AI Model Cost Per Task Benchmark (Multiple Models)

omnial/get-cost-per-task

Returns cost-per-task benchmark data for a set of AI models at once: the average dollar cost of running a standard task per model (with a breakdown by input/output/reasoning/cache tokens), token counts, response timing, an intelligence-index score, and a coding-specific cost and timing variant where the benchmark has evaluated one. Pass a comma-separated list of model slugs to select the models you want.

activeper callv2

Price

Up to $0.0683 per call; you pay what the call used

You pay the price shown. If a call turns out to cost more than its quote, you pay the actual price, capped at twice the quote. No monthly minimum. Top-ups start at $5.00.

Data source

Artificial Analysis

Data from Artificial Analysis.

Use it

Your AI assistant does the work: it finds this tool, shows you the price first, runs it, and you are charged when the run finishes. There is nothing to set up for this tool in particular.

Connect once and your AI can find and run this tool, and any other it needs.

Install it Create an account

For developers: the calls your assistant makes

agent

// 1. search: find the tool
omnial_search({ query: "what you need" })

// 2. inspect: price and input schema
omnial_inspect({ tool: "omnial/get-cost-per-task" })

// 3. learn: read the usage guide at runtime
omnial_learn({ tool: "omnial/get-cost-per-task" })

// 4. run: price the exact call first, then run it
omnial_execute({ tool: "omnial/get-cost-per-task", input: { /* see input_schema */ }, dry_run: true })
omnial_execute({ tool: "omnial/get-cost-per-task", input: { /* ... */ } })

// 5. settle: the call is charged when it finishes, nothing to do

Not connected yet? Point your MCP client at https://mcp.eden-engine.com/mcp, then copy a config for your client.

Pricing

Every charge this tool can incur.

Charge	Price
Per call	$0.0683

Updated: Oct 27, 2026

Input and output schemas

Input schema

input_schema.json

{
  "type": "object",
  "required": [
    "models"
  ],
  "properties": {
    "models": {
      "type": "string",
      "description": "Required. Comma-separated list of model slugs to fetch (e.g. 'claude-sonnet-5,gpt-5-6-sol,gemini-3-5-flash-lite')."
    }
  },
  "additionalProperties": false
}

Output schema

output_schema.json

{
  "type": "object",
  "properties": {
    "data": {
      "type": "object",
      "properties": {
        "models": {
          "type": "array",
          "items": {
            "type": "object",
            "properties": {
              "name": {
                "type": "string",
                "description": "Full display name, e.g. 'GPT-5.6 Sol (max)'."
              },
              "slug": {
                "type": "string",
                "description": "The model slug."
              },
              "ttft": {
                "type": "number",
                "description": "Time to first token, seconds; populated on every model observed across both real calls."
              },
              "short_name": {
                "type": "string",
                "description": "Short display name; often identical to `name`, sometimes a shortened form."
              },
              "coding_index": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "Coding-specific benchmark score; null on every model observed on both real calls -- the benchmark does not currently expose per-coding-task data."
              },
              "cost_per_task": {
                "type": "number",
                "description": "USD, average total cost to run the benchmark's standard task."
              },
              "time_per_task": {
                "type": "number",
                "description": "Seconds, average total time to complete the standard task; populated on every model observed across both real calls (7 distinct models total)."
              },
              "intelligence_index": {
                "type": "number",
                "description": "The benchmark's aggregate reasoning/quality score for this model."
              },
              "coding_cost_per_task": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "USD, coding-task variant of `cost_per_task`; null on every model observed."
              },
              "coding_time_per_task": {
                "type": [
                  "number",
                  "null"
                ],
                "description": "Seconds, coding-task variant of `time_per_task`; null on every model observed."
              },
              "input_tokens_per_task": {
                "type": "number"
              },
              "output_tokens_per_task": {
                "type": "number"
              },
              "cost_per_task_breakdown": {
                "type": "object",
                "properties": {
                  "cache_hit": {
                    "type": "number"
                  },
                  "cache_write": {
                    "type": "number"
                  },
                  "input_tokens": {
                    "type": "number"
                  },
                  "output_tokens": {
                    "type": "number"
                  },
                  "reasoning_tokens": {
                    "type": "number"
                  }
                },
                "description": "USD contribution of each token category to `cost_per_task`.",
                "additionalProperties": true
              },
              "end_to_end_response_time": {
                "type": "number",
                "description": "Seconds; populated on every model observed across both real calls."
              },
              "reasoning_tokens_per_task": {
                "type": "number"
              },
              "coding_cost_per_task_breakdown": {
                "type": [
                  "object",
                  "null"
                ],
                "description": "Coding-task variant of `cost_per_task_breakdown`; null on every model observed. Populated shape unconfirmed since no non-null example exists.",
                "additionalProperties": true
              }
            },
            "additionalProperties": true
          },
          "description": "One entry per requested model."
        }
      },
      "additionalProperties": true
    },
    "status": {
      "type": "string",
      "description": "'success' on both real calls observed."
    }
  },
  "description": "The cost-per-task payload.",
  "additionalProperties": true
}