Contract
input_schema.json
{
"type": "object",
"required": [
"slug"
],
"properties": {
"slug": {
"type": "string",
"examples": [
"gpt-4o"
],
"description": "The source's own slug for the model, lowercase with hyphens. A slug the source does not know returns an empty result."
}
},
"additionalProperties": false
}output_schema.json
{
"type": "object",
"properties": {
"data": {
"type": "object",
"properties": {
"model": {
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The model's slug."
}
}
},
"providers": {
"type": "array",
"items": {
"type": "object",
"properties": {
"host": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "The host's full name."
},
"slug": {
"type": "string",
"description": "The host's slug."
},
"label": {
"type": "string",
"description": "The host's short label."
}
}
},
"slug": {
"type": "string",
"description": "The host-and-model entry's slug."
},
"model": {
"type": "object",
"properties": {
"slug": {
"type": "string",
"description": "The model's slug."
}
}
},
"pricing": {
"type": "object",
"properties": {
"cacheHitPrice": {
"type": "number",
"description": "Price per million input tokens served from the cache."
},
"price1mInputTokens": {
"type": "number",
"description": "Price per million input tokens."
},
"price1mOutputTokens": {
"type": "number",
"description": "Price per million output tokens."
},
"price1mBlended0To1To1": {
"type": "number",
"description": "Blended price per million tokens for 0 cache-hit : 1 input : 1 output tokens."
},
"price1mBlended0To3To1": {
"type": "number",
"description": "Blended price per million tokens for 0 cache-hit : 3 input : 1 output tokens."
},
"price1mBlended7To2To1": {
"type": "number",
"description": "Blended price per million tokens for 7 cache-hit : 2 input : 1 output tokens."
},
"cacheHitDiscountPercent": {
"type": "number",
"description": "The cache-hit discount on the input price, as a fraction (0.5 is half price)."
},
"price1mBlended0To100To1": {
"type": "number",
"description": "Blended price per million tokens for 0 cache-hit : 100 input : 1 output tokens."
},
"price1mBlended100To1To1": {
"type": "number",
"description": "Blended price per million tokens for 100 cache-hit : 1 input : 1 output tokens."
}
},
"description": "Prices in US dollars per million tokens."
},
"jsonMode": {
"type": "boolean",
"description": "Whether the host supports JSON mode."
},
"performance": {
"type": "object",
"properties": {
"outputSpeed": {
"type": "object",
"properties": {
"median": {
"type": "number",
"description": "Median, in output tokens per second."
},
"quartile25": {
"type": "number",
"description": "25th percentile, in output tokens per second."
},
"quartile75": {
"type": "number",
"description": "75th percentile, in output tokens per second."
},
"percentile05": {
"type": "number",
"description": "5th percentile, in output tokens per second."
},
"percentile95": {
"type": "number",
"description": "95th percentile, in output tokens per second."
}
},
"description": "Output speed."
},
"timeToFirstToken": {
"type": "object",
"properties": {
"median": {
"type": "number",
"description": "Median, in seconds."
},
"quartile25": {
"type": "number",
"description": "25th percentile, in seconds."
},
"quartile75": {
"type": "number",
"description": "75th percentile, in seconds."
},
"percentile05": {
"type": "number",
"description": "5th percentile, in seconds."
},
"percentile95": {
"type": "number",
"description": "95th percentile, in seconds."
}
},
"description": "Time to the first token."
},
"endToEndResponseTime": {
"type": "object",
"properties": {
"inputTime": {
"type": "number",
"description": "Input processing time."
},
"totalTime": {
"type": "number",
"description": "Total."
},
"answerTime": {
"type": "number",
"description": "Answer generation time."
},
"reasoningTime": {
"type": "number",
"description": "Reasoning time."
}
},
"description": "Median end-to-end response time, in seconds."
},
"timeToFirstAnswerToken": {
"type": "object",
"properties": {
"inputTime": {
"type": "number",
"description": "Input processing time."
},
"totalTime": {
"type": "number",
"description": "Total."
},
"reasoningTime": {
"type": "number",
"description": "Reasoning time."
}
},
"description": "Median time to the first answer token, in seconds."
}
}
},
"functionCalling": {
"type": "boolean",
"description": "Whether the host supports function calling."
}
}
},
"description": "One entry per API host serving the model."
}
}
},
"status": {
"type": "string",
"description": "success when the lookup worked."
}
},
"description": "The model's API hosts."
}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
- Oct 11, 2026