \
  --header 'Authorization: Bearer YOUR_API_KEY'
```

## Response

### `uid` (string)

Public model identifier. For APIs that accept `model`, use this value in the request body's `model` field.

### `name` (string)

Display name.

### `version` (string | null)

Version field. Current entries usually return `null`.

### `type` (string)

Model type, currently mainly `text`, `image`, or `video`.

### `pricing` (object | null)

Current platform pricing for the model. Use the live API or console for current values.

### Success Example

```json
{
  "success": true,
  "data": [
    {
      "uid": "gpt-5.6-sol",
      "name": "ChatGPT-5.6 Sol",
      "version": null,
      "type": "text",
      "pricing": {
        "unit": "credits",
        "tokenTierBasis": "input_tokens",
        "tiers": []
      }
    },
    {
      "uid": "seedance-2.5",
      "name": "Seedance 2.5",
      "version": null,
      "type": "video",
      "pricing": {
        "unit": "credits",
        "tiers": []
      }
    }
  ],
  "requestId": "req_..."
}
```

## Current Text Models

The following table summarizes the currently documented text models. For each request, use the models returned by your own `GET https://api.apihop.ai/v1/models` call.

| Model family | Model ID | Chat Completions | Responses | Claude Messages |
| --- | --- | --- | --- | --- |
| OpenAI | `gpt-5.4` | Yes | Yes | - |
| OpenAI | `gpt-5.5` | Yes | Yes | - |
| OpenAI | `gpt-5.6-sol` | Yes | Yes | - |
| OpenAI | `gpt-5.6-terra` | Yes | Yes | - |
| OpenAI | `gpt-6-astra` | Yes | Yes | - |
| Anthropic | `claude-fable-5` | Yes | - | Yes |
| Anthropic | `claude-fable-5-1` | Yes | - | Yes |
| Anthropic | `claude-opus-4-6` | Yes | - | Yes |
| Anthropic | `claude-opus-4-7` | Yes | - | Yes |
| Anthropic | `claude-opus-4-8` | Yes | - | Yes |
| Anthropic | `claude-opus-5` | Yes | - | Yes |
| Anthropic | `claude-opus-5-5` | Yes | - | Yes |
| Anthropic | `claude-sonnet-5` | Yes | - | Yes |
| Anthropic | `claude-sonnet-5-5` | Yes | - | Yes |
| DeepSeek | `deepseek-v4-flash` | Yes | - | - |
| DeepSeek | `deepseek-v4-pro` | Yes | - | - |
| DeepSeek | `deepseek-v4.1-flash` | After deployment and enablement | - | - |
| Gemini | `gemini-3.6-flash` | Yes | - | - |
| Gemini | `gemini-3.7-flash` | Yes | - | - |
| Gemini | `gemini-3.8-flash` | Yes | - | - |
| Gemini | `gemini-3.5-flash-lite` | Yes | - | - |
| Gemini | `gemini-4-argon` | Yes (after enablement) | - | - |
| Kimi | `kimi-k3` | Yes | - | - |
| MiniMax | `minimax-m3` | Yes | - | - |

Claude output budgets include thinking and final text. A small `max_tokens` value such as `128` may be exhausted before any final text is produced. Use a positive integer budget with room for both, as described in [Claude Messages](https://apihop.ai/en/docs/api-reference/Claude/messages).

## Model Family Guides

- [DeepSeek Models](https://apihop.ai/en/docs/api-reference/DeepSeek/models): `deepseek-v4-flash`, `deepseek-v4-pro`, `deepseek-v4.1-flash` (a distinct ID, available only after deployment and enablement; check `GET https://api.apihop.ai/v1/models`)
- [Gemini Models](https://apihop.ai/en/docs/api-reference/Gemini/models): `gemini-3.6-flash`, `gemini-3.7-flash`, `gemini-3.8-flash`, `gemini-3.5-flash-lite`, `gemini-4-argon` (after deployment and enablement)
- [Kimi Model](https://apihop.ai/en/docs/api-reference/Kimi/models): `kimi-k3`
- [MiniMax Model](https://apihop.ai/en/docs/api-reference/MiniMax/models): `minimax-m3`

These guides cover model selection, request examples, output-budget notes, and the current public protocol boundary. The live response from this endpoint remains authoritative for availability.

## Current Image and Video Models

| Model family | Model ID | Type | Public endpoint |
| --- | --- | --- | --- |
| OpenAI | `gpt-image-2` | Image | `POST https://api.apihop.ai/openai/v1/images/generations` |
| OpenAI | `gpt-image-2.5-flare` | Image | `POST https://api.apihop.ai/openai/v1/images/generations` |
| OpenAI | `gpt-image-2.5-sunburst` | Image | `POST https://api.apihop.ai/openai/v1/images/generations` |
| BytePlus | `seedance-2.0` | Video | `POST https://api.apihop.ai/v1/video/seedance` |
| BytePlus | `seedance-2.5` | Video | `POST https://api.apihop.ai/v1/video/seedance` |

## Other API Entry

`twitterapi` represents the Twitter data APIs and is not a Chat model. Use the `/v1/twitter/*` endpoints instead of passing `twitterapi` to Chat Completions.

## Model ID Rules

- Chat Completions, Responses, Claude Messages, image, and Seedance video APIs

use `model`.

- The canonical Seedance model IDs are `seedance-2.0` and `seedance-2.5`. The Seedance 2.0 endpoint also accepts the legacy alias `seedance-2-0`, but new requests and catalog lookups should use the canonical dotted ID.
- Use only model IDs returned by `GET https://api.apihop.ai/v1/models`.
- Unavailable models do not appear in `/v1/models` and should not be used for new calls.
- An API Key with model restrictions may receive a subset of the documented models.

## Related Docs

- [Common Chat Completions](https://apihop.ai/en/docs/api-reference/common-chat-completions)
- [DeepSeek Models](https://apihop.ai/en/docs/api-reference/DeepSeek/models)
- [Gemini Models](https://apihop.ai/en/docs/api-reference/Gemini/models)
- [Kimi Model](https://apihop.ai/en/docs/api-reference/Kimi/models)
- [MiniMax Model](https://apihop.ai/en/docs/api-reference/MiniMax/models)
- [OpenAI Responses](https://apihop.ai/en/docs/api-reference/OpenAI/responses)
- [Claude Messages](https://apihop.ai/en/docs/api-reference/Claude/messages)
- [GPT-Image-2 Image Generation](https://apihop.ai/en/docs/api-reference/OpenAI/gpt-image-2)
- [Seedance 2.0 Video Generation](https://apihop.ai/en/docs/api-reference/BytePlus/seedance-2-0)
- [Seedance 2.5 Video Generation](https://apihop.ai/en/docs/api-reference/BytePlus/seedance-2-5)

## Error Response

See [Error Codes and Troubleshooting](https://apihop.ai/en/docs/api-reference/errors) for the full code reference, protocol differences, and diagnostic steps.

```json
{
  "success": false,
  "error": {
    "code": 20000,
    "message": "Invalid or missing API key"
  },
  "requestId": "req_..."
}
```

GET https://api.apihop.ai/v1/models 會傳回目前 API 金鑰可用的模型。可用性會隨模型設定、服務健康狀態及 API 金鑰權限變動，因此以即時 API 回應為最終依據。

上游供應商支援 Claude Sonnet 4.6（claude-sonnet-4-6），但目前尚未在 RequestBeam 發布，因此不是已啟用的預設整合模型。呼叫任何模型前，請以您自己的 GET https://api.apihop.ai/v1/models 回應確認存取權限。

text

GET https://api.apihop.ai/v1/models

驗證

所有請求均需要 Bearer Token。

http

Authorization: Bearer YOUR_API_KEY

請求範例

bash

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

回應

uidstring

公開模型識別碼。對於接受 model 的 API，請將此值填入請求主體的 model 欄位。

namestring

顯示名稱。

versionstring | null

版本欄位。目前的項目通常傳回 null。

typestring

模型類型，目前主要為 text、image 或 video。

pricingobject | null

模型目前的平台定價。最新數值請以即時 API 或主控台為準。

成功範例

json

{
  "success": true,
  "data": [
    {
      "uid": "gpt-5.6-sol",
      "name": "ChatGPT-5.6 Sol",
      "version": null,
      "type": "text",
      "pricing": {
        "unit": "credits",
        "tokenTierBasis": "input_tokens",
        "tiers": []
      }
    },
    {
      "uid": "seedance-2.5",
      "name": "Seedance 2.5",
      "version": null,
      "type": "video",
      "pricing": {
        "unit": "credits",
        "tiers": []
      }
    }
  ],
  "requestId": "req_..."
}

目前的文字模型

下表彙整目前文件列出的文字模型。每次請求都應使用您自己的 GET https://api.apihop.ai/v1/models 呼叫所傳回的模型。

模型系列	模型 ID	Chat Completions	Responses	Claude Messages
OpenAI	`gpt-5.4`	是	是	-
OpenAI	`gpt-5.5`	是	是	-
OpenAI	`gpt-5.6-sol`	是	是	-
OpenAI	`gpt-5.6-terra`	是	是	-
OpenAI	`gpt-6-astra`	是	是	-
Anthropic	`claude-fable-5`	是	-	是
Anthropic	`claude-fable-5-1`	是	-	是
Anthropic	`claude-opus-4-6`	是	-	是
Anthropic	`claude-opus-4-7`	是	-	是
Anthropic	`claude-opus-4-8`	是	-	是
Anthropic	`claude-opus-5`	是	-	是
Anthropic	`claude-opus-5-5`	是	-	是
Anthropic	`claude-sonnet-5`	是	-	是
Anthropic	`claude-sonnet-5-5`	是	-	是
DeepSeek	`deepseek-v4-flash`	是	-	-
DeepSeek	`deepseek-v4-pro`	是	-	-
DeepSeek	`deepseek-v4.1-flash`	部署並啟用後	-	-
Gemini	`gemini-3.6-flash`	是	-	-
Gemini	`gemini-3.7-flash`	是	-	-
Gemini	`gemini-3.8-flash`	是	-	-
Gemini	`gemini-3.5-flash-lite`	是	-	-
Gemini	`gemini-4-argon`	是（啟用後）	-	-
Kimi	`kimi-k3`	是	-	-
MiniMax	`minimax-m3`	是	-	-

Claude 輸出預算包含思考與最終文字。像 128 這樣較小的 max_tokens 值，可能在產生任何最終文字前就已耗盡。請使用能容納兩者的正整數預算，詳見 Claude 訊息。

模型系列指南

DeepSeek 模型：deepseek-v4-flash、deepseek-v4-pro、deepseek-v4.1-flash（獨立 ID，僅在部署並啟用後可用；請檢查 GET https://api.apihop.ai/v1/models）
Gemini 模型：gemini-3.6-flash、gemini-3.7-flash、gemini-3.8-flash、gemini-3.5-flash-lite、gemini-4-argon（部署並啟用後）
Kimi 模型：kimi-k3
MiniMax 模型：minimax-m3

這些指南涵蓋模型選擇、請求範例、輸出預算注意事項及目前的公開協定邊界。可用性仍以此端點的即時回應為準。

目前的圖像與影片模型

模型系列	模型 ID	類型	公開端點
OpenAI	`gpt-image-2`	圖像	`POST https://api.apihop.ai/openai/v1/images/generations`
OpenAI	`gpt-image-2.5-flare`	圖像	`POST https://api.apihop.ai/openai/v1/images/generations`
OpenAI	`gpt-image-2.5-sunburst`	圖像	`POST https://api.apihop.ai/openai/v1/images/generations`
BytePlus	`seedance-2.0`	影片	`POST https://api.apihop.ai/v1/video/seedance`
BytePlus	`seedance-2.5`	影片	`POST https://api.apihop.ai/v1/video/seedance`

其他 API 項目

twitterapi 代表 Twitter 資料 API，不是聊天模型。請使用 /v1/twitter/* 端點，不要將 twitterapi 傳入 Chat Completions。

模型 ID 規則

Chat Completions、Responses、Claude Messages、圖像與 Seedance 影片 API 使用 model。
Seedance 的標準模型 ID 為 seedance-2.0 與 seedance-2.5。Seedance 2.0 端點也接受舊別名 seedance-2-0，但新請求與目錄查詢應使用含小數點的標準 ID。
僅使用 GET https://api.apihop.ai/v1/models 傳回的模型 ID。
不可用的模型不會出現在 /v1/models 中，也不應用於新的呼叫。
設有模型限制的 API 金鑰，可能只會取得文件所列模型的一部分。

錯誤回應

完整代碼參考、協定差異及診斷步驟，請見錯誤代碼與疑難排解。

json

{
  "success": false,
  "error": {
    "code": 20000,
    "message": "Invalid or missing API key"
  },
  "requestId": "req_..."
}