Skip to main content
Glama

Runway MCP Server by useapi.net (third-party)

Create images (all models)

runway_create_image

Generate images with any of the 13 image models on Runway (FLUX 3, FLUX.2 Max / Klein, Nano Banana / 2 / 2 Lite / Pro, GPT Image 1.5 / 1 Mini / 2, Seedream 5, Gen-4, Gen-4 Turbo) from a prompt and up to 14 reference image assets, 1 or 4 images per task. The general image tool; runway_create_frames is the older Frames route (1080p, up to 3 references). Waits up to ~50 s, then returns each image's url and assetId plus the first image inline, the failure reason or the taskId for runway_get_task. Uses credits, or none with exploreMode (not flux-3). POST /images/create.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model": "<model>"
    },
    "name": "runway_create_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNogen4, gen4-turbo, flux-2-max and flux-2-klein only: seed, 1-4294967294.
waitNoWait up to ~50 s for the task to finish (default true); false returns the taskId at once.
emailNoThe Runway account to run it on: its email from runway_list_accounts. Omit it with reference assets (the account that holds them runs the task) or to let the API pick one of your accounts.
modelYesThe image model. References and prompt limits: flux-3 (0-10 refs, prompt required, 4000, one image), flux-2-max (0-8) / flux-2-klein (0-4, prompt 4000, cite refs as "image 1"), nano-banana (0-3), nano-banana-2, nano-banana-2-lite, nano-banana-pro (0-14; prompt 5000), gpt-image-1-5, gpt-image-1-mini (0-1), gpt-image-2 (0-14; prompt required, 32000), seedream-5 (0-14, 4000), gen4 (0-3), gen4-turbo (1-3 required; prompt 1000).
styleNogen4 and gen4-turbo only: a style preset.
maxJobsNoOverride the account's maxJobs (Runway tasks at once) for this request, 1-10. Default: the account's own setting.
qualityNogpt-image-2 only: low, medium or high (default).
replyRefNoYour own reference id, stored and returned with the task.
replyUrlNoA callback URL the API calls with the task (the runway_get_task shape) when it completes or fails. Default: the replyUrl of your useapi.net account.
diversityNogen4 only: aesthetic range, 1-5; higher varies the images in a set more. With reference images the value is ignored: 2 is always used; without, nothing is sent when omitted.
num_imagesNoImages per task: 1 (default) or 4; flux-3 makes 1.
resolutionNoPer model: flux-3 1K (default), 2K, 4K, 0.5K, 0.75K; flux-2-max 1K (default), 2K, 4K, 0.6MP; flux-2-klein 1K (default), 2K, 0.6MP; gpt-image-2, nano-banana-2, nano-banana-pro 1K (default), 2K, 4K; seedream-5 2K (default), 3K; gen4 1080p (default), 720p; gen4-turbo 1080p. Not taken by nano-banana, nano-banana-2-lite, gpt-image-1-5, gpt-image-1-mini.
exploreModeNoExplore Mode: true spends no credits and runs at lower priority; only for accounts on a Runway Unlimited plan; not on flux-3. Omit or false: Credits Mode.
text_promptNoWhat the image shows. Required by flux-3, gpt-image-1-5, gpt-image-1-mini and gpt-image-2. Max length per model under model. On gen4, seedream-5 and Nano Banana models @IMG_1, @IMG_2 cite the reference images.
aspect_ratioNoImage shape. Default auto (the model picks) on nano-banana, nano-banana-pro, nano-banana-2, nano-banana-2-lite, flux-3, else 16:9. gpt-image-1-5, gpt-image-1-mini do not take 16:9 (1:1, 3:2, 2:3 only): always set aspect_ratio there; seedream-5: no 4:5, 5:4, 9:21; Nano Banana: no 9:21; 2:1, 1:2, 7:5, 5:7 flux-3 only.
imageAssetId1NoimageAssetId1, reference image 1 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId2NoimageAssetId2, reference image 2 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId3NoimageAssetId3, reference image 3 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId4NoimageAssetId4, reference image 4 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId5NoimageAssetId5, reference image 5 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId6NoimageAssetId6, reference image 6 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId7NoimageAssetId7, reference image 7 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId8NoimageAssetId8, reference image 8 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId9NoimageAssetId9, reference image 9 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId10NoimageAssetId10, reference image 10 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId11NoimageAssetId11, reference image 11 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId12NoimageAssetId12, reference image 12 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId13NoimageAssetId13, reference image 13 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).
imageAssetId14NoimageAssetId14, reference image 14 (fill slots in order; the count per model is under model): an assetId from runway_upload_asset, runway_list_assets or a finished task (runway_get_task artifacts).

Schema Changelog

Changes observed during successful MCP inspections.

No schema history has been recorded yet.

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Goes well beyond the annotations by disclosing the ~50 s wait window and the wait=false fast path, the exact return payload (urls, assetIds, first image inline, failure reason, taskId), the credit cost and exploreMode credit-free behavior, and the underlying POST /images/create. The mutation semantics align with readOnlyHint=false and destructiveHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One dense paragraph that is front-loaded with purpose, then routing, then return behavior and cost. It is efficient overall, though enumerating all 13 model names duplicates the model enum and lengthens the lead sentence.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 29-parameter, no-output-schema generation tool, the description covers the essentials: what it returns, how waiting works, credit implications, the account/asset interaction, and where to go on failure. Nothing an agent needs before calling it is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so per-model limits, enum constraints, and slot ordering are already documented in the schema. The description restates the headline facts (up to 14 reference assets, 1 or 4 images per task, prompt plus model) but adds little interpretation beyond that, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Generate images") and pins down scope with the exact model roster and reference-image/num-images limits. It explicitly differentiates itself from the sibling route runway_create_frames, so an agent can choose without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the alternative (runway_create_frames as the older Frames route with 1080p and up to 3 references) and gives the credit/exploreMode tradeoff plus the taskId handoff to runway_get_task. It stops short of a full when-not-to-use statement for the other generation siblings, but the general-vs-frames routing is explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources