docs: label zai pricing section as Mistral hosted

The zai provider section prices Z.ai GLM models that are billed
through Mistral's marketplace (zai-glm-5-3 in harness logs, same
Mistral API key - no separate Z.ai account). The section keeps
the harness's model prefix as its name, and its new note says
who actually hosts/bills the models. Per-model notes now say
"Mistral hosted" where that is the route priced, and AGENTS.md's
price-update steps cover naming a provider section after the
harness log prefix while documenting the real billing route.
No rate values changed.

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>
This commit is contained in:
nvaldez
2026-11-10 19:40:51 +01:00
parent 18503a58f3
commit e1bb36954b
4 changed files with 23 additions and 6 deletions
+11
View File
@@ -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
+5
View File
@@ -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.
+6 -5
View File
@@ -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"
}
+1 -1
View File
@@ -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"