Integration
Connect OpenAI and Runway
When New batch fires in OpenAI, your agent runs Animate Character From Video in Runway, or New Avatar in Runway to Create message in OpenAI. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want OpenAI and Runway to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Grok
Open grok.com/connectors, choose New Connector, then Custom, and paste the address. Grok signs you in in your browser.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Example flows
What OpenAI and Runway can do together
From OpenAI to Runway
When New batch in OpenAI
then Animate Character From Video in Runway
When New file in OpenAI
then Convert Image to Video in Runway
From Runway to OpenAI
When New Avatar in Runway
then Create message in OpenAI
When New Voice in Runway
then Create assistant in OpenAI
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with OpenAI and Runway
Triggers and actions 7 triggers · 82 actions
Trigger
New batchList your organization's batches.
Trigger
New fileReturns a list of files.
Trigger
New modelLists the currently available models.
Trigger
New vector storeReturns a list of vector stores.
Trigger
New videoList recently generated videos for the current project.
Action
Ask docs with file searchAsks an OpenAI model a question answered from a vector store via the Responses API file_search tool, and returns just the reply text. Authenticates with this account's own OpenAI connection, unlike the platform AI Agent step which requires a platform-level system key.
Action
Cancel batchCancels an in-progress batch.
Action
Cancel runCancels a run that is in_progress.
Action
Cancel vector store file batchCancel a vector store file batch.
Action
Content moderationClassifies text for hate, harassment, self-harm, sexual, and violence categories using the Moderations API.
Action
Count input tokensReturns input token counts of the request.
Action
Create assistantCreate an assistant with a model and instructions.
Action
Create chat completionSends a list of chat messages to a model via the Chat Completions API and returns the assistant's reply.
Action
Create completionCreates a completion for the provided prompt and parameters.
Action
Create embeddingGenerates a vector embedding for input text using an embeddings model (e.g. text-embedding-3-small).
Action
Create messageCreate a message.
Action
Create runCreate a run.
Action
Creates and executes a batch from an uploaded file of requestsCreates and executes a batch from an uploaded file of requests
Action
Create threadCreate a thread.
Action
Create thread and runCreate a thread and run it in one request.
Action
Create vector storeCreate a vector store.
Action
Create vector store fileCreate a vector store file by attaching a File to a vector store.
Action
Create vector store file batchCreate a vector store file batch.
Action
Create video edit jobCreate a new video generation job by editing a source or existing generated video.
Action
Create video extensionCreate an extension of a completed video.
Action
Create video generation jobCreate a new video generation job from a prompt and optional reference assets.
Action
Create video remixCreate a remix of a completed video using a refreshed prompt.
Action
Delete assistantDelete an assistant.
Action
Delete eval runDelete an eval run.
Action
Delete fileDelete a file and remove it from all vector stores.
Action
Delete messageDeletes a message.
Action
Delete threadDelete a thread.
Action
Delete vector storeDelete a vector store.
Action
Delete vector store fileDelete a vector store file (removes from store, file itself not deleted).
Action
Delete videoPermanently delete a completed or failed video and its stored assets.
Action
Download video contentDownload the generated video bytes or a derived preview asset.
Action
Edit imageCreates an edited or extended image given one or more source images and a prompt.
Action
Generate imageGenerates an image from a text prompt using gpt-image-1 / DALL-E and returns the image URL or base64 data.
Action
Generate speechConverts text into spoken audio using a TTS model and the selected voice. Returns audio bytes.
Action
Get assistantRetrieves an assistant.
Action
Get batchRetrieves a batch.
Action
Get fileReturns information about a specific file.
Action
Get file contentReturns the contents of the specified file.
Action
Get messageRetrieve a message.
Action
Get modelRetrieves a model instance.
Action
Get runRetrieves a run.
Action
Get run stepRetrieves a run step.
Action
Get threadRetrieves a thread.
Action
Get vector storeRetrieves a vector store.
Action
Get vector store fileRetrieves a vector store file.
Action
Get vector store file batchRetrieves a vector store file batch.
Action
Get vector store file contentRetrieve the parsed contents of a vector store file.
Action
Get videoFetch the latest metadata for a generated video.
Action
List conversation itemsList all items for a conversation with the given ID.
Action
List filesLists files that have been uploaded to your OpenAI account.
Action
List messagesReturns a list of messages for a given thread.
Action
List modelsLists the models currently available to your account.
Action
List runsReturns a list of runs belonging to a thread.
Action
List run stepsReturns a list of run steps belonging to a run.
Action
List vector store file batch filesReturns a list of vector store files in a batch.
Action
List vector store filesReturns a list of vector store files.
Action
OpenAI agent messageRuns one AI agent turn on OpenAI and returns the model's reply. The turn is billed to the OpenAI account connected on this step, and the agent can call the account's AI tool automations.
Action
Retrieve responseRetrieves a previously created model response by its Response ID.
Action
Search vector storeSearch a vector store for relevant chunks based on a query and filter.
Action
Send model a messageSends a message to an OpenAI model via the Responses API and emits its response. Returns a Response ID usable as previous_response_id for multi-turn conversations.
Action
Submit tool outputs to runSubmit tool outputs when a run requires action.
Action
Transcribe audioTranscribes audio into the input language.
Action
Translate audioTranslates audio into English.
Action
Update assistantModifies an assistant.
Action
Update messageModifies a message.
Action
Update runModifies a run.
Action
Update threadModifies a thread.
Action
Update vector storeModifies a vector store.
Action
Update vector store file attributesUpdate attributes on a vector store file.
Action
Upload fileUpload a file that can be used across various endpoints.
Trigger
New AvatarTriggers when a new avatar is created in your organization.
Trigger
New VoiceTriggers when a new custom voice is created in your organization.
Action
Animate Character From VideoStarts a task that transfers the performance in a reference video onto a character image or video. Returns the task ID.
Action
Cancel TaskCancels a running generation task, or deletes a finished one.
Action
Convert Image to VideoStarts a task that animates an image into a video. Returns the task ID to check with Get Task Details.
Action
Generate Image From TextStarts a task that generates an image from a text prompt, optionally guided by a reference image. Returns the task ID.
Action
Generate Sound EffectStarts a task that generates a sound effect from a text description. Returns the task ID.
Action
Generate Speech From TextStarts a task that turns text into spoken audio. Returns the task ID.
Action
Generate Video From TextStarts a task that generates a video from a text prompt. Returns the task ID to check with Get Task Details.
Action
Get Organization InfoReturns your organization's tier, remaining credit balance and current usage.
Action
List VoicesReturns the custom voices in your organization.
Action
Retrieve Credit UsageReturns your organization's daily credit usage by model over a date range.
Action
Transform Video to VideoStarts a task that restyles or edits an existing video from a text prompt. Returns the task ID.
Action
Upscale VideoStarts a task that upscales a video to a higher resolution. Returns the task ID.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from OpenAI
OpenAI to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
OpenAI to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
OpenAI to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
OpenAI to StripeStripe is a payment processing platform for online businesses.
OpenAI to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
OpenAI to PipedrivePipedrive is a sales CRM and pipeline management tool.
More into Runway
HubSpot to RunwayHubSpot is your all-in-one stop for all of your marketing software needs.
Google Sheets to RunwayGoogle Sheets is Google's online spreadsheet app for creating, editing and sharing spreadsheets.
Gmail to RunwayGmail is Google’s email service, featuring spam protection, search functions, and seamless integration with...
Google Calendar to RunwayGoogle Calendar is a time management tool providing scheduling features, event reminders, and integration...
Google Drive to RunwayGoogle Drive is a cloud storage solution for uploading, sharing, and collaborating on files across devices...
Mailchimp to RunwayMailchimp marketing automation and email platform.
Questions
OpenAI and Runway, answered
What can start an automation from OpenAI?
Any of OpenAI's 5 triggers in the catalog, including New batch, New file, New model and New vector store. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Runway when something happens in OpenAI?
Any of Runway's 12 actions, including Animate Character From Video, Convert Image to Video, Generate Image From Text and Generate Sound Effect. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Runway to OpenAI?
Yes. When something happens in Runway, your agent can act in OpenAI too. This page covers both directions: Runway's triggers and OpenAI's actions are listed here as well.
Do I have to build a connector for OpenAI or Runway?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use OpenAI and Runway without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.