Contract
input_schema.json
{
"type": "object",
"properties": {},
"additionalProperties": false
}output_schema.json
{
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"models": {
"type": "array",
"items": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The model's exact, versioned identifier, e.g. 'gpt-5.5-instant-2026-05-28' or 'gpt-5.2-high-no-system-prompt-text'. Frequently longer than `displayName`; the stable name of the precise model variant."
},
"rank": {
"type": "number",
"description": "The model's overall leaderboard position. The key is ABSENT (never null) for models not on the leaderboard -- e.g. the first-listed model of the real capture carries no rank -- so check for presence rather than a value before treating a model as ranked."
},
"publicName": {
"type": "string",
"description": "The model's product name as shown in the arena's public list. Usually the same as `displayName`, but a codename (e.g. 'Max', 'pteronura') when the model competes anonymously -- confirmed against real entries."
},
"displayName": {
"type": "string",
"description": "The human-facing model label a user sees, e.g. 'gpt-5.5-instant', 'gemma-4-31b'. May differ from `publicName` (a codename) and from `name` (a versioned slug)."
},
"capabilities": {
"type": "object",
"properties": {
"inputCapabilities": {
"type": "object",
"properties": {
"file": {
"type": "boolean",
"description": "The model accepts document/file input. 'true' on every model observed with file support."
},
"text": {
"type": "boolean",
"description": "The model accepts text input. 'true' on every model in the capture."
},
"image": {
"type": [
"boolean",
"object"
],
"properties": {
"multipleImages": {
"type": "boolean",
"description": "Whether several images can be passed in one input."
},
"requiresUpload": {
"type": "boolean",
"description": "Whether the image must be uploaded rather than referenced."
}
},
"description": "The model accepts image input. Usually a bare boolean ('true'/'false'), but observed as a details object -- with the flags below -- where the upstream surfaces them; both shapes appear in the same real capture. An absent key means no image input.",
"additionalProperties": false
},
"video": {
"type": [
"boolean",
"object"
],
"properties": {
"required": {
"type": "boolean",
"description": "Whether the model requires video input to respond."
}
},
"description": "The model accepts video input. Usually a bare boolean, but observed once as an object with the `required` flag; an absent key means no video input.",
"additionalProperties": false
}
},
"additionalProperties": false
},
"outputCapabilities": {
"type": "object",
"properties": {
"web": {
"type": "boolean",
"description": "The model can draw on web results when answering."
},
"text": {
"type": "boolean",
"description": "The model produces text output. 'true' on every model in the capture."
},
"image": {
"type": "object",
"properties": {
"aspectRatios": {
"type": "array",
"items": {
"type": "string"
},
"description": "Supported output aspect ratios as strings, e.g. '1:1' -- the only value observed in the real capture."
}
},
"description": "Image-output details. Only present for the models that carry them; the single real observation was an aspect-ratio constraint list.",
"additionalProperties": false
},
"video": {
"type": "boolean",
"description": "The model generates video output (e.g. the veo models)."
},
"search": {
"type": "boolean",
"description": "The model can perform web search as part of a response."
}
},
"additionalProperties": false
}
},
"additionalProperties": false
},
"organization": {
"type": "string",
"description": "The organization that publishes the model, e.g. 'google', 'openai', 'anthropic'. A public company or lab name."
},
"rankByModality": {
"type": "object",
"properties": {
"chat": {
"type": "number",
"description": "Rank in the chat arena; 9007199254740991 (2^53 - 1) = not ranked here."
},
"image": {
"type": "number",
"description": "Rank in the image-arena; 9007199254740991 (2^53 - 1) = not ranked here."
},
"video": {
"type": "number",
"description": "Rank in the video arena; 9007199254740991 (2^53 - 1) = not ranked here."
},
"search": {
"type": "number",
"description": "Rank in the search arena; 9007199254740991 (2^53 - 1) = not ranked here."
},
"webdev": {
"type": "number",
"description": "Rank in the web-development arena; 9007199254740991 (2^53 - 1) = not ranked here."
}
},
"description": "Per-modality leaderboard positions. Only the modalities a model participates in appear as keys. The value 9007199254740991 (2^53 - 1) is the upstream's sentinel for 'not ranked in this modality' -- it appeared for all five modalities on the first-listed model of the real capture, while ranked models show small integers (e.g. chat: 31, webdev: 64).",
"additionalProperties": false
},
"userSelectable": {
"type": "boolean",
"description": "Whether the model can be selected for direct interaction. 'true' for every one of the 298 models in the real capture; a 'false' value (unobserved) would mean the model is listed in the catalog but not directly selectable."
}
},
"additionalProperties": false
},
"description": "Every model in the catalog (298 entries on the real calibration call), in the upstream's own listing order."
}
},
"additionalProperties": false
},
"status": {
"type": "string",
"description": "'success' on the real calibration call."
}
},
"description": "The model catalog, as returned at routing.responseResultPath ($.output).",
"additionalProperties": false
}Pricing
Every real charge, itemised. A model that quietly omits one is a slow financial leak, so nothing here is rolled up, and a charge that only applies to some inputs says so rather than being added in.
Prices in this catalog are the provider's own list price, not your bill: Omnial MCP charges provider cost plus a platform markup on top, so what you are charged is higher than the figure shown. For the exact amount a specific call will cost, run omnial_execute with dry_run: true; that number includes the markup and is what we hold while the call runs. It is a quote, not a cap on the charge.
| Charge | Rate |
|---|---|
Per call Flat, regardless of what comes back | $0.01365 |
- Cost basis
- Not recorded
This tool's catalog entry does not record how its final bill is determined, so we will not tell you whether its cost is fixed before the call or reported by the provider afterwards. Either way what is held is a quote rather than a cap: you are charged what the call actually costs, bounded at 2x the quote.
- Updated
- Sep 30, 2026