Contract
input_schema.json
{
"type": "object",
"properties": {},
"additionalProperties": false
}output_schema.json
{
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"endpoints": {
"type": "array",
"items": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The endpoint's internal UUID, e.g. 'c9cbf21c-31b5-4147-a69f-a8a1d617b258' -- confirmed a UUID on every one of 1151 entries observed, not a phone number or any other personal identifier despite superficially digit-and-dash-heavy."
},
"host": {
"type": "object",
"properties": {
"logo": {
"type": "string",
"description": "Relative logo asset filename, e.g. 'novita_small.svg' -- not a fetchable URL."
},
"name": {
"type": "string",
"description": "Hosting provider's public company name, e.g. 'Novita', 'Google'."
},
"slug": {
"type": "string"
},
"color": {
"type": "string",
"description": "Hex color, e.g. '#5348EC'."
}
},
"additionalProperties": true
},
"label": {
"type": "string",
"description": "Human-readable model + variant label, e.g. 'GPT-5.2 Codex (xhigh)'."
},
"model": {
"type": "object",
"properties": {
"hle": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"lcr": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"gpqa": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"slug": {
"type": "string"
},
"tau2": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"aime25": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"critpt": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"creator": {
"type": "object",
"properties": {
"logo": {
"type": "string",
"description": "Relative logo asset filename -- not a fetchable URL."
},
"name": {
"type": "string",
"description": "Model creator/lab's public company name, e.g. 'Z AI', 'Google' -- not a person's identity."
}
},
"additionalProperties": true
},
"ifbench": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"mmmuPro": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"scicode": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"briefcase": {
"type": [
"object",
"string"
],
"description": "Either an object `{ elo: number }` or, on some endpoints, the literal STRING \"null\" (not a JSON null) -- an upstream data-quality quirk confirmed directly against the real fixture, not assumed."
},
"harveyLab": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"sizeClass": {
"type": [
"string",
"null"
],
"description": "e.g. 'medium', 'large'; null when not classified for this model."
},
"apexAgents": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"deprecated": {
"type": "boolean"
},
"itbenchSre": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"tauBanking": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"omniscience": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"isOpenWeights": {
"type": "boolean"
},
"livecodebench": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"reasoningModel": {
"type": "boolean"
},
"automationBench": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"gdpvalNormalized": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"terminalbenchV21": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"terminalbenchV40": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"intelligenceIndex": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"terminalbenchHard": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"omniscienceAccuracy": {
"type": [
"number",
"string"
],
"description": "Benchmark score, or the literal STRING \"null\" on some endpoints (not a JSON null) -- an upstream data-quality quirk, confirmed directly against the real fixture."
},
"omniscienceNonHallucination": {
"type": [
"number",
"null"
],
"description": "Benchmark score; null when not evaluated for this model."
},
"intelligenceIndexIsEstimated": {
"type": "boolean"
}
},
"description": "Static model metadata plus ~20 benchmark score fields. Most benchmark fields were observed null for at least one endpoint in the one real call (a model not evaluated on that particular benchmark) -- treat every benchmark field as nullable, not guaranteed populated.",
"additionalProperties": true
},
"pricing": {
"type": "object",
"properties": {
"priceClass": {
"type": [
"string",
"null"
],
"description": "e.g. 'low', 'medium', 'high'; null when not classified for this endpoint."
},
"costPerTask": {
"type": [
"number",
"string"
],
"description": "USD, or the literal STRING \"null\" on some endpoints (not a JSON null) -- an upstream data-quality quirk, confirmed directly against the real fixture."
},
"cacheHitPrice": {
"type": [
"number",
"null"
]
},
"cacheWritePrice": {
"type": [
"number",
"null"
]
},
"price1mInputTokens": {
"type": "number",
"description": "USD per 1M input tokens."
},
"price1mOutputTokens": {
"type": "number",
"description": "USD per 1M output tokens."
}
},
"additionalProperties": true
},
"features": {
"type": "object",
"properties": {
"jsonMode": {
"type": "boolean"
},
"functionCalling": {
"type": "boolean"
},
"openaiCompatible": {
"type": "boolean"
},
"contextWindowTokens": {
"type": "number"
}
},
"additionalProperties": true
},
"hostApiId": {
"type": "string",
"description": "The hosting provider's own API identifier for this model, e.g. 'zai-org/glm-4.5v' or 'gpt-5.2-codex' -- an API path/slug, not personal data."
},
"performance": {
"type": [
"object",
"string"
],
"properties": {
"medianReasoningTimeSeconds": {
"type": [
"number",
"null"
],
"description": "Null for a non-reasoning model or when not measured."
},
"medianOutputTokensPerSecond": {
"type": "number"
},
"medianTimeToFirstTokenSeconds": {
"type": "number"
},
"quartile25OutputTokensPerSecond": {
"type": "number"
},
"quartile75OutputTokensPerSecond": {
"type": "number"
},
"medianEndToEndResponseTimeSeconds": {
"type": "number"
},
"percentile05OutputTokensPerSecond": {
"type": "number"
},
"percentile95OutputTokensPerSecond": {
"type": "number"
},
"quartile25TimeToFirstTokenSeconds": {
"type": "number"
},
"quartile75TimeToFirstTokenSeconds": {
"type": "number"
},
"medianTimeToFirstAnswerTokenSeconds": {
"type": "number"
},
"percentile05TimeToFirstTokenSeconds": {
"type": "number"
},
"percentile95TimeToFirstTokenSeconds": {
"type": "number"
}
},
"description": "Speed/latency percentiles for this endpoint, or the literal STRING \"null\" on some endpoints (not a JSON null) when no timing data was collected -- an upstream data-quality quirk, confirmed directly against the real fixture.",
"additionalProperties": true
}
},
"additionalProperties": true
},
"description": "1151 provider-model endpoint entries on the one real call observed."
}
},
"additionalProperties": true
},
"status": {
"type": "string",
"description": "'success' on the one real call observed."
}
},
"description": "The leaderboard payload, as returned at routing.responseResultPath ($.output).",
"additionalProperties": true
}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 23, 2026