diff --git a/.vibe/ai-usage-cost.md b/.vibe/ai-usage-cost.md index 42ee058..11d8cd2 100644 --- a/.vibe/ai-usage-cost.md +++ b/.vibe/ai-usage-cost.md @@ -122,6 +122,17 @@ And add the cost information to this file for the current session. corrected; verified 2026-11-10); AGENTS.md documents the price-update procedure; 4 regression tests added. +#### (pending) - docs: label zai pricing section as Mistral hosted +- **Date**: 2026-11-10 +- **Model**: zai:zai-glm-5-3 +- **Session Cost**: $1.46 (running total at commit time) +- **Turn Cost**: $0.18 +- **Total for commit**: $1.46 +- **Notes**: pricing.json zai section gets a "(Mistral hosted)" note + (no separate Z.ai account; section named after the harness model + prefix), per-model notes clarified; AGENTS.md price-update steps + now cover section naming. No rate changes. + --- ## Instructions for Contributors diff --git a/AGENTS.md b/AGENTS.md index 3011a15..80f9d41 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -252,6 +252,11 @@ How to update prices in the future: follow that rule (e.g. GLM 5.3 direct: $0.26/M cached vs $0.14 via Mistral's marketplace) - always take the cached price from the same page as the rate you record, and say in the `note` which route the entry prices. + Name a provider section after the **provider/model prefix the harness logs + use** (e.g. "zai-glm-5-3" -> the "zai" section), even when the model is + billed through another host; then say so in the section `note` (e.g. the + zai section's "(Mistral hosted)" note) so nobody expects a second API + account. 3. **Watch for promotional/sale rates.** If a price is promotional (e.g. Mistral Large 4's sale), record the sale rate in the price fields and keep the regular rate in the `note`, so it can be restored when the sale ends. diff --git a/agent_cost_estimator/pricing.json b/agent_cost_estimator/pricing.json index f21b075..f2bfdd3 100644 --- a/agent_cost_estimator/pricing.json +++ b/agent_cost_estimator/pricing.json @@ -124,12 +124,13 @@ }, "zai": { "currency": "USD", + "note": "Z.ai GLM models as hosted through Mistral's marketplace (Mistral API key, no separate Z.ai account). Section is named zai because that is the provider/model prefix in harness logs (zai-glm-5-3).", "models": { "default": { "input_price": 1.4, "cached_input_price": 0.14, "output_price": 4.4, - "note": "Z.ai default rates - matches GLM 5.3 via Mistral's marketplace", + "note": "Z.ai default rates - matches GLM 5.3 (Mistral hosted)", "source": "https://docs.mistral.ai/inference/pricing", "date": "2026-11-10" }, @@ -137,7 +138,7 @@ "input_price": 1.4, "cached_input_price": 0.14, "output_price": 4.4, - "note": "GLM 5.3 as billed via Mistral's marketplace (zai-glm-5-3); Z.ai direct lists cached input at $0.26/1M - see https://docs.z.ai/guides/overview/pricing", + "note": "GLM 5.3 (Mistral hosted; billed via Mistral's marketplace as zai-glm-5-3). Z.ai direct API lists cached input at $0.26/1M - see https://docs.z.ai/guides/overview/pricing", "source": "https://docs.mistral.ai/inference/pricing", "date": "2026-11-10" }, @@ -145,15 +146,15 @@ "input_price": 0.15, "cached_input_price": 0.03, "output_price": 0.5, - "note": "GLM 5.3 Flash - efficient MoE model (320B total, 18B active)", - "source": "https://docs.z.ai/guides/overview/pricing", + "note": "GLM 5.3 Flash (Mistral hosted) - efficient MoE model (320B total, 18B active); same rates on Z.ai direct", + "source": "https://docs.mistral.ai/inference/pricing", "date": "2026-11-10" }, "zai-glm-5.3-flashx": { "input_price": 0.37, "cached_input_price": 0.075, "output_price": 1.25, - "note": "GLM 5.3 FlashX - advanced variant", + "note": "GLM 5.3 FlashX - advanced variant; not listed on Mistral's pricing page, rates are Z.ai direct (would differ if Mistral hosts it later)", "source": "https://docs.z.ai/guides/overview/pricing", "date": "2026-11-10" } diff --git a/pyproject.toml b/pyproject.toml index 81401c4..16325a7 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta" [project] name = "agent-cost-estimator" -version = "0.4.8" +version = "0.4.9" description = "Report token usage and estimated USD cost of AI agent sessions from local harness logs" readme = "README.md" requires-python = ">=3.9"