Pricing
Benchmarked against: Anthropic โ Pricing Rule source: Company Constitution ยง6, Cost Awareness governance rule Captain insight: Paying 20x Max Plan + large API deposits โ every token has real cost
SuperPortia's cost structure spans Claude subscription plans, low-cost API engines, and infrastructure services. Understanding these costs is essential for engine selection and operational efficiency.
Claude pricingโ
Subscription plansโ
| Resource | Billing | Shared with | Notes |
|---|---|---|---|
| All Models quota (Opus, Sonnet, Haiku) | Max Plan monthly | claude.ai Chat + Claude Code CLI | Chat (ๅฐ่ฅฟ) and Code (ๅฐๅ ) share this quota |
| Sonnet-only quota | Separate monthly allowance | claude.ai Chat + Claude Code CLI | Independent โ does not consume All Models |
| API credits (extra usage / LiteLLM) | Per-token | Direct API calls only | Kicks in when quota exceeded |
Critical insight: All Models quota is shared between claude.ai (Chat tab = ๅฐ่ฅฟ) and Claude Code (Code tab = ๅฐๅ ). Heavy CLI usage directly reduces Chat availability, and vice versa.
Claude per-token rates (API / extra usage)โ
| Model | Input | Output |
|---|---|---|
| Opus 4.6 | Most expensive | Most expensive |
| Sonnet 4.6 | Moderate | Moderate |
| Haiku 4.5 | Cheapest Claude | Cheapest Claude |
Exact per-token pricing follows Anthropic's published rates. Check anthropic.com/pricing for current numbers.
Low-cost engine pricingโ
| Engine | Default Model | Cost per request | Monthly estimate (100 req/day) |
|---|---|---|---|
| Groq | Llama 3.3 70B | Free | $0 |
| Groq Search | Compound | Free | $0 |
| Gemini | 2.5 Flash | ~$0.003 | ~$9 |
| Gemini Search | + Google Grounding | ~$0.014 | ~$42 |
| DeepSeek | R1 / V3 | Cents | ~$5-10 |
| Mistral | Latest | Cents | ~$5-10 |
| Zhipu | GLM-5 | Cents | ~$5-10 |
| Ingest | MTAAA Pipeline | Free (internal) | $0 |
Infrastructure pricingโ
All infrastructure currently operates within free tiers:
| Service | Free tier | Current usage | Overage cost |
|---|---|---|---|
| Cloudflare Workers | 100K requests/day | Well within | $0.50/million |
| Cloudflare D1 | 5M reads/day, 100K writes/day | Well within | $0.001/million reads |
| Cloudflare Vectorize | 30M queries/month | Well within | Usage-based |
| Cloudflare R2 | 10GB storage, 1M reads/month | Well within | $0.015/GB/month |
| Supabase | Free tier / Pro plan | Varies by project | Plan-based |
Cost comparison: engine selection impactโ
The same task at different engine levels:
| Task | Free (Groq) | Cheap (Gemini) | Standard (Sonnet) | Premium (Opus) |
|---|---|---|---|---|
| Web search | $0 | $0.014 | $0.10+ | $0.50+ |
| Text summary | $0 | $0.003 | $0.05+ | $0.30+ |
| Code generation | N/A | N/A | $0.10-0.50 | $0.50-2.00 |
| File operations | N/A | N/A | $0.10-0.50 | $0.50-2.00 |
| WO dispatch | $0 | $0.01 | $0.50-1.00 | $1.00-2.00 |
Key takeaway: Delegating research to Groq/Gemini instead of using Opus directly saves 10-100x per query.
Cost optimization strategiesโ
| Strategy | Savings | How |
|---|---|---|
| UB-first search | Massive | search_brain() before any external search โ answer may already be ingested |
| Delegate research | 10-100x | Use intel_search (Groq free) or search_web instead of Opus WebSearch |
| Batch patrol | Linear | Run patrol once for a domain, not individual searches |
| Engine matching | Variable | Match engine to task importance per selection guide |
| Progressive Disclosure | Token savings | Load skills on demand, not at startup |
| Concise prompts | Token savings | Slim rules, skills load only when invoked |
Monitoring and trackingโ
# Check engine availability and API key status
list_models()
# Check UB volume (indicates ingestion costs)
get_stats()
# Check WO history (each WO has engine + actual_hours)
list_work_orders(include_completed=True)
Monitoring gaps (planned)โ
| Feature | Status |
|---|---|
| Per-session token counter | Planned |
| Per-WO cost estimation | Planned |
| Monthly cost dashboard | Planned |
| Budget alerts | Planned |
| Cost-per-capability tracking | Planned |
Related pagesโ
| Page | Relationship |
|---|---|
| Choosing an Engine | Selection framework |
| Usage & Cost | Admin tracking tools |
| Cost Awareness | Governance rule |
| Engine Overview | Full engine catalog |