Dispatch · Internal · 💲
The whole money picture up top — what we're spending and the headroom — then the services we're considering, then the compute detail underneath. Numbers pulled from the compute ledger + the live account inventory; nothing here is fabricated.
Figures as-of: monthly spend live from accounts.config.json · weekly usage 2026-07-07 · per-task tokens 2026-07-09 · a snapshot, not a live meter (see the honesty box)
Everything in one place: fixed subscriptions + variable/usage-based API = the real monthly total. ✅ = confirmed · ~ = estimate. Fixed rows are live-sourced from the account-health inventory; variable rows are estimated from the compute ledger + connector runsheets.
| Service | What | $/mo |
|---|---|---|
| Claude / Anthropic (Max) | Dispatch's backbone — every session + scheduled task | ~$200 * |
| Gemini / Google AI Plus | Justin's sub (already paid) | $8 † |
| DigitalOcean VPS | 24/7 host — Hermes + Umami | ~$6 * |
| Domain — fast2future.com | registrar, amortized | ~$1 |
| GitHub · Cloudflare · Buttondown · Gumroad ×2 · Seedance · socials | free tiers | $0 ✅ |
| Fixed subtotal | ≈ 93% is Claude | ~$215/mo |
| Service | Status | $/mo now | if active (est.) |
|---|---|---|---|
| Claude API | runs on the Max sub — no separate metered API | $0 ✅ | — |
| OpenRouter (Hermes) | pay-per-token; capped $0, Hermes not live | $0 ✅ | ~$5–20 (capped) |
| Hunter.io + Tomba/Reoon/ZeroBounce | lead verify/enrich — free tiers (~800 verify/mo free) | $0 ✅ | $0, or $34+ paid |
| ElevenLabs | TTS — free tier; $5 Starter to publish audio commercially | $0 ✅ | ~$5 |
| Exa (neural search) | ~$10 free credits, then pay-as-you-go | $0 ✅ | usage |
| fal.ai | not wired — no active account in the repo | $0 | usage if added |
| Variable subtotal (today) | armed but idle | ~$0/mo | — |
~93% is Claude. The variable/usage layer is armed but idle — OpenRouter capped at $0, and enrichment + TTS + search all sit on free tiers. So today's total ≈ the fixed subscriptions. Headroom: Claude's weekly capacity is 76% used (full gauge in §03 below); the one $ line to watch is OpenRouter, the moment Hermes goes live (capped, never silent).
* Confirm: Claude Max tier ($100 vs $200) + DO droplet price (best estimates). † Gemini $8 → ~$5 at next renewal (Google AI Plus cut to $4.99, eff. 2026-06-08). Fixed rows live-sourced from accounts.config.json → account_health.py; variable estimates from the compute ledger + CONNECTOR_RUNSHEETS.md — reconcile against real balances (openrouter_cost.py) when any usage-based service goes live. This section is the single source of truth for "what are we spending per month, total."
Firsthand exposure to other frontier ecosystems, kept ≈ flat. Prices verified July 2026 (they move fast — re-check at signup). Nothing is bought without your tap (money = hard-gate).
loop/llm_client.py), any API key drops in as a one-line completion(model=…) — same pattern as the OpenRouter key. Multi-LLM through the engine costs ~$0–10/mo metered, vs. ~$60–90/mo stacking consumer subscriptions.| Ecosystem | Real price | What it teaches / builds vs Claude | Engine fit |
|---|---|---|---|
| Claude (keep) | ~$100–200/mo | The backbone — non-negotiable. Everything else is additive. | 🔌 is the engine |
| Grok (xAI) | API $2/$6 per M · SuperGrok $30/mo | Real-time X/social-grounded reasoning; "Heavy" multi-agent mode. Up to $175/mo free dev credits. | 🔌 API (LiteLLM xai/) · 📱 app |
| Nous Hermes | ~$0.13–3 per M (OpenRouter) | Open-weight, steerable/less-restricted agentic behavior. ⚠️ SEPARATE from your internal "Hermes." | 🔌 API (OpenRouter — already wired) |
| OpenAI / ChatGPT | Plus $20 · Pro $100–200 · API sep. | Sora (video), Operator (browser agent), Codex, Workspace Agents — a different frontier lineage. | 🔌 core API · 🖥️ Codex CLI · 📱 Sora/Operator/voice |
| Meta / Muse Spark | Consumer FREE · Muse Spark API $1.25/$4.25 per M | Cheap agentic computer-use (the FB-Marketplace-listing demo). "Meta One" $8/$20 = app-only. | 🔌 Muse Spark API (US preview) · 📱 Meta AI app |
| Gemini / Google AI already paid | $8 → ~$5/mo (AI Plus) | Get more from what you own: Gems, AI Studio (free Flash), Veo/Nano-Banana + Antigravity CLI. | 🔌 Gemini API · 🖥️ Antigravity CLI · 📱 app/Gems |
| Abacus.AI (ChatLLM/DeepAgent) | $10–20/mo · enterprise API ~$5K/mo | "Personal superintelligence" — one app over many models + DeepAgent (build custom agents) + CodeLLM vibe-coding. Credit-based (⚠️ 75% usage-lock rule). | 📱 app (wireable API is enterprise-tier only) |
| DeepSeek ⭐ | API ~$0.14/$0.28 per M · 5M free | Near-free frontier reasoning → learn "run 1,000 experiments for pennies" (bulk/agentic loops). | 🔌 API (LiteLLM, one-line) |
| Perplexity Pro | $20/mo · Sonar API | Live cited search as the default unit — grounded/RAG answers without building retrieval. | 🔌 Sonar API (LiteLLM) |
| Mistral | Le Chat $15/mo · API sep. | EU/open-weight lineage + Codestral (code model to benchmark vs Claude); native MCP agents. | 🔌 API · MCP connector |
"Grok 4.5 with Hermes": Grok = xAI. "Hermes" almost certainly = Nous Research's open Hermes model (a separate thing) — NOT your internal Dispatch "Hermes" agent. They connect, though: your Hermes framework could run on Grok or Nous-Hermes as its backing model. Confirm which you meant.
"anti gravity cli" = Google Antigravity CLI — a real, locally-run agentic CLI (successor to the now-retired Gemini CLI), free tier + ~$20 Pro. Runs alongside Claude Code; it's a CLI, not an API you wire in.
Abacus.AI at $10–20/mo is a polished consumer app that aggregates models you already have (GPT/Claude/Gemini) + an agent-builder (DeepAgent). Its real developer API is enterprise-tier (~$5K/mo), so at your price point it doesn't cheaply extend Dispatch — great for hands-on tinkering, not an engine hook. Watch the credit-based "75% usage-lock" rule.
Best learning-per-dollar that EXTENDS Dispatch: wire 2–3 pay-as-you-go API keys into llm_client.py — DeepSeek (near-free bulk), xAI Grok (free dev credits), Nous Hermes (OpenRouter, already wired). ≈ $0–10/mo metered, no new subscription, each becomes a skill/loop.
For hands-on consumer tinkering (Operator, Sora, Antigravity CLI, Abacus DeepAgent, the Grok app): rotate ONE ~$10–20 sub at a time. The Gemini drop to ~$5 frees a little headroom.
No subscriptions created — this is a menu for your tap. Name one and I'll stage the wiring (API key → skill/loop) or the signup steps.
On the flat-rate Claude Max plan there is no per-token dollar meter. The weekly "all models" usage bar IS the budget signal.
76% used as of 2026-07-07 (Justin-reported from Claude Max → Settings → Usage — there is no API to read this, so it is updated by hand in compute-usage-cap.json). The dashed line is a suggested 85% ceiling to keep a safety margin — no ceiling is set yet; tell me your real number and I'll track against it. A separate weekly "Sonnet-only" bucket exists and draws independently. The Fable window closed ~2026-07-12.
Compute discipline says default Sonnet, Opus only on explicit override. Here's what actually fires.
Default = Sonnet 🔵. Opus 🟣 requires an explicit override + a logged reason. Haiku ⚪ for scan/classify. Every unnamed task should be Sonnet.
Enforced by COMPUTE_ENFORCEMENT.md (pre-spawn gate) + the weekly weekly-compute-audit that reads the ledger.
Scheduled tasks ≈ 100% Opus 4.8. Verified across 9+ post-pin fires (07-08 / 07-09): every one ran Opus. In-prompt model pins are ignored by the runtime — native tasks inherit the app-session model at fire time.
The only real lever: set the Claude app's session/default model to Sonnet before scheduled tasks fire (UI-only — can't be set from a file).
⚠️ This is call-count share, not token-cost share — a per-model token-cost breakdown is not yet computed (instrumentation gap).
Scheduled tasks by total tokens moved (input + output + cache), MEASURED from local transcripts, 2026-07-09.
| Task | Runs | Total tokens | Avg / run | Model |
|---|---|---|---|---|
| assess-advance-overnight | 113 | 468.6M | 4.1M | opus 🟣 |
| assess-advance-heartbeat | 76 | 246.7M | 3.2M | opus 🟣 |
| the-forerunner | 25 | 130.7M | 5.2M | opus 🟣 |
| automation-audit-loop | 16 | 75.7M | 4.7M | opus 🟣 |
| assess-advance-backstop | 64 | 64.4M | 1.0M | opus 🟣 |
| best-of-best-radar | 18 | 62.6M | 3.5M | opus 🟣 |
| agent-infra-watchlist | 18 | 58.3M | 3.2M | opus 🟣 |
| body-watchlist | 17 | 56.8M | 3.3M | opus 🟣 |
| morning-brief | 19 | 51.6M | 2.7M | opus 🟣 |
| assess-advance trio | 253 | ~780M · 65% | — | opus 🟣 |
The assess-advance trio (overnight + heartbeat + backstop) is the single largest center — ~65% of all scheduled compute. Cadence was cut on 07-07 (overnight 28 → 11.5 fires/24h, ~38% fleet-wide reduction) — the run counts above cover the full window, so post-cut burn is lower than the averages imply.
The honesty box — so no number here is trusted further than it earns.
usage fields in local transcripts. Exact, re-runnable (compute_usage_audit.py).message.model. This is how we know pins are ignored.accounts.config.json); free tiers verified $0.openrouter_cost.py) when anything goes live.compute_usage_audit.py to emit JSON this page reads — a clean next step if you want it.