Skip to main content
Glama
Sign In

AirGallery

by com.airgallery
OverviewDiscussionsAdmin

create_image

Create or transform an image using AirGallery's core multi-modal image pipeline (powers the Create page). Accepts up to 5 reference images plus a custom prompt and/or style preset, and supports multiple image models. Every model accepts reference images. Returns { image }. Cost depends on the model, in credits: nano-banana-2 3, nano-banana-pro 6, nano-banana-2-lite 2, nano-banana 3, gpt-image-2.6-flare 8, gpt-image-2.6-sunburst 8, gpt-image-2.5-flare 8, gpt-image-2.5-sunburst 8, gpt-image 8, gpt-image-mini 3, flux-3 3, flux-3-klein 1, mai-image-2.6 3, grok-imagine-2 4, seedream-5-pro 2, muse-image 1, minimax-h3 2, recraft-v4.1 2. Requires 'ai' scope.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoImage model: 'nano-banana-2' (Gemini 3.1 Flash Image, default), 'nano-banana-pro' (Gemini 3 Pro Image), 'nano-banana-2-lite' (Gemini 3.1 Flash-Lite Image, fast and cheap), 'nano-banana' (Gemini 2.5 Flash Image), 'gpt-image-2.6-flare' (OpenAI GPT Image 2.6 Flare, newest, fast), 'gpt-image-2.6-sunburst' (OpenAI GPT Image 2.6 Sunburst, careful edits, about 50s), 'gpt-image-2.5-flare' and 'gpt-image-2.5-sunburst' (OpenAI GPT Image 2.5, previous generation), 'gpt-image' (OpenAI GPT Image 2), 'gpt-image-mini' (OpenAI GPT Image 1 Mini), 'flux-3' (Black Forest Labs FLUX 3), 'flux-3-klein' (FLUX 3 Klein, fastest and cheapest), 'mai-image-2.6' (Microsoft MAI-Image 2.6, precise edits), 'grok-imagine-2' (xAI Grok Imagine Image 2.0), 'seedream-5-pro' (ByteDance Seedream 5.0 Pro, slower), 'muse-image' (Meta Muse Image 1.0, blends photos), 'minimax-h3' (MiniMax H3 Image, open weights, many references), 'recraft-v4.1' (Recraft V4.1, design and illustration; text only, no reference images).
imagesNoOptional: 0–5 reference images, each as a base64 data URI or HTTPS image URL. Omit for pure text-to-image (customPrompt is then required).
presetNoStyle preset applied to the images and/or prompt (default none).
pluginsNoOptional effects (the Create page's Plugins & Effects).
customPromptNoFree-form description of what to create (max 2000 chars). Required when no images are given.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations, the description carries the full disclosure burden and does well: it states the return shape ({ image }), the required 'ai' scope, the 5-reference cap, and per-model credit costs, plus latency hints for slow models in the schema. It is less clear on side effects such as whether the result is persisted to the user's gallery or whether a failed generation still charges credits.

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?

Purpose and input contract are front-loaded in the first two sentences, then costs. The long model-cost enumeration is dense but genuinely decision-relevant for model selection, so it earns its space; a compact cost table format would read better than a comma-separated run-on list.

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

Completeness4/5

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

No output schema exists, yet the description states the return object and the credit implications, and the schema fully documents the five parameters including nested plugin options. What remains missing is side-effect and failure behavior for a billable generation call.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description goes beyond it by mapping each model to its credit cost, which the enum descriptions do not provide, and by stating the 'ai' scope requirement. The preset and plugins parameters get no additional meaning beyond the schema.

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

Purpose4/5

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

The description leads with a specific verb and resource ('Create or transform an image') and identifies the tool as AirGallery's core multi-modal pipeline that powers the Create page, which implicitly sets it apart from single-purpose siblings like colorize_image or upscale_image. It never names those siblings or states the routing condition explicitly, so differentiation is suggestive rather than stated.

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

Usage Guidelines3/5

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

Usage is implied by the input contract: reference images for transformation, customPrompt required when no images are given, and 'every model accepts reference images' except recraft (noted in the schema). There is no explicit when-to-use-this-vs-alternatives guidance and no statement about when a specialized sibling would be preferable.

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

All AirGallery toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources