Model Register

MATERIALS.
EVERY PLAN AND EVERY MODEL ID
THIS BOX REACHES
PLANS. 5 metered subscriptions, all probed live
CATALOGUE. 10 provider endpoints · 640 model ids reachable
LADDER. 5 rungs, cheap to expensive
PROBE. 2026-09-29 07:57 UTC · read-only, no model is called to read this
SOURCE. ~/.hermes provider caches, auth pool, and the subscription pulse
01

Paid plans


KeyPlanLive usage
anthropic Anthropic · Claude Max
plan not reported · live
Claude Max. 5-hour session window plus a weekly cap shared by Claude and Claude Code.
Session window resets every 5 hours. A weekly cap applies across all models, reset at a fixed weekly time assigned to the account. Fable 5 / 5.1 included, capped at 50% of the weekly limit on Max tiers.
Current session — 4% used — resets in 3h
Current week — 78% used — resets in 22h
chatgpt ChatGPT · Plus
Prolite · live
ChatGPT plan used through the Codex endpoint by Hermes and the codex CLI.
Codex usage against the ChatGPT plan. One weekly window. Separate from any API billing.
Weekly — 1% used — resets in 4d
glm GLM · Coding Lite
GLM Coding Lite · live
GLM Coding Lite flat plan. Two credit buckets, this is the default Hermes chat model.
Two credit buckets, the 1 bucket on a weekly cycle and the 5 bucket on a 5-hour cycle.
Credit Limit · 5 — 1% used — resets in 3h · 1998 remaining
Credit Limit · 1 — 5% used — resets in 4d · 9404 remaining
grok Super Grok
Super Grok · live
SuperGrok. Credit-metered, two OAuth credentials in the pool.
Credit-based, metered per cycle.
Current period — 5% used — resets in 4d · Product usage: GrokBuild 5.0%
google Google · AI Pro
Google AI Pro · live
Google AI Pro subscription. Also the Antigravity / agy path for cheap coding jobs.
Subscription tier; the API key is a separate metered path and is the one that 429s.
API key valid (usable)
Meters are read from each provider's own usage endpoint. Where a provider reports no percentage, the bar is drawn full and the line says so rather than inventing a number.
02

The ladder


RungModelRole and price band
0 z-ai/glm-5.3-flash rung 0 - the default Hermes chat model
1 z-ai/glm-5.3-flash rung 1 - cheap, Z.AI Coding Lite flat plan (bucket 1 then 5)
https://api.z.ai/api
2 gpt-5.6-luna rung 2 - cheap, ChatGPT Plus flat plan, manager stand-in
https://chatgpt.com/backend-api/codex
3 z-ai/glm-5.3:US rung 3 - mid, Nous subscription backstop (GLM 5.3 US SKU)
https://inference-api.nousresearch.com/v1
4 claude-opus-5 rung 4 - expensive, Claude Max flat plan, last resort
03

Endpoints


ProviderModelsSample of what it serves, and which credentials are on it
nous 412 anthropic/claude-opus-4.1, anthropic/claude-opus-4.1:batch, anthropic/claude-opus-4.5, anthropic/claude-opus-4.5:batch, anthropic/claude-opus-4.6, anthropic/claude-opus-4.6:batch, anthropic/claude-opus-4.7, anthropic/claude-opus-4.7:batch, anthropic/claude-opus-4.8, anthropic/claude-opus-4.8:batch +402 more
diogo7dias@gmail.com (unused)
copilot 55 claude-fable-5.1, claude-fable-5, claude-opus-4.7, claude-opus-4.8-fast, claude-opus-4.8, claude-opus-5.5, claude-opus-5, claude-sonnet-5.5, claude-sonnet-5, copilot-search-a +45 more
gh auth token (unused)
openrouter 53 anthropic/claude-fable-5.1, anthropic/claude-fable-5, anthropic/claude-opus-5.5, anthropic/claude-opus-5, anthropic/claude-opus-4.8, anthropic/claude-sonnet-5, anthropic/claude-haiku-4.5, openai/gpt-6-astra, openai/gpt-6-astra-pro, openai/gpt-6-sol +43 more
opencode-go 42 deepseek-v4-flash, deepseek-v4-flash-vision-exp, deepseek-flash, deepseek-v4.1-flash, deepseek-v4-pro, glm-5.2, glm-5.3, grok-4.6, grok-4.7, muse-spark-1.2-contributor +32 more
h4rg0s-vps (unused)
anthropic 16 claude-fable-5.1, claude-fable-5, claude-opus-5, claude-sonnet-5, claude-opus-4-8, claude-opus-4-7, claude-opus-4-6, claude-sonnet-4-6, claude-opus-4-5-20251101, claude-sonnet-4-5-20250929 +6 more
gemini 15 gemini-flash-latest, gemini-flash-lite-latest, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-3.1-pro-preview, gemini-3.5-flash, gemini-2.5-pro, gemini-2.5-flash, gemini-3.7-flash, gemini-3-flash-preview +5 more
GOOGLE_API_KEY (ok) · GEMINI_API_KEY (ok)
openai-codex 14 gpt-6-astra, gpt-6-astra-900k, gpt-6-sol, gpt-6-sol-900k, gpt-6-luna, gpt-6-luna-900k, gpt-5.6-sol, gpt-5.6-sol-900k, gpt-5.6-terra, gpt-5.6-terra-900k +4 more
openai-codex-oauth-1 (unused)
zai 13 glm-5.3, glm-5.3-flash, glm-5.2, glm-5.1, glm-5, glm-5v-turbo, glm-5-turbo, glm-4.7, glm-4.5, glm-4.5-flash +3 more
ZAI_API_KEY (ok)
xai-oauth 13 grok-4.6, grok-4.7, grok-4.3, grok-4.20-0309-reasoning, grok-4.5, grok-4.20-0309-non-reasoning, grok-build-0.1, grok-4.20-multi-agent-0309, grok-imagine-image, grok-imagine-image-quality +3 more
xai-oauth-oauth-1 (ok) · device_code (ok)
opencode-free 7 jev-1.13-free, muse-spark-1.3-contributor-free, muse-spark-1.2-contributor-free, mimo-v2.5-free, ling-3.0-flash-fin-free, nemotron-3-ultra-free, nemotron-3.5-lightning-free
04

Who runs what


RuntimeModelJob
hermes z-ai/glm-5.3-flash chat, research, scheduling, orchestration
cron: lector-opds-reboot-watch deepseek-v4-flash-free
cron: brain-heartbeat glm-5.3-flash
cron: 4K watch — Reacher S04 + Lan glm-5.3-flash
cron: shipacademy-renewal-warning gemini-3.8-flash
opencode opencode-go/space-bunny-free