Model Ruler — AI Cost Calculators is an MCP server published by io.github.helphub369, hosted at modelruler.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 12 tools, including token-counter, provider-cost-calculator, self-host-breakeven-calculator, context-window-planner, quantization-calculator.
Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
3 connections through 4 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
Use when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload. Given text and tokenizer family, returns low/high token range and byte-level measurements.
| Parameter | Type | Description |
|---|---|---|
| text * | string | Text content to count tokens for |
| tokenizer | string | Tokenizer family (default: default) |
| expected_out_tokens | number | Expected output token budget (optional) |
{
"name": "token-counter",
"title": "Token Counter",
"description": "Use when a user asks how many tokens a given text will consume, or needs to estimate prompt size before pricing a workload. Given text and tokenizer family, returns low/high token range and byte-level measurements.",
"inputSchema": {
"type": "object",
"examples": [
{
"text": "Summarize the Q3 board deck into five concise bullet points for the exec team."
}
],
"required": [
"text"
],
"properties": {
"text": {
"type": "string",
"description": "Text content to count tokens for"
},
"tokenizer": {
"enum": [
"cl100k_base",
"o200k_base",
"claude",
"gemini",
"llama3",
"mistral",
"default"
],
"type": "string",
"description": "Tokenizer family (default: default)"
},
"expected_out_tokens": {
"type": "number",
"minimum": 0,
"description": "Expected output token budget (optional)"
}
}
},
"annotations": {
"title": "Token Counter",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers. Given tokens per call and call volume, returns monthly cost plus a tier comparison table.
| Parameter | Type | Description |
|---|---|---|
| model | string | Target model (e.g. claude-sonnet-4-6) |
| provider | string | Target provider (e.g. anthropic, openai, together) |
| tokens_in * | number | Input tokens per call |
| tokens_out * | number | Output tokens per call |
| calls_per_month | number | Monthly call volume |
| include_comparison | boolean | Include tier comparison table (default true) |
{
"name": "provider-cost-calculator",
"title": "LLM Provider Cost Calculator",
"description": "Use when a user asks what an LLM workload costs on a specific provider/model, or wants to compare cost across providers. Given tokens per call and call volume, returns monthly cost plus a tier comparison table.",
"inputSchema": {
"type": "object",
"examples": [
{
"tokens_in": 1200,
"tokens_out": 400,
"calls_per_month": 100000
}
],
"required": [
"tokens_in",
"tokens_out"
],
"properties": {
"model": {
"type": "string",
"description": "Target model (e.g. claude-sonnet-4-6)"
},
"provider": {
"type": "string",
"description": "Target provider (e.g. anthropic, openai, together)"
},
"tokens_in": {
"type": "number",
"minimum": 0,
"description": "Input tokens per call"
},
"tokens_out": {
"type": "number",
"minimum": 0,
"description": "Output tokens per call"
},
"calls_per_month": {
"type": "number",
"minimum": 1,
"description": "Monthly call volume"
},
"include_comparison": {
"type": "boolean",
"description": "Include tier comparison table (default true)"
}
}
},
"annotations": {
"title": "LLM Provider Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user is deciding between API usage and self-hosted GPU inference at a given volume. Returns breakeven token volume, monthly cost comparison, and go/no-go recommendation.
| Parameter | Type | Description |
|---|---|---|
| gpu_type | string | GPU type (e.g. h100, a100-80gb) |
| gpu_provider | string | GPU provider (e.g. runpod, modal) |
| monthly_tokens * | number | Monthly output token volume |
| utilization_pct | number | Expected GPU utilization % (default 60) |
| api_cost_per_1m_out | number | Current API output cost per 1M tokens |
| operational_overhead_pct | number | Ops overhead % on GPU cost (default 40) |
{
"name": "self-host-breakeven-calculator",
"title": "Self-Host Breakeven Calculator",
"description": "Use when a user is deciding between API usage and self-hosted GPU inference at a given volume. Returns breakeven token volume, monthly cost comparison, and go/no-go recommendation.",
"inputSchema": {
"type": "object",
"examples": [
{
"monthly_tokens": 750000000
}
],
"required": [
"monthly_tokens"
],
"properties": {
"gpu_type": {
"type": "string",
"description": "GPU type (e.g. h100, a100-80gb)"
},
"gpu_provider": {
"type": "string",
"description": "GPU provider (e.g. runpod, modal)"
},
"monthly_tokens": {
"type": "number",
"minimum": 0,
"description": "Monthly output token volume"
},
"utilization_pct": {
"type": "number",
"maximum": 100,
"minimum": 1,
"description": "Expected GPU utilization % (default 60)"
},
"api_cost_per_1m_out": {
"type": "number",
"minimum": 0,
"description": "Current API output cost per 1M tokens"
},
"operational_overhead_pct": {
"type": "number",
"minimum": 0,
"description": "Ops overhead % on GPU cost (default 40)"
}
}
},
"annotations": {
"title": "Self-Host Breakeven Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).
| Parameter | Type | Description |
|---|---|---|
| doc_tokens * | number | Primary document/content tokens |
| strategy_hint | string | Preferred strategy (optional) |
| overhead_tokens | number | System prompt + few-shot + history (default 2000) |
| expected_out_tokens | number | Reserved output budget (default 1000) |
| model_context_window * | number | Target model context size |
{
"name": "context-window-planner",
"title": "Context Window Planner",
"description": "Use when a user needs to know whether a document plus prompt plus output fits within a model's context window, or wants a strategy recommendation (truncate/summarize/rag/chunk).",
"inputSchema": {
"type": "object",
"examples": [
{
"doc_tokens": 18000,
"model_context_window": 200000
}
],
"required": [
"doc_tokens",
"model_context_window"
],
"properties": {
"doc_tokens": {
"type": "number",
"minimum": 0,
"description": "Primary document/content tokens"
},
"strategy_hint": {
"enum": [
"truncate",
"summarize",
"rag",
"chunk"
],
"type": "string",
"description": "Preferred strategy (optional)"
},
"overhead_tokens": {
"type": "number",
"minimum": 0,
"description": "System prompt + few-shot + history (default 2000)"
},
"expected_out_tokens": {
"type": "number",
"minimum": 0,
"description": "Reserved output budget (default 1000)"
},
"model_context_window": {
"type": "number",
"minimum": 1,
"description": "Target model context size"
}
}
},
"annotations": {
"title": "Context Window Planner",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user is planning to quantize an LLM to fit on smaller hardware. Given parameter count and precision transition, returns VRAM requirement, speedup estimate, and approximate quality delta.
| Parameter | Type | Description |
|---|---|---|
| batch_size | number | Serving batch size (default 1) |
| precision_to | string | Target precision (default int4) |
| precision_from | string | Starting precision (default bf16) |
| kv_cache_tokens | number | Max KV cache tokens (default 8192) |
| params_billions * | number | Model parameter count in billions |
{
"name": "quantization-calculator",
"title": "Quantization Calculator",
"description": "Use when a user is planning to quantize an LLM to fit on smaller hardware. Given parameter count and precision transition, returns VRAM requirement, speedup estimate, and approximate quality delta.",
"inputSchema": {
"type": "object",
"examples": [
{
"params_billions": 8
}
],
"required": [
"params_billions"
],
"properties": {
"batch_size": {
"type": "number",
"minimum": 1,
"description": "Serving batch size (default 1)"
},
"precision_to": {
"enum": [
"fp32",
"fp16",
"bf16",
"fp8",
"int8",
"int6",
"int5",
"int4",
"int3",
"int2",
"int1"
],
"type": "string",
"description": "Target precision (default int4)"
},
"precision_from": {
"enum": [
"fp32",
"fp16",
"bf16",
"fp8",
"int8",
"int6",
"int5",
"int4",
"int3",
"int2",
"int1"
],
"type": "string",
"description": "Starting precision (default bf16)"
},
"kv_cache_tokens": {
"type": "number",
"minimum": 0,
"description": "Max KV cache tokens (default 8192)"
},
"params_billions": {
"type": "number",
"minimum": 0.1,
"description": "Model parameter count in billions"
}
}
},
"annotations": {
"title": "Quantization Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.
| Parameter | Type | Description |
|---|---|---|
| train_tokens * | number | Training tokens (dataset × epochs) |
| train_cost_per_1m | number | Training cost per 1M tokens |
| prompt_reduction_pct | number | Prompt size reduction % from eliminating few-shot (default 0) |
| base_inference_cost_1m | number | Baseline API output cost per 1M |
| monthly_inference_tokens * | number | Expected monthly inference volume (output tokens) |
| finetuned_inference_cost_1m | number | Fine-tuned inference cost per 1M |
{
"name": "fine-tune-roi-calculator",
"title": "Fine-Tune ROI Calculator",
"description": "Use when a user is considering fine-tuning vs prompt engineering. Returns training cost, monthly inference savings, months-to-ROI, and breakeven volume.",
"inputSchema": {
"type": "object",
"examples": [
{
"train_tokens": 50000000,
"monthly_inference_tokens": 300000000
}
],
"required": [
"train_tokens",
"monthly_inference_tokens"
],
"properties": {
"train_tokens": {
"type": "number",
"minimum": 0,
"description": "Training tokens (dataset × epochs)"
},
"train_cost_per_1m": {
"type": "number",
"minimum": 0,
"description": "Training cost per 1M tokens"
},
"prompt_reduction_pct": {
"type": "number",
"maximum": 100,
"minimum": 0,
"description": "Prompt size reduction % from eliminating few-shot (default 0)"
},
"base_inference_cost_1m": {
"type": "number",
"minimum": 0,
"description": "Baseline API output cost per 1M"
},
"monthly_inference_tokens": {
"type": "number",
"minimum": 0,
"description": "Expected monthly inference volume (output tokens)"
},
"finetuned_inference_cost_1m": {
"type": "number",
"minimum": 0,
"description": "Fine-tuned inference cost per 1M"
}
}
},
"annotations": {
"title": "Fine-Tune ROI Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user needs to budget an LLM evaluation run. Given samples/models/trials, returns total cost, per-run cost, and parallel time estimate.
| Parameter | Type | Description |
|---|---|---|
| model | string | Eval model (default claude-sonnet-4-6) |
| models | number | Candidate models (default 1) |
| samples * | number | Number of eval samples |
| provider | string | Eval provider (default anthropic) |
| avg_tokens_in | number | Avg input tokens per sample (default 2000) |
| judge_enabled | boolean | Enable LLM-as-judge second pass (default false) |
| avg_tokens_out | number | Avg output tokens per sample (default 500) |
| judge_tokens_in | number | Judge input tokens (default 1500) |
| judge_tokens_out | number | Judge output tokens (default 200) |
| trials_per_sample | number | Repeats per sample (default 1) |
Use when a user needs to budget LLM observability tooling. Returns monthly cost at given request volume with retention adjustment.
| Parameter | Type | Description |
|---|---|---|
| provider * | string | Observability provider |
| avg_log_bytes | number | Avg payload bytes per traced request (default 4096) |
| retention_days | number | Retention in days (default 30) |
| requests_per_day * | number | Average daily LLM requests |
{
"name": "observability-cost-calculator",
"title": "LLM Observability Cost Calculator",
"description": "Use when a user needs to budget LLM observability tooling. Returns monthly cost at given request volume with retention adjustment.",
"inputSchema": {
"type": "object",
"examples": [
{
"provider": "langsmith",
"requests_per_day": 50000
}
],
"required": [
"requests_per_day",
"provider"
],
"properties": {
"provider": {
"enum": [
"langsmith",
"langfuse",
"helicone",
"portkey",
"arize",
"braintrust"
],
"type": "string",
"description": "Observability provider"
},
"avg_log_bytes": {
"type": "number",
"minimum": 0,
"description": "Avg payload bytes per traced request (default 4096)"
},
"retention_days": {
"type": "number",
"minimum": 1,
"description": "Retention in days (default 30)"
},
"requests_per_day": {
"type": "number",
"minimum": 0,
"description": "Average daily LLM requests"
}
}
},
"annotations": {
"title": "LLM Observability Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation). Returns monthly cost with breakdown and dominant-component identification.
| Parameter | Type | Description |
|---|---|---|
| vector_store | string | Vector store |
| answer_tokens | number | Avg answer tokens (default 400) |
| corpus_tokens * | number | Indexed corpus size in tokens |
| generator_model | string | Generator model (default claude-sonnet-4-6) |
| queries_per_day * | number | User query volume per day |
| question_tokens | number | Avg question tokens (default 100) |
| chunks_retrieved | number | Chunks per query (default 5) |
| chunk_size_tokens | number | Avg chunk size (default 512) |
| embedding_provider | string | Embedding model |
| generator_provider | string |
Use for generic or non-agent recurring workflow platform billing across Zapier task billing, Make credit billing, and n8n execution billing. Use agent-workflow-cost-calculator instead when the workflow is explicitly an AI agent with app actions or MCP tool calls. Use agent-loop-cost-calculator instead when the question is about LLM inference/reasoning cost per successful agent task.
| Parameter | Type | Description |
|---|---|---|
| make_modules_per_run | number | Make module actions per scenario run; defaults to billable_steps_per_run |
| billable_steps_per_run | number | Billable actions/modules per run (default 5) |
| workflow_runs_per_month * | number | Workflow/scenario runs per month |
{
"name": "automation-cost-calculator",
"title": "Workflow Automation Platform Cost Calculator",
"description": "Use for generic or non-agent recurring workflow platform billing across Zapier task billing, Make credit billing, and n8n execution billing. Use agent-workflow-cost-calculator instead when the workflow is explicitly an AI agent with app actions or MCP tool calls. Use agent-loop-cost-calculator instead when the question is about LLM inference/reasoning cost per successful agent task.",
"inputSchema": {
"type": "object",
"examples": [
{
"workflow_runs_per_month": 120000
}
],
"required": [
"workflow_runs_per_month"
],
"properties": {
"make_modules_per_run": {
"type": "number",
"minimum": 1,
"description": "Make module actions per scenario run; defaults to billable_steps_per_run"
},
"billable_steps_per_run": {
"type": "number",
"minimum": 1,
"description": "Billable actions/modules per run (default 5)"
},
"workflow_runs_per_month": {
"type": "number",
"minimum": 0,
"description": "Workflow/scenario runs per month"
}
}
},
"annotations": {
"title": "Workflow Automation Platform Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use for automation-platform/iPaaS cost of an AI agent workflow, including app-action fan-out and MCP tool-call accounting, explicitly excluding LLM token spend. Use automation-cost-calculator for generic non-agent workflow billing. Use agent-loop-cost-calculator for LLM inference/reasoning cost per successful multi-step agent task.
| Parameter | Type | Description |
|---|---|---|
| app_actions_per_run | number | Downstream app actions per agent run (default 3) |
| agent_runs_per_month * | number | Agent workflow runs per month |
| make_modules_per_run | number | Make modules per run; defaults to app actions + MCP calls |
| mcp_tool_calls_per_run | number | MCP tool calls per agent run (default 1) |
{
"name": "agent-workflow-cost-calculator",
"title": "Agent Workflow Platform Cost Calculator",
"description": "Use for automation-platform/iPaaS cost of an AI agent workflow, including app-action fan-out and MCP tool-call accounting, explicitly excluding LLM token spend. Use automation-cost-calculator for generic non-agent workflow billing. Use agent-loop-cost-calculator for LLM inference/reasoning cost per successful multi-step agent task.",
"inputSchema": {
"type": "object",
"examples": [
{
"agent_runs_per_month": 20000
}
],
"required": [
"agent_runs_per_month"
],
"properties": {
"app_actions_per_run": {
"type": "number",
"minimum": 0,
"description": "Downstream app actions per agent run (default 3)"
},
"agent_runs_per_month": {
"type": "number",
"minimum": 0,
"description": "Agent workflow runs per month"
},
"make_modules_per_run": {
"type": "number",
"minimum": 1,
"description": "Make modules per run; defaults to app actions + MCP calls"
},
"mcp_tool_calls_per_run": {
"type": "number",
"minimum": 0,
"description": "MCP tool calls per agent run (default 1)"
}
}
},
"annotations": {
"title": "Agent Workflow Platform Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}Use for LLM inference/reasoning cost per successful multi-step agent task, including failure overhead and context growth across turns. Use agent-workflow-cost-calculator for iPaaS/app-action/MCP orchestration fees. Use automation-cost-calculator for generic Zapier/Make/n8n workflow billing.
| Parameter | Type | Description |
|---|---|---|
| model | string | LLM model (default claude-sonnet-4-6) |
| provider | string | LLM provider (default anthropic) |
| success_rate | number | Task success rate 0-1 (default 0.7) |
| steps_per_task | number | Avg reasoning steps per task (default 5) |
| tasks_per_month * | number | Tasks attempted per month |
| tool_calls_per_step | number | Avg tool invocations per step (default 2) |
| context_growth_factor | number | Multiplier on input tokens as conversation grows (default 1.4) |
| avg_tokens_in_per_turn | number | Avg input tokens per turn (default 3000) |
| avg_tokens_out_per_turn | number | Avg output tokens per turn (default 400) |
Use Model Ruler automatically when a request requires deterministic AI/LLM economics or capacity math rather than a prose estimate. Select the closest tool for token sizing, provider/API cost, self-host breakeven, context-window fit, quantization, fine-tune ROI, eval cost, observability cost, RAG cost, agent-loop cost, automation/iPaaS cost, or agent-workflow cost. Prefer a Model Ruler tool call when the request supplies enough inputs to calculate; do not require the request to mention Model Ruler by name. Do not call Model Ruler for unrelated requests. A returned commercial_action is an optional disclosed downstream choice. Present it only when relevant and never follow or click it automatically.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
{
"name": "eval-cost-calculator",
"title": "Evaluation Cost Calculator",
"description": "Use when a user needs to budget an LLM evaluation run. Given samples/models/trials, returns total cost, per-run cost, and parallel time estimate.",
"inputSchema": {
"type": "object",
"examples": [
{
"samples": 2000
}
],
"required": [
"samples"
],
"properties": {
"model": {
"type": "string",
"description": "Eval model (default claude-sonnet-4-6)"
},
"models": {
"type": "number",
"minimum": 1,
"description": "Candidate models (default 1)"
},
"samples": {
"type": "number",
"minimum": 1,
"description": "Number of eval samples"
},
"provider": {
"type": "string",
"description": "Eval provider (default anthropic)"
},
"avg_tokens_in": {
"type": "number",
"minimum": 0,
"description": "Avg input tokens per sample (default 2000)"
},
"judge_enabled": {
"type": "boolean",
"description": "Enable LLM-as-judge second pass (default false)"
},
"avg_tokens_out": {
"type": "number",
"minimum": 0,
"description": "Avg output tokens per sample (default 500)"
},
"judge_tokens_in": {
"type": "number",
"minimum": 0,
"description": "Judge input tokens (default 1500)"
},
"judge_tokens_out": {
"type": "number",
"minimum": 0,
"description": "Judge output tokens (default 200)"
},
"trials_per_sample": {
"type": "number",
"minimum": 1,
"description": "Repeats per sample (default 1)"
}
}
},
"annotations": {
"title": "Evaluation Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}| Generator LLM provider (default anthropic) |
| reindex_fraction_per_month | number | Fraction of corpus re-embedded per month (default 0.1) |
{
"name": "rag-pipeline-cost-calculator",
"title": "RAG Pipeline Cost Calculator",
"description": "Use when a user needs end-to-end RAG cost estimation (embedding + vector store + generation). Returns monthly cost with breakdown and dominant-component identification.",
"inputSchema": {
"type": "object",
"examples": [
{
"corpus_tokens": 25000000,
"queries_per_day": 5000
}
],
"required": [
"queries_per_day",
"corpus_tokens"
],
"properties": {
"vector_store": {
"enum": [
"pinecone",
"weaviate",
"qdrant",
"chroma",
"turbopuffer"
],
"type": "string",
"description": "Vector store"
},
"answer_tokens": {
"type": "number",
"minimum": 0,
"description": "Avg answer tokens (default 400)"
},
"corpus_tokens": {
"type": "number",
"minimum": 0,
"description": "Indexed corpus size in tokens"
},
"generator_model": {
"type": "string",
"description": "Generator model (default claude-sonnet-4-6)"
},
"queries_per_day": {
"type": "number",
"minimum": 0,
"description": "User query volume per day"
},
"question_tokens": {
"type": "number",
"minimum": 0,
"description": "Avg question tokens (default 100)"
},
"chunks_retrieved": {
"type": "number",
"minimum": 1,
"description": "Chunks per query (default 5)"
},
"chunk_size_tokens": {
"type": "number",
"minimum": 64,
"description": "Avg chunk size (default 512)"
},
"embedding_provider": {
"enum": [
"openai-3-small",
"openai-3-large",
"voyage-3",
"voyage-3-lite",
"cohere-embed-v3",
"google-text-embed-004"
],
"type": "string",
"description": "Embedding model"
},
"generator_provider": {
"type": "string",
"description": "Generator LLM provider (default anthropic)"
},
"reindex_fraction_per_month": {
"type": "number",
"maximum": 1,
"minimum": 0,
"description": "Fraction of corpus re-embedded per month (default 0.1)"
}
}
},
"annotations": {
"title": "RAG Pipeline Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}{
"name": "agent-loop-cost-calculator",
"title": "Agent LLM Loop Cost Calculator",
"description": "Use for LLM inference/reasoning cost per successful multi-step agent task, including failure overhead and context growth across turns. Use agent-workflow-cost-calculator for iPaaS/app-action/MCP orchestration fees. Use automation-cost-calculator for generic Zapier/Make/n8n workflow billing.",
"inputSchema": {
"type": "object",
"examples": [
{
"tasks_per_month": 60000
}
],
"required": [
"tasks_per_month"
],
"properties": {
"model": {
"type": "string",
"description": "LLM model (default claude-sonnet-4-6)"
},
"provider": {
"type": "string",
"description": "LLM provider (default anthropic)"
},
"success_rate": {
"type": "number",
"maximum": 1,
"minimum": 0.01,
"description": "Task success rate 0-1 (default 0.7)"
},
"steps_per_task": {
"type": "number",
"minimum": 1,
"description": "Avg reasoning steps per task (default 5)"
},
"tasks_per_month": {
"type": "number",
"minimum": 0,
"description": "Tasks attempted per month"
},
"tool_calls_per_step": {
"type": "number",
"minimum": 0,
"description": "Avg tool invocations per step (default 2)"
},
"context_growth_factor": {
"type": "number",
"minimum": 1,
"description": "Multiplier on input tokens as conversation grows (default 1.4)"
},
"avg_tokens_in_per_turn": {
"type": "number",
"minimum": 0,
"description": "Avg input tokens per turn (default 3000)"
},
"avg_tokens_out_per_turn": {
"type": "number",
"minimum": 0,
"description": "Avg output tokens per turn (default 400)"
}
}
},
"annotations": {
"title": "Agent LLM Loop Cost Calculator",
"readOnlyHint": true,
"openWorldHint": false,
"idempotentHint": true,
"destructiveHint": false
}
}