See what AI costs —
and what it delivers.
AI without a cockpit is a black box on the bill. Nexograph makes every euro, every workflow, and every action visible: costs per model, department, and operation, agent workflows from prebuilt prompts, and a complete audit trail — from budget to individual model call.
Every euro has an address.
The usage cockpit breaks down every AI output — by model, department, and operation, over 7, 30, or 90 days. No "the AI was expensive," but rather: which AI, for whom, in which process.
Top by token volume — per model
| Model | Events | Input | Output | Total | Costs |
|---|---|---|---|---|---|
| GPT-4o-mini | 71.240 | 20,1 M | 2,3 M | 22,4 M | € 312 |
| Claude Sonnet 4.5 | 22.880 | 11,9 M | 2,3 M | 14,2 M | € 1.044 |
| GPT-4o | 14.110 | 7,2 M | 1,4 M | 8,6 M | € 921 |
| Llama 3.1 70B (Private) | 12.640 | 3,6 M | 0,5 M | 4,1 M | € 0 |
| embedding-3-large | 6.310 | 1,3 M | — | 1,3 M | € 41 |
| Claude Haiku | 1.250 | 0,2 M | 0,1 M | 0,3 M | € 529 |
| Total | 128.430 | 41,8 M | 9,1 M | 50,9 M | € 2.847 |
Top by token volume — per department
| Workspace | Activity | Events | Total | Costs |
|---|---|---|---|---|
| Sales workspace | Quotes, CRM research, cross-selling | 46.120 | 18,1 M | € 988 |
| Service | Support responses from knowledge base | 33.480 | 12,9 M | € 612 |
| Compliance | Evidence review, source checks | 21.900 | 9,4 M | € 701 |
| Controlling | Analyses, report drafts | 16.740 | 6,6 M | € 358 |
| Procurement | Tenders, contract analysis | 10.190 | 3,9 M | € 188 |
| Total | 128.430 | 50,9 M | € 2.847 |
Top by token volume — per operation
| Operation | Events | Input | Output | Total | Costs |
|---|---|---|---|---|---|
| graphrag:query | 52.300 | 16,4 M | 3,4 M | 19,8 M | € 1.121 |
| chat | 38.910 | 9,3 M | 2,1 M | 11,4 M | € 486 |
| agent-mode:query | 9.640 | 7,1 M | 1,6 M | 8,7 M | € 798 |
| document:ingest | 14.880 | 5,5 M | 0,3 M | 5,8 M | € 211 |
| summarize | 6.090 | 3,2 M | 0,7 M | 3,9 M | € 190 |
| embedding | 6.610 | 1,3 M | — | 1,3 M | € 41 |
| Total | 128.430 | 41,8 M | 9,1 M | 50,9 M | € 2.847 |
Limit per request & workspace
Every logical request has a token/cost budget — including all retries. If a workspace runs hot, the limit kicks in before the bill does.
Cheapest suitable model
The multi-LLM router sends simple tasks to small models and sensitive data to the private LLM. In the example: 18 % lower costs at the same quality.
Cost center assignment
Every event carries department, project, and operation. The analysis can be exported — as a basis for internal chargeback and ROI proof.
From prebuilt prompt
to orchestrated workflow.
Nobody has to program agents. Tested prompt templates describe the task in plain language — Nexograph turns that into an agent, connects several into a workflow, and executes them traceably step by step.
- From plain language, not code: tested prompt templates per use case — customizable, versioned, reusable.
- Controlled connections: supervisor, agent-as-tool, parallel and conditional paths — with approval steps at critical points.
- Nothing runs in the dark: every reasoning and tool step is visible with input/output, duration, and token costs.
Nothing happens without a trace.
Every security-relevant action writes an immutable audit event — who, what, when, with which model. From enabling agent mode to the individual tool call, everything remains traceable and auditable.
Authenticated user or agent — every line carries the responsible actor.
The specific action — access, run, tool call, approval, configuration change.
Timestamp plus model, data room, and cost of the operation.
Every AI response carries its sources — auditable down to the document.
Append-only
Events are only appended, never overwritten — manipulation stands out.
For audits & supervision
Complete history per tenant — as evidence for GDPR, internal audit, and financial auditing.
Telemetry included
Spans and metrics per run — anomalies such as rate limits or rejected tools are visible.