# 💼 API代理对接文档 ## 对接指南 1. 将请求地址由原厂商地址（例如 `api.openai.com`）替换为平台地址（`api.aimindsky.com`）。 2. 将原厂商的 token 替换为平台提供的 token。 3. 示例： ```bash curl https://api.aimindsky.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "gpt-4o", "messages": [ { "role": "user", "content": "hello" } ], "stream": true }' ``` 如需对接其他模型（例如 deepseek、claude 等），只需替换模型名称即可。平台已将 claude 等模型的格式转换为与 OpenAI 相同的格式，确保无缝对接。 ## 支持模型 支持常见的大部分模型，OpenAI、Claude、豆包等，包括且不限于以下模型（模型列表不定时更新，全部可支持的模型以官网为准：https://api.aimindsky.com/pricing）： ```bash gpt-3.5-turbo gpt-4 gpt-4-turbo gpt-4o gpt-4-vision-preview gpt-4o-mini gpt-4o-realtime-preview babbage-002 claude-3-5-sonnet-20240620 claude-3-5-sonnet-20241022 claude-3-5-sonnet-latest claude-3-sonnet-20240229 claude-3-opus-20240229 claude-3-haiku-20240307 claude-3-7-sonnet-20250219 claude-3-7-sonnet-20250219-thinking claude-opus-4-20250514 claude-opus-4-1-20250805 claude-sonnet-4-20250514 claude-3-7-sonnet-20250219-thinking dall-e-2 dall-e-3 davinci-002 deepseek-r1 deepseek-r1-250120 deepseek-v3 deepseek-v3-241226 doubao-1-5-lite-32k-250115 doubao-1-5-pro-256k-250115 doubao-1-5-pro-32k-250115 doubao-1-5-vision-pro-32k-250115 doubao-pro-256k-241115 doubao-pro-32k-241215 doubao-vision-lite-32k-241015 doubao-vision-pro-32k-241028 gemini-1.5-flash gemini-1.5-flash-latest gemini-1.5-pro gemini-1.5-pro-latest gemini-2.0-flash gemini-2.0-flash-exp gemini-2.0-flash-lite-preview gemini-2.0-flash-lite-preview-02-05 gemini-2.0-flash-thinking-exp gemini-2.0-flash-thinking-exp-02-05 gemini-2.0-pro-exp gemini-2.0-pro-exp-02-05 gemini-exp-1206 grok-2 mj_blend mj_custom_zoom mj_describe mj_high_variation mj_imagine mj_inpaint mj_modal mj_pan mj_upscale mj_variation o1 o1-2024-12-17 o1-mini o1-mini-2024-09-12 o1-preview o1-preview-2024-09-12 o3 o3-mini o3-mini-2025-01-31 o3-mini-2025-01-31-high o3-mini-2025-01-31-low o3-mini-2025-01-31-medium o3-mini-high o3-mini-low o3-mini-medium suno_lyrics suno_music text-ada-001 text-babbage-001 text-curie-001 text-davinci-002 text-davinci-003 text-embedding-3-large text-embedding-3-small text-embedding-ada-002 tts-1 tts-1-1106 tts-1-hd tts-1-hd-1106 whisper-1 gpt-image-1 ...... ``` ## 联网模型对接方式 目前支持 `DeepSeek R1` 和 `DeepSeek V3` 的联网，将模型名称后缀添加 `-network` 即可开启，示例如下： ```bash curl https://api.aimindsky.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "deepseek-r1-network", "messages": [ { "role": "user", "content": "hello" } ], "stream": true }' ``` ## Claude 3.7 thinking模式对接方式如下 将模型名称从`claude-3-7-sonnet-20250219`改为`claude-3-7-sonnet-20250219-thinking` 即可开启thinking模式： ```bash curl https://api.aimindsky.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "claude-3-7-sonnet-20250219-thinking", "messages": [ { "role": "user", "content": "hello" } ], "stream": true }' ``` ## AI图片生成 ### gpt-image-1 生图模型 #### 请求示例：创建图像 ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "gpt-image-1", "prompt": "一只可爱的小海獭", # 必填，描述图像内容，可以为中文 "moderation": auto, # 可选，low或者auto。如果是low，则会进行较少的内容审核。 "size": "auto" # 可选，1024x1024, 1536x1024 (风景), 1024x1536 (人物), 或者 auto (默认值) }' ``` #### 请求示例：编辑图像 ```bash # image每张不能超过25MB # prompt不能超过32000个字符 curl -s -D >(grep -i x-request-id >&2) \ -o >(jq -r '.data[0].b64_json' | base64 --decode > gift-basket.png) \ -X POST "https://api.aimindsky.com/v1/images/edits" \ -H "Authorization: Bearer your-own-token" \ -F "model=gpt-image-1" \ -F "image[]=@body-lotion.png" \ -F "image[]=@bath-bomb.png" \ -F "image[]=@incense-kit.png" \ -F "image[]=@soap.png" \ -F 'prompt=Create a lovely gift basket with these four items in it' ``` #### 返回值示例（创建和编辑都相同） ```bash { "created": 1713833628, "data": [ { "b64_json": "..." } ], "usage": { "total_tokens": 100, "input_tokens": 50, "output_tokens": 50, "input_tokens_details": { "text_tokens": 10, "image_tokens": 40 } } } ``` 更加详细的使用方式，请参考官方文档：https://platform.openai.com/docs/guides/image-generation?image-generation-model=gpt-image-1 ### 豆包即梦生图模型(即梦3.0) 模型名称：`doubao-seedream-3-0-t2i-250415` #### 请求示例 ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "doubao-seedream-3-0-t2i-250415", "prompt": "一只可爱的小海獭", # 必填，描述图像内容，支持中文 "size": "1024x1024", # 可选，支持：1024x1024(1:1), 864x1152(3:4), 1152x864(4:3), 1280x720(16:9), 720x1280(9:16), 832x1248(2:3), 1248x832(3:2), 1512x648(21:9)，默认值为1024x1024 "seed": -1, # 可选，随机数种子，取值范围[-1, 2147483647]，默认值为-1 "guidance_scale": 2.5, # 可选，模型输出结果与prompt的一致程度，取值范围[1, 10]，默认值为2.5 "watermark": true # 可选，是否在生成的图片中添加水印，默认值为true，可改为false来去除水印 }' ``` #### 返回值示例 ```bash { "model": "doubao-seedream-3-0-t2i-250415", "created": 1750162231, "data": [ { "url": "https://xxxxxxx.png" } ], "usage": { "generated_images": 1 } } ``` ### 豆包即梦生图模型(即梦4.5) 模型名称：`doubao-seedream-4-0-250828` 或者 `doubao-seedream-4-5-251128` #### 文生图 ##### 请求示例 ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_api_key" \ -d '{ "model": "doubao-seedream-4-0-250828", "prompt": "a cat", "size": "2k" }' ``` ##### 响应示例 ```json { "model": "doubao-seedream-4-0-250828", "created": 1761810887, "data": [ { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217618108818088cd1c854cd9412bce1ed325c44488d9e9c8859_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T075447Z&X-Tos-Expires=86400&X-Tos-Signature=b4796879060509719f28115c7e7d756f1b55814c78c0db8263feb83c1c931112&X-Tos-SignedHeaders=host", "size": "2304x1728" } ], "usage": { "generated_images": 1, "output_tokens": 15552, "total_tokens": 15552 } } ``` #### 图片编辑 ##### 请求示例 ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_api_key" \ -d '{ "model": "doubao-seedream-4-0-250828", "prompt": "生成狗狗趴在草地上的近景画面", "image": "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imageToimage.png" }' ``` ##### 响应示例 ```json { "model": "doubao-seedream-4-0-250828", "created": 1761811020, "data": [ { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217618110092311fe581390692aa6b4e841f642e3d83cc9d623f_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T075700Z&X-Tos-Expires=86400&X-Tos-Signature=2d59bde0a8005b23a9609a924d34db67ffb9fe70b5531d7eafd138b5a69ad31b&X-Tos-SignedHeaders=host", "size": "2048x2048" } ], "usage": { "generated_images": 1, "output_tokens": 16384, "total_tokens": 16384 } } ``` #### 多图融合 ##### 请求示例 ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_api_key" \ -d '{ "model": "doubao-seedream-4-0-250828", "prompt": "将图1的服装换为图2的服装", "image": ["https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_1.png", "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_2.png"] }' ``` ##### 响应示例 ```json { "model": "doubao-seedream-4-0-250828", "created": 1761837249, "data": [ { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/021761837232492e69418056205ce81d973ba378da5a2867963b5_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T151409Z&X-Tos-Expires=86400&X-Tos-Signature=ddc46589005d07778e61b0055eb0b3ec963a12f27b25c0bc4a03ddce97f31a34&X-Tos-SignedHeaders=host", "size": "2048x2048" } ], "usage": { "generated_images": 1, "output_tokens": 16384, "total_tokens": 16384 } } ``` #### 生成组图（支持文生组图、单图生组图、多图生组图等） ##### 请求示例 **注意：生成组图的时候，sequential_image_generation必须设置为"auto"** **sequential_image_generation_options.max_images设置最大生成图片的数量，可设置为1-15之间，默认值为15** ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_api_key" \ -d '{ "model": "doubao-seedream-4-0-250828", "prompt": "生成3张女孩和奶牛玩偶在游乐园开心地坐过山车的图片，涵盖早晨、中午、晚上", "image": ["https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_1.png", "https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimages_2.png"], "sequential_image_generation": "auto" }' ``` ##### 非流式响应示例 ```json { "model": "doubao-seedream-4-0-250828", "created": 1761811189, "data": [ { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217618111037911fe581390692aa6b4e841f642e3d83ccd93190_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T075946Z&X-Tos-Expires=86400&X-Tos-Signature=45f2a5ddf32b01ef385ce0addc20d143a473ad23b16aa593ce50d77c64999fc3&X-Tos-SignedHeaders=host", "size": "2848x1600" }, { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217618111037911fe581390692aa6b4e841f642e3d83ccd93190_1.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T075948Z&X-Tos-Expires=86400&X-Tos-Signature=b7d8a6b5694d62475078ba22a4ab62c9dde6a59390a55f648e0d5fcc73f53bb9&X-Tos-SignedHeaders=host", "size": "2848x1600" }, { "url": "https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217618111037911fe581390692aa6b4e841f642e3d83ccd93190_2.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251030%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251030T075949Z&X-Tos-Expires=86400&X-Tos-Signature=04cc9287350b17ac43fb2ed8e5ea50ea260aed4c4cb7418d9a0e63f621ef9eb9&X-Tos-SignedHeaders=host", "size": "2848x1600" } ], "usage": { "generated_images": 3, "output_tokens": 53400, "total_tokens": 53400 } } ``` ##### 以上接口均支持流式响应，需在入参中设置stream=true，流式响应示例如下： ``` 单图输出： event: image_generation.partial_succeeded data: {"type":"image_generation.partial_succeeded","model":"doubao-seedream-4-0-250828","created":1760911189,"image_index":0,"url":"https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217619660277930879b4c49432771e6cf3401f13842775c846f5_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251101%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251101T030036Z&X-Tos-Expires=86400&X-Tos-Signature=a0b838d22bc604774cbc0d0d6332234232abbdffb538e27d61e794486effb621&X-Tos-SignedHeaders=host","size":"2048x2048"} event: image_generation.completed data: {"type":"image_generation.completed","model":"doubao-seedream-4-0-250828","created":1760911189,"usage":{"generated_images":1,"output_tokens":16384,"total_tokens":16384}} data: [DONE] 多图输出： event: image_generation.partial_succeeded data: {"type":"image_generation.partial_succeeded","model":"doubao-seedream-4-0-250828","created":1761811189,"image_index":0,"url":"https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217619624895354d9829e219e4eab995575a7b2af653bc53456f_0.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251101%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251101T020213Z&X-Tos-Expires=86400&X-Tos-Signature=c89d3ae9d95c0b3a1f5a64cc01d635757a874191ae77c12ac489063519ae0729&X-Tos-SignedHeaders=host","size":"2048x2048"} event: image_generation.partial_succeeded data: {"type":"image_generation.partial_succeeded","model":"doubao-seedream-4-0-250828","created":1761811190,"image_index":1,"url":"https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217619624895354d9829e219e4eab995575a7b2af653bc53456f_1.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251101%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251101T020238Z&X-Tos-Expires=86400&X-Tos-Signature=52f0866818e115533d49dcbf6fd83764fb18b4ff74c413f27b737158833fece3&X-Tos-SignedHeaders=host","size":"2048x2048"} event: image_generation.partial_succeeded data: {"type":"image_generation.partial_succeeded","model":"doubao-seedream-4-0-250828","created":1761811191,"image_index":2,"url":"https://ark-content-generation-v2-cn-beijing.tos-cn-beijing.volces.com/doubao-seedream-4-0/0217619624895354d9829e219e4eab995575a7b2af653bc53456f_2.jpeg?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYWJkZTExNjA1ZDUyNDc3YzhjNTM5OGIyNjBhNDcyOTQ%2F20251101%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20251101T020254Z&X-Tos-Expires=86400&X-Tos-Signature=6df6aa6071b0e4855900bf6b9501f671e00ef55a7a930d599873483daa77c432&X-Tos-SignedHeaders=host","size":"2048x2048"} event: image_generation.completed data: {"type":"image_generation.completed","model":"doubao-seedream-4-0-250828","created":1761962574,"usage":{"generated_images":3,"output_tokens":49152,"total_tokens":49152}} data: [DONE] ``` 更加详细的使用方式，请参考: 官方效果预览：https://www.volcengine.com/docs/82379/1824718#6c2e2d17 官方使用手册：https://www.volcengine.com/docs/82379/1824121 官方参数文档：https://www.volcengine.com/docs/82379/1541523（支持所有参数） ### Nano Banana 模型 #### 模型概述 | 版本 | 模型名称 | 说明 | |------|----------|------| | **Nano Banana 2(Nano Banana Pro)** | `gemini-3-pro-image-preview` | 推荐使用，稳定性更好 | | Nano Banana 1 | `gemini-2.5-flash-image-preview` | 偶尔不返回图片，需添加重试机制 | #### 调用方式说明 | 端点 | 推荐程度 | 说明 | |------|----------|------| | `/v1/chat/completions` | ⭐ **推荐** | 支持流式输出，格式统一，兼容性好 | | `/v1/images/generations` | 可选 | 简化调用方式 | > ⚠️ **注意事项** > - 不支持 `/v1/images/edits` 端点，如需图片编辑，请在 `/v1/chat/completions` 或 `/v1/images/generations` 中传入图片参数 > - Nano Banana 1 模型偶尔不返回图片内容（官方现象），请自行添加重试机制 --- #### 文生图 ##### 请求示例（推荐：/v1/chat/completions） ```bash curl https://api.aimindsky.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_own_token" \ -d '{ "model": "gemini-3-pro-image-preview", "messages": [ { "role": "user", "content": "a cat" } ], "stream": true }' ``` ##### 响应示例（/v1/chat/completions） ```json data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{"content":"","role":"assistant"},"finish_reason":null,"index":0}]} data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{"content":"![image](data:image/jpeg;base64,/9j/4AAQSkZJRgABAQ....m7smk9L6H/9k=)"},"finish_reason":null,"index":0}]} data: {"id":"chatcmpl-xxx","object":"chat.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{},"finish_reason":"stop","index":0}]} data: [DONE] ```
📎 备选方式：/v1/images/generations **请求示例** ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your_own_token" \ -d '{ "model": "gemini-3-pro-image-preview", "prompt": "a cat" }' ``` **响应示例** ```json { "created": 1769565997, "data": [ { "b64_json": "/9j/4AAQSkZJRgABAQxxxxxxxx...." } ], "usage": { "total_tokens": 1624, "input_tokens": 238, "output_tokens": 1386, "input_tokens_details": { "text_tokens": 10, "image_tokens": 500 } } } ```
--- #### 图片编辑 ##### 请求示例（推荐：/v1/chat/completions） ```bash curl https://api.aimindsky.com/v1/chat/completions \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "gemini-3-pro-image-preview", "messages": [ { "role": "user", "content": [ { "type": "text", "text": "合并这两张图片" }, { "type": "image_url", "image_url": { "url": "your_image_url1" } }, { "type": "image_url", "image_url": { "url": "your_image_url2" } } ] } ], "stream": true }' ``` ##### 响应示例（/v1/chat/completions） ```json data: {"id":"imgeditcmpl-xxx","object":"image_edit.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{"content":"","role":"assistant"},"finish_reason":null,"index":0}]} data: {"id":"imgeditcmpl-xxx","object":"image_edit.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{"content":"![image](data:image/jpeg;base64,/9j/4AAQSkZJRgABAQ....m7smk9L6H/9k=)"},"finish_reason":null,"index":0}]} data: {"id":"imgeditcmpl-xxx","object":"image_edit.completion.chunk","created":1763688665,"model":"gemini-3-pro-image-preview","choices":[{"delta":{},"finish_reason":"stop","index":0}]} data: [DONE] ```
📎 备选方式：/v1/images/generations **请求示例** ```bash curl https://api.aimindsky.com/v1/images/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "gemini-3-pro-image-preview", "prompt": "合并这两张图片", "image": ["your_image_url1", "your_image_url2"] }' ``` **响应示例** ```json { "created": 1769565997, "data": [ { "b64_json": "/9j/4AAQSkZJRgABAQxxxxxxxx...." } ], "usage": { "total_tokens": 1624, "input_tokens": 238, "output_tokens": 1386, "input_tokens_details": { "text_tokens": 10, "image_tokens": 500 } } } ```
## AI视频生成 ### 火山模型 模型名称：`doubao-seedance-1-0-pro-250528` 计费方式：按token计费，每百万token 15元。 token计算方式：视频token用量≈ (宽 × 高 × 帧率 × 时长)/1024，准确的 token 用量以调用 API 后返回信息中的usage字段为准。 综合来看，每秒视频大约1元左右。 #### 请求示例 注意：除了prompt参数，其他参数都为可选参数。 ```bash curl https://api.aimindsky.com/v1/videos/generations \ -H "Content-Type: application/json" \ -H "Authorization: Bearer your-own-token" \ -d '{ "model": "doubao-seedance-1-0-pro-250528", "prompt": "一只可爱的小海獭在游泳", # 必填，描述图像内容，可以为中文 "image": 'base64data......', # 可选,base64编码的图片数据 "ratio": '16:9' # 可选，默认16:9,可选值：21:9, 16:9,4:3,1:1,3:4, 9:16, 21:9。doubao-seedance-1-0-pro-250528模型有参考图的时候仅支持adaptive。 "duration": 5 # 可选，默认5秒，只能选5或者10，不能输入其他值 "framepersecond": 24 # 可选，帧率，默认24，可选16或者24 "watermark": false, # 可选，是否生成水印 "camerafixed": false, # 可选，是否固定镜头，默认false "seed": 123456 # 可选，随机种子，用于生成相同的视频，范围0-4294967295，默认是随机种子 "resolution": "1080p"， # 可选，默认1080p,可选值：480p, 1080p }' ``` #### 返回值示例 ```bash { created: 1749967991, data: [ { url: 'https://ark-content-generation-cn-beijing.tos-cn-beijing.volces.com/doubao-seedance-1-0-pro/02174996789110900000000000000000000ffffac182c17e4bd45.mp4?X-Tos-Algorithm=TOS4-HMAC-SHA256&X-Tos-Credential=AKLTYjg3ZjNlOGM0YzQyNGE1MmI2MDFiOTM3Y2IwMTY3OTE%2F20250615%2Fcn-beijing%2Ftos%2Frequest&X-Tos-Date=20250615T061310Z&X-Tos-Expires=86400&X-Tos-Signature=e01bebc2b89fea0642b48bce31aaf7eda2c0732021939b73470ec8e3b1dacc3a&X-Tos-SignedHeaders=host', } ], id: 'cgt-xxxxx-xxxxxxx', usage: 488025 } ``` ## Claude Code使用方法 本站支持Claude Code的使用，无需注册和购买 Claude 账号，没有封号风险。 使用方法如下： 1. 正常下载安装Claude Code，官方文档：https://docs.anthropic.com/zh-CN/docs/claude-code/overview。 2. 在系统中设置环境变量： ``` export ANTHROPIC_BASE_URL="https://api.aimindsky.com" export ANTHROPIC_AUTH_TOKEN="your-own-token"（注意：这里的key必须是claude-raw分组，否则无法使用） ``` **特别注意：新建令牌的时候，一定要选择"claude-raw"分组。因为如果不选的话系统默认会使用OpenAI的接口格式，不符合Claude Code的规范，从而无法使用。** 3. 终端中输入`claude`命令，正常使用即可，用法同官方一样。 4. 最佳实践： 4.1 可以将以上命令写入到`~/.bashrc`或者`~/.zshrc`文件中，这样每次打开终端时，环境变量都会自动设置。 4.2 在`vscode`或者`cursor`中，可以安装`Claude Code`插件，这样就可以在编辑器中使用Claude Code。 ## Claude Code使用GLM-4.5模型 Claude Code支持使用GLM-4.5模型，使用方法同上。 ``` export ANTHROPIC_BASE_URL="https://api.aimindsky.com" export ANTHROPIC_AUTH_TOKEN="your-own-token" ``` 注意：这里的key分组要选择“glm-claude-code”分组。 glm-claude-code分组计费说明： GLM-4.5支持Claude Code的原理是：GLM收到Claude Code的请求后，将Claude的模型ID转换为GLM4.5的模型ID，从而实现兼容。因此，在计费系统中显示的是Claude模型。由于GLM-4.5模型费用基本上是Claude模型的13%，因此，glm-claude-code分组的计费基本上是claude-raw分组的13%，也就是0.13倍率，价格比Claude模型便宜很多。 ## 其他注意事项 1. Deepseek R1 已按开源模型格式进行封装，推理消息内容使用 `` 标签包裹。如需采用 `reasoning_content` 格式，请在创建 token 时选择“huoshan-raw”分组（注意：修改分组为高危操作，修改之后，该key的返回值结构将变化。建议在新建的key上进行修改，如确需修改原key，则请确定好之前的代码是否已经兼容。同时：huoshan-raw分组只能调用火山模型，无法使用OpenAI等其他模型。）。