AI Token Spend Diagnostic
Your AI Spend Report.
Now eliminate the waste.
A ranked analysis of token spend, workflow inefficiency, and identified savings. Designed to be read by your engineering team and presented to your CFO.
Client
Meridian Advisory Group
Analysis Period
1 Apr — 31 May 2026
Report Generated
5 June 2026
Identified Monthly Saving
$47,600
$571,200 annualised across 5 ranked changes
Recoverable Spend
42.5%
Of current monthly AI outlay
Efficiency Score
3.2/10
Significant Waste Detected
Executive Summary
Page 2 of 6
Meridian: $47,600 recoverable every month.
Based on 61 days of Meridian's usage data across 4 providers and 6 workflow categories. Every recommendation can be implemented without changing your AI stack. That is $571,200 per year from 5 structural changes.
Monthly AI Spend
$112,000
OpenAI, Anthropic & Azure · 2-month average
Identified Monthly Saving
$47,600
More than covers the cost of this diagnostic, every month
Recoverable Spend
42.5%
Nearly half your current monthly AI bill is unnecessary
Efficiency Score: where Meridian sits today
Score 3.2: Significant Waste
Critical
Significant Waste
Moderate
Optimised
0.0 – 2.5: Critical, immediate action
2.5 – 5.0: Significant waste, high ROI on changes
5.0 – 7.5: Moderate, optimise selectively
7.5 – 10.0: Optimised
Top three findings
$18,700/mo
System prompt bloat in Meridian's Client Briefing Pipeline. Prompts are averaging 11,400 tokens (roughly 8,500 words) before each request. Only about 2,000 of those tokens are doing useful work; the rest is static boilerplate the AI reads and discards every time. Compressing to a structured template removes the waste with no measurable difference in output quality. This is the single highest-return action in the report: 39% of total identified savings, implementable in under one working day.
$13,800/mo
GPT-4o used for document classification where GPT-3.5-turbo costs 94% less. GPT-4o is a frontier reasoning model, well-suited to complex tasks. Document classification (assigning incoming files to a category) does not require that level of capability. Your team is using a precision instrument for a routine sorting job. Switching 4 identified workflows to a cheaper model costs one day of engineering work, with no material change to classification accuracy on evaluation against Meridian's actual output samples.
$8,200/mo
Agent loop redundancy in the Research Automation workflow. 31% of API calls within this workflow ask the AI an identical question to one already asked in the last 60 seconds. Each call is billed as a fresh request. The fix is a lightweight cache that checks recent answers before making a new call. If the question is the same, the cached answer is returned and no charge is incurred. Engineering effort: approximately 3 working days.
Verdict: Meridian's highest-impact action is compressing the Client Briefing Pipeline system prompt from 11,400 tokens to approximately 2,000 tokens. This single change saves $18,700 per month (39% of total identified savings) and can be implemented in under one working day. It requires no model changes, no infrastructure changes, and no retraining.
Spend trajectory
Projected annual AI spend at current patterns, at 3x and 5x usage growth, and at 1.2x and 1.5x provider pricing increases, with and without the identified fixes applied.
| Scenario |
Annual Spend (current) |
Annual Spend (fixes applied) |
Annual Saving |
| Volume growth scenarios |
| Current run rate |
$1,344,000 |
$772,800 |
$571,200 |
| 3x usage growth |
$4,032,000 |
$2,318,400 |
$1,713,600 |
| 5x usage growth |
$6,720,000 |
$3,864,000 |
$2,856,000 |
| Provider pricing stress (current volume) |
1.2x provider pricing
Same workload, rates up 20% |
$1,612,800 |
$927,360 |
$685,440 |
1.5x provider pricing
Same workload, rates up 50% |
$2,016,000 |
$1,159,200 |
$856,800 |
Volume growth: structural inefficiencies scale proportionally with usage. Fixing them now costs one to three days of engineering time at any volume. Provider pricing stress: eliminating the structural waste reduces the absolute bill you are defending against rate changes, because the baseline starts lower.
AI Layer Gross Margin
One additional input unlocks this calculation: your AI-attributable annual revenue. This is the value of work delivered with AI embedded in the workflow, such as client fees, contracts, or output volume. On the live diagnostic, you provide this figure and TokenomicsIQ calculates your AI Layer Gross Margin before and after the identified fixes. The illustrative example below uses $2,880,000 AI-attributable annual revenue.
| Metric |
Before fixes |
After fixes |
Change |
| AI-attributable revenue (illustrative) |
$2,880,000 |
$2,880,000 |
— |
| AI token spend (annual) |
($1,344,000) |
($772,800) |
$571,200 |
| AI Layer Gross Margin |
53.3% |
73.2% |
+19.9pp |
AI Layer Gross Margin = (AI-attributable revenue − AI token spend) / AI-attributable revenue. The $47,600/month in identified savings flows directly into margin. That is the number an investor reads.
Meridian Advisory Group · AI Token Spend Diagnostic · June 2026
TokenomicsIQ
2 of 6
Spend Landscape
Page 3 of 6
60% of Meridian's spend is in one model. Much of it on the wrong tasks.
GPT-4o accounts for $67,200 of Meridian's monthly bill: the right choice for complex reasoning, but over-deployed for classification and templated drafting.
Spend by model
Monthly average, all providers. GPT-4o dominates at 60% of total spend. The model is appropriate for some workflows but significantly over-used for simpler tasks where cheaper models perform equally well.
Spend by task type
Monthly average. Document analysis and classification combined account for 40% of spend, and both categories show high substitution potential. Code generation is the one category where current model selection is appropriate.
Cost efficiency by task type
Efficiency Score = (benchmark cost for this task category at current volume) / (actual cost) x 10. A score below 5.0 indicates the workflow is consuming materially more tokens per output than comparable deployments. P&L classification reflects how each workflow maps to your income statement: COGS is AI spend tied directly to client service delivery, R&D is product and capability development, OpEx is internal operations.
| Task Type |
Model |
Avg Tokens / Request |
Monthly Spend |
Efficiency Score |
P&L Class. |
Action |
| Document Analysis |
GPT-4o |
4,200 |
$33,600 |
4.1 |
COGS |
Optimise prompts |
| Code Generation |
GPT-4o |
3,100 |
$22,400 |
7.8 |
R&D |
Keep current model |
| Client Report Drafting |
GPT-4o + Claude |
8,600 |
$19,600 |
3.2 |
COGS |
Compress system prompt |
| Data Extraction |
Claude Sonnet |
2,800 |
$16,800 |
6.9 |
OpEx |
Keep current model |
| Classification |
GPT-4o |
1,900 |
$11,200 |
1.6 |
OpEx |
Substitute model |
| Other / Uncategorised |
Various |
2,200 |
$8,400 |
4.8 |
? |
Review & categorise |
Note on Other / Uncategorised: These calls could not be reliably mapped to a named workflow: typically ad hoc queries, developer test calls, and multi-purpose scripts without a consistent prompt structure. Adding a workflow_id tag to your API call metadata enables full categorisation in subsequent diagnostics.
Meridian Advisory Group · AI Token Spend Diagnostic · June 2026
TokenomicsIQ
3 of 6
Inefficiency Analysis
Page 4 of 6
Five inefficiencies. Total monthly impact: $47,600. That is $571,200 per year.
Ranked by monthly saving potential. Difficulty rating reflects estimated engineering hours to implement the fix.
| # |
Workflow / Pattern |
Monthly Cost (current) |
Monthly Saving |
Saving % |
Difficulty |
1 |
System Prompt Bloat
Client Briefing Pipeline |
$22,000 |
$18,700 |
85% |
Low |
2 |
Model-Task Mismatch
Document Classification (4 workflows) |
$14,600 |
$13,800 |
94% |
Low |
3 |
Agent Loop Redundancy
Research Automation |
$16,400 |
$8,200 |
50% |
Medium |
4 |
Synchronous-on-Batch
Daily Report Generation |
$7,200 |
$4,300 |
60% |
Low |
5 |
Prompt Cache Miss
Content Review Pipeline |
$5,800 |
$2,600 |
45% |
Medium |
| Total |
$66,000 |
$47,600 |
72% |
|
Note on workflow costs vs. task-type spend: The monthly spend figures in this table reflect the cost attributable to each identified inefficiency pattern, measured at the individual workflow level. These may differ from task-type totals on Page 3, which aggregate spend by category across all workflows. For example, the Model-Task Mismatch row ($14,600) covers four specific workflows flagged for model substitution; the Classification row on Page 3 ($11,200) is the category-level total for all classification tasks, some of which are not flagged. Saving % represents the proportion of each flagged workflow's cost that can be eliminated through the recommended change, not a percentage of total AI spend.
Current cost vs. optimised cost: top 5 inefficiencies
The amber segment on each bar is money leaving your P&L unnecessarily each month. The indigo segment is the baseline cost of running the same workflows efficiently. Fixing just the top two items recovers $32,500 per month: more than the cost of this diagnostic, at roughly two days of engineering work between them.
Meridian Advisory Group · AI Token Spend Diagnostic · June 2026
TokenomicsIQ
4 of 6
Recommendations
Page 5 of 6
Three structural checks. Two flagged, one clear.
TokenomicsIQ runs three automated structural checks on every engagement. Below are the results for Meridian, followed by a ranked action list a developer can start from tomorrow morning.
System Prompt
Bloat
Critical
System prompts average 11,400 tokens in the Client Briefing Pipeline, accounting for 38% of total token spend in that workflow. The excess is static boilerplate sent with every request: content that never changes between calls, billed each time as if it does.
In plain terms
Your team is sending roughly 8,500 words of instructions to the AI before every client briefing request. Only about 1,500 of those words vary between requests. The rest is the same standing brief read aloud at the start of every meeting. Cutting this to a lean 2,000-token template is the highest-return action in this report: $18,700/month saved, less than one day of work, and no change to output quality.
$18,700/mo
identified saving if resolved
Agent Loop
Redundancy
Flagged
31% of Research Automation API calls repeat identical or near-identical context within 60 seconds of a prior call. This is a classic agent loop signature: intermediate outputs are not being cached, so the AI is asked the same question multiple times in quick succession and charged each time.
In plain terms
Nearly one in three calls in this workflow is a duplicate the AI has already answered moments earlier. A lightweight cache (essentially a short-term memory layer) checks whether the same question was asked in the last 60 seconds before making a new API call. If it was, the cached answer is returned at no cost. Engineering effort: approximately 3 working days.
$8,200/mo
identified saving if resolved
Synchronous-
on-Batch
Clear
No critical synchronous-on-batch pattern detected for Meridian's core workflows. One borderline instance found in the Daily Report pipeline, included in Priority Action 4 as a low-effort saving opportunity. It does not meet the threshold for a structural flag.
In plain terms
Some AI tasks are time-sensitive: a chatbot response needs to return immediately. Others are not: a daily report can run overnight. When time-insensitive jobs are processed in real-time (synchronous), they pay full rate. When batched overnight, providers charge 50–60% less for the same work. This check identifies jobs that are paying real-time prices without needing real-time delivery. Meridian passes this check on all core workflows.
No critical issue
minor optimisation opportunity noted below
Model substitution recommendations
Where model substitution is recommended, quality impact is assessed against a sample of Meridian's actual outputs. "No change" indicates no material quality difference detected on evaluation; "Minimal" indicates a measurable but operationally acceptable difference.
| Task Type |
Current Model |
Recommended Model |
Monthly Saving |
Quality Impact |
| Document Classification |
GPT-4o |
GPT-3.5-turbo |
$13,800 |
No change |
| Internal Routing Logic |
Claude Sonnet 3.7 |
Claude Haiku 3.5 |
$2,400 |
Minimal (<3%) |
| Simple Q&A Queries |
GPT-4o |
GPT-4o-mini |
$1,100 |
No change |
Priority action list
Ranked by monthly saving. Effort in working days for a mid-level engineer familiar with Meridian's codebase.
1
Compress Meridian's Client Briefing Pipeline system prompt from 11,400 to ~2,000 tokens
Refactor static boilerplate into a shared context template. Test against 20 sample outputs before deploying.
2
Switch Document Classification workflows (4 identified) from GPT-4o to GPT-3.5-turbo
Update model parameter in each workflow configuration. No prompt changes required. Validated against sample outputs.
3
Add 60-second deduplication cache to Research Automation agent loop
Hash context window content; return cached response if identical call made within 60s. Redis or in-memory cache both work here.
$8,200/mo
Effort: 2 – 3 days
4
Convert Daily Report generation to async batch API calls
Daily report jobs are non-time-sensitive and currently running synchronous. Batch API costs approximately 60% less per token on OpenAI and Anthropic.
$4,300/mo
Effort: 1 – 2 days
5
Enable prompt caching for Content Review workflow repeated system prompts
Anthropic and OpenAI both support prompt caching for repeated prompt prefixes. Single configuration change per workflow.
$2,600/mo
Effort: 0.5 day
Meridian Advisory Group · AI Token Spend Diagnostic · June 2026
TokenomicsIQ
5 of 6
How TokenomicsIQ classifies and scores your usage.
The classification engine processes your raw LLM usage CSV and applies six diagnostic passes. Here is what each pass does and how the Efficiency Score is calculated.
01
Usage Ingestion
Your usage export (CSV or JSON) is normalised across provider formats: OpenAI, Anthropic, Azure, AWS Bedrock, and TypingMind. Token counts, model IDs, timestamps, and endpoint identifiers are standardised into a unified schema. No API connection required.
02
Workflow Classification
Each API call is assigned to one of six task categories using a combination of prompt structure analysis, system prompt fingerprinting, and token ratio patterns. Each report discloses the percentage of records classified directly versus inferred. Where classification cannot be determined directly from prompt structure, TIQ applies pattern-based inference and flags those records separately.
03
Benchmark Comparison
Actual cost per task type is compared against our benchmark dataset of efficient deployments at comparable scale and workflow type. The benchmark is updated quarterly from anonymised engagement data.
04
Structural Checks
Three automated detectors run on the full dataset: System Prompt Bloat (prompt token ratio above threshold), Agent Loop Redundancy (repeated context within time window), and Synchronous-on-Batch (non-time-sensitive synchronous calls).
05
Savings Calculation
Identified savings are calculated conservatively, using current provider pricing at the client's actual volume tier, with no assumption of future pricing changes. Model substitution savings are based on validated accuracy parity, not theoretical capability.
06
Efficiency Score
Efficiency Score = (benchmark cost for this task category at current volume) ÷ (actual cost) × 10. A score of 10 means you are running at benchmark efficiency; a score below 5 indicates material structural waste. Score 3.2 means Meridian's actual cost is approximately three times the benchmark for its workflow mix, indicating significant room for structural improvement.
Data handling
Your usage export is processed in an isolated environment and deleted immediately after the report is generated. The report itself expires approximately 15 minutes after delivery. No data is stored, shared, retained between reports, or used to train any model. TokenomicsIQ processes the structure of your usage patterns, not the content of your prompts or AI outputs. The classification engine works on token counts, model IDs, timestamps, and cost metadata only.
About TokenomicsIQ
TokenomicsIQ is a fixed-fee AI token spend diagnostic for engineering teams and the CFOs they report to. Export your usage data from OpenAI, Anthropic, Azure, or TypingMind and upload it. Receive a ranked report (HTML and PDF) with specific, implementable savings recommendations in under 30 minutes. No integration. No ongoing subscription. No consultant retainer. $3,500: the kind of clarity that used to cost ten times as much.
Get your report at tokenomicsiq.ai
Meridian Advisory Group · AI Token Spend Diagnostic · June 2026
TokenomicsIQ
6 of 6