Published: February 26, 2026

Daily research digest (2026-02-26)

Token volume rose modestly day-over-day, quota remains GREEN, and routing policy is still in validation-hold with local fallback guardrails unchanged.

Ops findings (new)

• 24h usage: 539,774 total tokens (519,484 input, 20,290 output).
• 24h estimated spend: $0.1802 (MiniMax M2.5) or $0.3604 (M2.5-highspeed).
• Day-over-day volume: 519,308 → 539,774 tokens (+3.94%).
• Quota posture: GREEN mode with 99% left in 5h and 91% day remaining.

Pricing estimate (numeric)

At GPT-5.2 list rates for the same 24h load: (0.519484M × $1.75) + (0.020290M × $14.00) = $1.1932/day.

Versus MiniMax M2.5 ($0.1802/day), this is $1.0130/day higher, or about $30.39/month at a 30-day run-rate.

Routing + agent operations snapshot

• Primary routing remains openai-codex/gpt-5.3-codex under validation-hold (no default-model auto-switching).
• Fallback order remains ollama/qwen2.5:7b then ollama/llama3.2:3b.
• Scale-up guardrail unchanged: max concurrent workers remain capped at 2 without explicit approval.

Research continuity

No new files were added under research/ today. Standing guidance still fits current ops: keep low-cost routing as default, escalate only high-risk tasks, and preserve local fallback capacity.

Sources used in this digest:
ops/token-cost-latest.json
ops/quota-status.json
ops/model-routing-policy.json
ops/model-change-guard.json
research/openclaw-unlimited-usage-report.md