chat_completion

Send a conversation to any text model available through CCAPI (Claude, GPT, Gemini, DeepSeek, GLM, MiniMax, Kimi, Qwen…) and get the reply. Useful for consulting a second model for a different perspective, running a cheap model over bulk work, or reaching a model the current client does not have configured. Responses are non-streaming.

Parameters6

model	string	required	Exact model name, e.g. claude-sonnet-5 or deepseek-v4-pro. Call list_models with category 'text' if unsure.
messages	null \| array	required	Conversation so far, oldest first. Must contain at least one message.
max_tokens	null \| integer	optional	Maximum tokens to generate. Omit for the model default.
temperature	null \| number	optional	Sampling temperature, typically 0-2. Omit for the model default.
top_p	null \| number	optional	Nucleus sampling probability mass, 0-1. Omit for the model default.
stop	null \| array	optional	Up to 4 sequences that stop generation.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Exact model name, e.g. claude-sonnet-5 or deepseek-v4-pro. Call list_models with category 'text' if unsure."
    },
    "messages": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "object",
        "properties": {
          "role": {
            "type": "string",
            "description": "Message author: system, user or assistant."
          },
          "content": {
            "type": "string",
            "description": "Message text."
          }
        },
        "required": [
          "role",
          "content"
        ],
        "additionalProperties": false
      },
      "description": "Conversation so far, oldest first. Must contain at least one message."
    },
    "max_tokens": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Maximum tokens to generate. Omit for the model default."
    },
    "temperature": {
      "type": [
        "null",
        "number"
      ],
      "description": "Sampling temperature, typically 0-2. Omit for the model default."
    },
    "top_p": {
      "type": [
        "null",
        "number"
      ],
      "description": "Nucleus sampling probability mass, 0-1. Omit for the model default."
    },
    "stop": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Up to 4 sequences that stop generation."
    }
  },
  "required": [
    "model",
    "messages"
  ],
  "additionalProperties": false
}

edit_image

Edit existing images according to an instruction, using the dedicated image edit endpoint. Provide at least one source image. For pure text-to-image, or for models that take references through the generation endpoint, use generate_image instead.

Parameters11

model	string	required	Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure.
prompt	string	required	Description of the image to generate.
images	null \| array	optional	Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.
size	string	optional	Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default.
n	null \| integer	optional	How many images to generate. Defaults to 1. Each one is billed.
quality	string	optional	Quality hint, e.g. low, medium, high or auto. Model-dependent.
response_format	string	optional	'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary.
aspect_ratio	string	optional	Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.
nsfw_checker	null \| boolean	optional	Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.
async	boolean	optional	Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'.
wait_seconds	null \| integer	optional	Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure."
    },
    "prompt": {
      "type": "string",
      "description": "Description of the image to generate."
    },
    "images": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references."
    },
    "size": {
      "type": "string",
      "description": "Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default."
    },
    "n": {
      "type": [
        "null",
        "integer"
      ],
      "description": "How many images to generate. Defaults to 1. Each one is billed."
    },
    "quality": {
      "type": "string",
      "description": "Quality hint, e.g. low, medium, high or auto. Model-dependent."
    },
    "response_format": {
      "type": "string",
      "description": "'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary."
    },
    "aspect_ratio": {
      "type": "string",
      "description": "Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16."
    },
    "nsfw_checker": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved."
    },
    "async": {
      "type": "boolean",
      "description": "Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time."
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}

extend_music

Continue an existing song from a given timestamp, producing a longer version. Requires the clip_id of a previously generated song, which appears in the 'raw' payload of a completed generate_music task. Asynchronous — poll with get_task.

Parameters7

clip_id	string	required	ID of the song to extend, taken from the 'raw' clip list of a completed generate_music task.
continue_at	number	required	Timestamp in seconds within the original song to continue from.
prompt	string	optional	Lyrics for the extended section.
title	string	optional	New title for the extended song.
tags	string	optional	Style tags for the extension.
provider	string	optional	Music backend: 'suno' (default) or 'producer'.
wait_seconds	null \| integer	optional	Poll server-side for up to this many seconds (max 240).

Raw schema

{
  "type": "object",
  "properties": {
    "clip_id": {
      "type": "string",
      "description": "ID of the song to extend, taken from the 'raw' clip list of a completed generate_music task."
    },
    "continue_at": {
      "type": "number",
      "description": "Timestamp in seconds within the original song to continue from."
    },
    "prompt": {
      "type": "string",
      "description": "Lyrics for the extended section."
    },
    "title": {
      "type": "string",
      "description": "New title for the extended song."
    },
    "tags": {
      "type": "string",
      "description": "Style tags for the extension."
    },
    "provider": {
      "type": "string",
      "description": "Music backend: 'suno' (default) or 'producer'."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Poll server-side for up to this many seconds (max 240)."
    }
  },
  "required": [
    "clip_id",
    "continue_at"
  ],
  "additionalProperties": false
}

generate_image

Generate an image from a text prompt, optionally guided by reference images (image-to-image). Returns image URLs directly. Most models finish in 10-60 seconds; if your client times out, set async=true to get a task_id you can poll instead. This call costs money — do not retry speculatively.

Parameters11

model	string	required	Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure.
prompt	string	required	Description of the image to generate.
images	null \| array	optional	Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references.
size	string	optional	Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default.
n	null \| integer	optional	How many images to generate. Defaults to 1. Each one is billed.
quality	string	optional	Quality hint, e.g. low, medium, high or auto. Model-dependent.
response_format	string	optional	'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary.
aspect_ratio	string	optional	Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16.
nsfw_checker	null \| boolean	optional	Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved.
async	boolean	optional	Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'.
wait_seconds	null \| integer	optional	Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Exact model name, e.g. gpt-image-2 or nano-banana-pro. Call list_models with category 'image' if unsure."
    },
    "prompt": {
      "type": "string",
      "description": "Description of the image to generate."
    },
    "images": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Optional reference images as HTTPS URLs or data URLs, for image-to-image generation. Not all models accept references."
    },
    "size": {
      "type": "string",
      "description": "Output size, e.g. 1024x1024, 1536x1024, or 'auto'. Model-dependent; omit for the model default."
    },
    "n": {
      "type": [
        "null",
        "integer"
      ],
      "description": "How many images to generate. Defaults to 1. Each one is billed."
    },
    "quality": {
      "type": "string",
      "description": "Quality hint, e.g. low, medium, high or auto. Model-dependent."
    },
    "response_format": {
      "type": "string",
      "description": "'url' (default) returns links; 'b64_json' returns base64 data, which is far larger and usually unnecessary."
    },
    "aspect_ratio": {
      "type": "string",
      "description": "Z-Image only: required output aspect ratio. Supported values: 1:1, 4:3, 3:4, 16:9, 9:16."
    },
    "nsfw_checker": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "Z-Image only: enable or disable the upstream NSFW checker. Explicit false is preserved."
    },
    "async": {
      "type": "boolean",
      "description": "Submit asynchronously and return a task_id instead of waiting. Use when the client times out on slow models; poll with get_task using platform 'image'."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Only with async: poll server-side for up to this many seconds (max 240) and return the finished image if it completes in time."
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}

generate_lyrics

Write song lyrics from a description, without generating audio. Useful as a first step before generate_music with custom=true, so the user can approve the words before paying for audio. Asynchronous — poll with get_task.

Parameters4

prompt	string	required	Description of the lyrics to write, e.g. 'a love song about meeting someone at a coffee shop'.
lyrics_model	string	optional	Lyrics model: classic or remi.
provider	string	optional	Music backend: 'suno' (default) or 'producer'.
wait_seconds	null \| integer	optional	Poll server-side for up to this many seconds (max 240). Lyrics usually finish in under 30 seconds.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "Description of the lyrics to write, e.g. 'a love song about meeting someone at a coffee shop'."
    },
    "lyrics_model": {
      "type": "string",
      "description": "Lyrics model: classic or remi."
    },
    "provider": {
      "type": "string",
      "description": "Music backend: 'suno' (default) or 'producer'."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Poll server-side for up to this many seconds (max 240). Lyrics usually finish in under 30 seconds."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}

generate_music

Generate a song with vocals or instrumental. Two modes: simple (custom=false) where you describe the song and the model writes the lyrics, or custom (custom=true) where you supply lyrics, title and style tags. Asynchronous — returns a task_id you poll with get_task; generation usually takes 30-120 seconds and normally yields two variations.

Parameters9

prompt	string	required	In simple mode (custom=false) a description of the song, e.g. 'a dreamy lo-fi track about late-night trains'. In custom mode (custom=true) the actual lyrics, with section markers like [Verse] and [Chorus].
custom	boolean	optional	false (default) lets the model write the lyrics from your description; true means prompt contains lyrics you wrote and you should also set title and tags.
title	string	optional	Song title. Used in custom mode.
tags	string	optional	Comma-separated style tags, e.g. 'pop, upbeat, guitar'. Max 200 characters.
negative_tags	string	optional	Styles to avoid, e.g. 'heavy metal, rap'.
instrumental	boolean	optional	Generate without vocals.
model	string	optional	Suno model version, e.g. chirp-v5 or chirp-v4-5-plus. Omit for the platform default.
provider	string	optional	Music backend: 'suno' (default) or 'producer'.
wait_seconds	null \| integer	optional	Poll server-side for up to this many seconds (max 240) and return finished audio if it completes in time. Omit to return a task_id immediately.

Raw schema

{
  "type": "object",
  "properties": {
    "prompt": {
      "type": "string",
      "description": "In simple mode (custom=false) a description of the song, e.g. 'a dreamy lo-fi track about late-night trains'. In custom mode (custom=true) the actual lyrics, with section markers like [Verse] and [Chorus]."
    },
    "custom": {
      "type": "boolean",
      "description": "false (default) lets the model write the lyrics from your description; true means prompt contains lyrics you wrote and you should also set title and tags."
    },
    "title": {
      "type": "string",
      "description": "Song title. Used in custom mode."
    },
    "tags": {
      "type": "string",
      "description": "Comma-separated style tags, e.g. 'pop, upbeat, guitar'. Max 200 characters."
    },
    "negative_tags": {
      "type": "string",
      "description": "Styles to avoid, e.g. 'heavy metal, rap'."
    },
    "instrumental": {
      "type": "boolean",
      "description": "Generate without vocals."
    },
    "model": {
      "type": "string",
      "description": "Suno model version, e.g. chirp-v5 or chirp-v4-5-plus. Omit for the platform default."
    },
    "provider": {
      "type": "string",
      "description": "Music backend: 'suno' (default) or 'producer'."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Poll server-side for up to this many seconds (max 240) and return finished audio if it completes in time. Omit to return a task_id immediately."
    }
  },
  "required": [
    "prompt"
  ],
  "additionalProperties": false
}

generate_video

Generate a video from a text prompt, optionally driven by reference images (image-to-video, first/last frame). This is asynchronous: it returns a task_id you poll with get_task(platform='video'). Generation usually takes 30-180 seconds. Pass wait_seconds to have the server poll for you. Video generation is the most expensive capability here — confirm the prompt with the user before spending on retries.

Parameters9

model	string	required	Exact model name, e.g. doubao-seedance-2-0-260128, veo-3.1-quality or viduq3-pro. Call list_models with category 'video' if unsure.
prompt	string	required	Description of the video to generate.
images	null \| array	optional	Optional reference image URLs. A single image is used as the first frame; use image_roles to control multiple.
duration	null \| integer	optional	Clip length in seconds. Model-dependent, typically 4-15; an unsupported value is rejected with a message naming the supported ones. Omit for the model default.
resolution	string	optional	Output resolution: 480p, 720p (widest compatibility) or 1080p. Model-dependent.
ratio	string	optional	Aspect ratio, e.g. 16:9, 9:16, 1:1, 21:9 or adaptive. Which values a model accepts varies; an unsupported one is rejected with a message naming the valid ones.
generate_audio	null \| boolean	optional	Generate a synchronised soundtrack. Only some models support this.
image_roles	null \| array	optional	Role of each entry in images, positionally: first_frame, last_frame or reference_image.
wait_seconds	null \| integer	optional	Poll server-side for up to this many seconds (max 240) and return the finished video if it completes in time. Omit to return a task_id immediately.

Raw schema

{
  "type": "object",
  "properties": {
    "model": {
      "type": "string",
      "description": "Exact model name, e.g. doubao-seedance-2-0-260128, veo-3.1-quality or viduq3-pro. Call list_models with category 'video' if unsure."
    },
    "prompt": {
      "type": "string",
      "description": "Description of the video to generate."
    },
    "images": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Optional reference image URLs. A single image is used as the first frame; use image_roles to control multiple."
    },
    "duration": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Clip length in seconds. Model-dependent, typically 4-15; an unsupported value is rejected with a message naming the supported ones. Omit for the model default."
    },
    "resolution": {
      "type": "string",
      "description": "Output resolution: 480p, 720p (widest compatibility) or 1080p. Model-dependent."
    },
    "ratio": {
      "type": "string",
      "description": "Aspect ratio, e.g. 16:9, 9:16, 1:1, 21:9 or adaptive. Which values a model accepts varies; an unsupported one is rejected with a message naming the valid ones."
    },
    "generate_audio": {
      "type": [
        "null",
        "boolean"
      ],
      "description": "Generate a synchronised soundtrack. Only some models support this."
    },
    "image_roles": {
      "type": [
        "null",
        "array"
      ],
      "items": {
        "type": "string"
      },
      "description": "Role of each entry in images, positionally: first_frame, last_frame or reference_image."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Poll server-side for up to this many seconds (max 240) and return the finished video if it completes in time. Omit to return a task_id immediately."
    }
  },
  "required": [
    "model",
    "prompt"
  ],
  "additionalProperties": false
}

get_balance

Report the remaining and used balance for this CCAPI key. Useful before starting an expensive batch of generations, or to explain a quota failure to the user.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "additionalProperties": false
}

get_task

Check the status of an asynchronous generation task submitted by generate_video, generate_music, generate_lyrics, extend_music, or generate_image with async=true. Pass the platform and task_id exactly as they were returned. Status is one of queued, in_progress, completed or failed; poll every few seconds until it settles, or pass wait_seconds to have the server wait for you.

Parameters3

platform	string	required	Platform the task belongs to, exactly as returned by the submit tool: image, video, suno or producer.
task_id	string	required	Task identifier returned by the submit tool.
wait_seconds	null \| integer	optional	Poll server-side for up to this many seconds (max 240) and return once the task finishes. Omit for a single immediate status check.

Raw schema

{
  "type": "object",
  "properties": {
    "platform": {
      "type": "string",
      "description": "Platform the task belongs to, exactly as returned by the submit tool: image, video, suno or producer."
    },
    "task_id": {
      "type": "string",
      "description": "Task identifier returned by the submit tool."
    },
    "wait_seconds": {
      "type": [
        "null",
        "integer"
      ],
      "description": "Poll server-side for up to this many seconds (max 240) and return once the task finishes. Omit for a single immediate status check."
    }
  },
  "required": [
    "platform",
    "task_id"
  ],
  "additionalProperties": false
}

list_models

List the AI models this CCAPI key can actually call, with their capability category and the MCP tool that drives them. Call this before generating anything if you are unsure a model name is valid — availability depends on the key's group and changes over time. Never guess model names.

Parameters2

category	string	optional	Filter by capability. One of: text, image, video, music, embedding, other. Omit to list every model this key can use.
search	string	optional	Case-insensitive substring match on the model name, e.g. 'claude' or 'seedance'.

Raw schema

{
  "type": "object",
  "properties": {
    "category": {
      "type": "string",
      "description": "Filter by capability. One of: text, image, video, music, embedding, other. Omit to list every model this key can use."
    },
    "search": {
      "type": "string",
      "description": "Case-insensitive substring match on the model name, e.g. 'claude' or 'seedance'."
    }
  },
  "additionalProperties": false
}

upscale_image

Increase the resolution of an existing image 2x with ccapi-upscale-v1. Input must be between 256x256 and 1024x1024 and under 5 MB; for larger inputs, regenerate with a high-resolution model instead.

Parameters3

image	string	required	The image to upscale, as an HTTPS URL, data URL, or raw base64. Width and height must each be 256-1024 px and the file at most 5 MB.
model_quality	string	optional	Upscale quality hint: HQ, MQ (default) or LQ.
response_format	string	optional	'url' (default) or 'b64_json'.

Raw schema

{
  "type": "object",
  "properties": {
    "image": {
      "type": "string",
      "description": "The image to upscale, as an HTTPS URL, data URL, or raw base64. Width and height must each be 256-1024 px and the file at most 5 MB."
    },
    "model_quality": {
      "type": "string",
      "description": "Upscale quality hint: HQ, MQ (default) or LQ."
    },
    "response_format": {
      "type": "string",
      "description": "'url' (default) or 'b64_json'."
    }
  },
  "required": [
    "image"
  ],
  "additionalProperties": false
}

CCAPI

MCP Server: ai.ccapi/mcp

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

chat_completion

edit_image

extend_music

generate_image

generate_lyrics

generate_music

generate_video

get_balance

get_task

list_models

upscale_image

Install

Remote endpoint