Integration

Higgsfield integration

The Higgsfield key is a PAIR: create a key id and a key secret at cloud.higgsfield.ai and enter them joined by a colon, as KEY_ID:KEY_SECRET. Entering only the key id returns 401 Invalid credentials. Higgsfield is a single API in front of most of the current generative video and image models: Google Veo 3.1, OpenAI Sora 2, Kuaishou Kling, ByteDance Seedance, MiniMax Hailuo, Alibaba Wan 2.5, FLUX.1 Kontext, Nano Banana and Reve, alongside Higgsfield's own DoP, Soul and Popcorn models. One key reaches all of them and they share one request shape. Every generation is asynchronous: the endpoint submits the job and waits for it, then returns the finished media as HTTPS URLs that Higgsfield keeps for at least seven days. Input media is always a public HTTPS URL, so use create_upload_url for a file that is not already hosted. The account limit is CONCURRENCY, not a request rate: too many generations in flight at once is refused with 400 and the message "Maximum number of concurrent requests (N) has been reached", which means wait for one to finish, not fix the request. 403 means the account is out of credits, and 423 or 503 means the chosen model is temporarily unavailable to it. Failed and moderation-rejected (nsfw) generations are never charged, and a cancellation is refunded only when it lands before processing has started.

Connect Higgsfield How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Higgsfield.Built from the 51 Higgsfield tools below, on the connection you add once.

Common Higgsfield use cases

Animate a product photo into a short ad
Turn a generated still into a moving shot
Interpolate between a start and an end frame for a controlled transition
Produce vertical clips for social from existing artwork
Generate a marketing clip from a written brief
Produce b-roll for a montage without a shoot
Storyboard a scene as a moving reference
Make vertical short-form video from a script line
Generate product or editorial imagery from a brief
Produce thumbnails and social visuals at scale

What you can do with Higgsfield

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Image to video, 24 operations

create_dop_liteCreate dop litePOSTHiggsfield DoP: generate a video from a prompt and an input image
create_dop_standardCreate dop standardPOSTHiggsfield DoP: generate a video from a prompt and an input image
create_dop_turboCreate dop turboPOSTHiggsfield DoP: generate a video from a prompt and an input image
create_hailuo_02_pro_image_to_videoCreate hailuo 02 pro image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_hailuo_02_standard_image_to_videoCreate hailuo 02 standard image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_hailuo_2_3_fast_pro_image_to_videoCreate hailuo 2 3 fast pro image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_hailuo_2_3_fast_standard_image_to_videoCreate hailuo 2 3 fast standard image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_hailuo_2_3_pro_image_to_videoCreate hailuo 2 3 pro image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_hailuo_2_3_standard_image_to_videoCreate hailuo 2 3 standard image to videoPOSTMiniMax Hailuo: animate a still image into a video
create_kling_video_v2_1_master_image_to_videoCreate kling video v2 1 master image to videoPOSTKuaishou Kling: animate a still image into a video
create_kling_video_v2_1_pro_image_to_videoCreate kling video v2 1 pro image to videoPOSTKuaishou Kling: animate a still image into a video
create_kling_video_v2_1_standard_image_to_videoCreate kling video v2 1 standard image to videoPOSTKuaishou Kling: animate a still image into a video
create_kling_video_v2_5_turbo_pro_image_to_videoCreate kling video v2 5 turbo pro image to videoPOSTKuaishou Kling: animate a still image into a video
create_kling_video_v2_5_turbo_standard_image_to_videoCreate kling video v2 5 turbo standard image to videoPOSTKuaishou Kling: animate a still image into a video
create_seedance_v1_lite_image_to_videoCreate seedance v1 lite image to videoPOSTByteDance Seedance 1.0: animate a still image into a video
create_seedance_v1_pro_fast_image_to_videoCreate seedance v1 pro fast image to videoPOSTByteDance Seedance 1.0: animate a still image into a video
create_sora_2_image_to_videoCreate sora 2 image to videoPOSTOpenAI Sora 2: animate a still image into a video
create_sora_2_image_to_video_proCreate sora 2 image to video proPOSTOpenAI Sora 2: animate a still image into a video
create_veo3_1_fast_first_last_frame_to_videoCreate veo3 1 fast first last frame to videoPOSTGoogle Veo 3.1: generate a video that starts on one image and ends on another
create_veo3_1_fast_image_to_videoCreate veo3 1 fast image to videoPOSTGoogle Veo 3.1: animate a still image into a video
create_veo3_1_first_last_frame_to_videoCreate veo3 1 first last frame to videoPOSTGoogle Veo 3.1: generate a video that starts on one image and ends on another
create_veo3_1_image_to_videoCreate veo3 1 image to videoPOSTGoogle Veo 3.1: animate a still image into a video
create_veo3_1_reference_to_videoCreate veo3 1 reference to videoPOSTGoogle Veo 3.1: generate a video that borrows subject and style from reference images
create_wan_25_preview_image_to_videoCreate wan 25 preview image to videoPOSTAlibaba Wan 2.5: animate a still image into a video

Text to video, 13 operations

create_hailuo_02_pro_text_to_videoCreate hailuo 02 pro text to videoPOSTMiniMax Hailuo: generate a video from a text prompt alone
create_hailuo_02_standard_text_to_videoCreate hailuo 02 standard text to videoPOSTMiniMax Hailuo: generate a video from a text prompt alone
create_hailuo_2_3_pro_text_to_videoCreate hailuo 2 3 pro text to videoPOSTMiniMax Hailuo: generate a video from a text prompt alone
create_hailuo_2_3_standard_text_to_videoCreate hailuo 2 3 standard text to videoPOSTMiniMax Hailuo: generate a video from a text prompt alone
create_kling_video_v2_1_master_text_to_videoCreate kling video v2 1 master text to videoPOSTKuaishou Kling: generate a video from a text prompt alone
create_kling_video_v2_5_turbo_pro_text_to_videoCreate kling video v2 5 turbo pro text to videoPOSTKuaishou Kling: generate a video from a text prompt alone
create_seedance_v1_lite_text_to_videoCreate seedance v1 lite text to videoPOSTByteDance Seedance 1.0: generate a video from a text prompt alone
create_seedance_v1_pro_fast_text_to_videoCreate seedance v1 pro fast text to videoPOSTByteDance Seedance 1.0: generate a video from a text prompt alone
create_sora_2_text_to_videoCreate sora 2 text to videoPOSTOpenAI Sora 2: generate a video from a text prompt alone
create_sora_2_text_to_video_proCreate sora 2 text to video proPOSTOpenAI Sora 2: generate a video from a text prompt alone
create_veo3_1Create veo3 1POSTGoogle Veo 3.1: generate a video from a text prompt alone
create_veo3_1_fastCreate veo3 1 fastPOSTGoogle Veo 3.1: generate a video from a text prompt alone
create_wan_25_preview_text_to_videoCreate wan 25 preview text to videoPOSTAlibaba Wan 2.5: generate a video from a text prompt alone

Text to image, 6 operations

create_flux_pro_kontext_max_text_to_imageCreate flux pro kontext max text to imagePOSTFLUX.1 Kontext [max]: generate an image from a text prompt
create_nano_bananaCreate nano bananaPOSTNano Banana: generate an image from a text prompt
create_popcorn_autoCreate popcorn autoPOSTHiggsfield Popcorn: generate an image from a text prompt
create_reve_text_to_imageCreate reve text to imagePOSTReve: generate an image from a text prompt
create_soul_characterCreate soul characterPOSTHiggsfield Soul: generate an image from a text prompt
create_soul_standardCreate soul standardPOSTHiggsfield Soul: generate an image from a text prompt

Image edit, 5 operations

create_reve_editCreate reve editPOSTReve: edit an existing image from a text instruction
create_reve_fast_editCreate reve fast editPOSTReve: edit an existing image from a text instruction
create_reve_fast_remixCreate reve fast remixPOSTReve: generate a new image by combining several reference images
create_reve_remixCreate reve remixPOSTReve: generate a new image by combining several reference images
create_soul_referenceCreate soul referencePOSTHiggsfield Soul: generate an image from a prompt and reference images

Request, 2 operations

cancel_requestCancel requestPOSTCancel a queued Higgsfield generation request and refund it.
get_request_statusGet request statusGETRead the status and output of one Higgsfield generation request.

Upload url, 1 operation

create_upload_urlCreate upload urlPOSTCreate a presigned URL for uploading model input media to Higgsfield.

Use Higgsfield from Claude Code, Cursor or Codex

Connect Higgsfield in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Higgsfield operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Higgsfield

Create your workspace
Sign up free. Nothing to install.
Connect Higgsfield once
Add your Higgsfield connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Higgsfield integration FAQ

What can you do with the Higgsfield integration?

LiveContext exposes 51 operations on Higgsfield, covering image to video, text to video, text to image and image edit. Common uses include Animate a product photo into a short ad, Turn a generated still into a moving shot and Interpolate between a start and an end frame for a controlled transition.