diff --git a/README.md b/README.md
index 9e066fabf6..79ac437b50 100644
--- a/README.md
+++ b/README.md
@@ -7,19 +7,19 @@
# π OmniRoute β The Free AI Gateway
-
+
@@ -1271,7 +1271,7 @@ MΓ©tricas canΓ΄nicas em 2026-08-24: **1.029 vΓdeos ΓΊnicos** Β· **11.132.922 vi
Resilience Guide Circuit breakers, cooldowns, queue, anti-thundering herd, TLS spoofing
Auto-Combo Engine 16-factor scoring, mode packs, self-healing
Proxy Guide 3-level proxy system, 1proxy marketplace, registry CRUD
-
Free Tiers Consolidated directory: 38 documented recurring pools / 446 cataloged free-tier entries
+
Free Tiers Consolidated directory: 35 documented recurring pools / 451 cataloged free-tier entries
Features Gallery Visual dashboard tour with screenshots
Codebase Documentation Beginner-friendly codebase walkthrough
diff --git a/docs/diagrams/README.md b/docs/diagrams/README.md
index 62ef3efff9..8d6a97fadb 100644
--- a/docs/diagrams/README.md
+++ b/docs/diagrams/README.md
@@ -34,7 +34,7 @@ inside GitHub's `
` sandbox:
| [combo-always-on.svg](./combo-always-on.svg) | style reference | Animated priority-combo fallback (4 layers, 16s loop). Edit the SVG directly β there is no `.mmd` source. |
| [cli-terminal.svg](./cli-terminal.svg) | README.md (root) | Compact half-height animated terminal (1200Γ350): 3 real CLI commands cycling with typewriter + scrolling subcommand ticker; first frame = completed providers screen. Edit the SVG directly β there is no `.mmd` source. |
| [compression-pipeline.svg](./compression-pipeline.svg) | README.md (root) | Animated 12-engine compression funnel (8s loop). Edit the SVG directly β there is no `.mmd` source. |
-| [free-tier-budget.svg](./free-tier-budget.svg) | README.md (root) | Animated free-tier budget card (~1.51B/mo quantified headline, 20-pool budget bar, per-pool grid, signup credits, 10s loop). Edit the SVG directly β there is no `.mmd` source. |
+| [free-tier-budget.svg](./free-tier-budget.svg) | README.md (root) | Animated free-tier budget card (~1.50B/mo quantified headline, 17-pool budget bar, per-pool grid, signup credits, 10s loop). Edit the SVG directly β there is no `.mmd` source. |
| [readme-hero.svg](./readme-hero.svg) | README.md (root) | Animated hero card (tagline, live provider/free-access headline, full-width compression bar demo, 6 stat chips). Edit the SVG directly β there is no `.mmd` source. |
| [promise-pillars.svg](./promise-pillars.svg) | README.md (root) | Animated "The Promise" 6-pillar card (12s border-highlight sweep). Edit the SVG directly β there is no `.mmd` source. |
| [why-pain-fix.svg](./why-pain-fix.svg) | README.md (root) | Animated "Why OmniRoute" 10-row pain-vs-fix ledger (15s green row sweep). Edit the SVG directly β there is no `.mmd` source. |
diff --git a/docs/diagrams/free-tier-budget.svg b/docs/diagrams/free-tier-budget.svg
index 51267b3ae2..48c643e632 100644
--- a/docs/diagrams/free-tier-budget.svg
+++ b/docs/diagrams/free-tier-budget.svg
@@ -1,5 +1,5 @@
-
- Pool-deduplicated chart of the 20 recurring free-token pools with positive published budgets, plus signup credits and uncapped providers shown separately.
+
+ Pool-deduplicated chart of the 17 recurring free-token pools with positive published budgets (plus Groq's five per-model caps as one segment), plus signup credits and uncapped providers shown separately.
@@ -61,10 +61,10 @@
- ~1.51B
+ ~1.50B
FREE TOKENS / MONTH · STEADY
up to ~2.13B in your first month — signup credits
- documented free tiers · 38 recurring pools · 446 catalog entries · one endpoint
+ documented free tiers · 35 recurring pools · 451 catalog entries · one endpoint
@@ -75,66 +75,62 @@
every rate limit · 24/7
we don't publish that
- ~1.51B
+ ~1.50B
each shared free pool
counted once ✓
13 providers ToS-flagged — we flag it · you decide
-
- WHERE IT COMES FROM · 20 QUANTIFIED RECURRING POOLS
+
+ WHERE IT COMES FROM · 17 QUANTIFIED POOLS + 5 GROQ PER-MODEL CAPS
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
- each segment = one recurring pool · widths floored so every pool shows · audited pool budgets below
+ each segment = one recurring pool (Groq = its five per-model caps) · widths floored so every pool shows · audited pool budgets below
-
+
Mistral 1.00B
- LLM7 150M
- Nara 150M
- Gemini 60M
+ Nara 210M
+ LLM7 150M
+ Groq 30M · 5 caps
Cerebras 30M
Cloudflare AI 30M
API Airforce 24M
- Ollama Cloud 20M
- Groq 15M
- Bluesminds 7.2M
- SambaNova 6M
- Arcee 4.8M
- Navy 4.5M
- BazaarLink 3.6M
- OpenRouter 1.2M
- Cohere 800K
- HuggingChat 500K
- Morph 400K
- Hugging Face 200K
- Kiro 25K
+ Bluesminds 7.2M
+ SambaNova 6M
+ Arcee 4.8M
+ Navy 4.5M
+ BazaarLink 3.6M
+ OpenRouter 1.2M
+ Cohere 800K
+ HuggingChat 500K
+ Morph 400K
+ Hugging Face 200K
+ Kiro 25K
@@ -178,10 +174,14 @@
OpenCode Zen
baidu
-
- …
+
+ Gemini
+
+ Ollama Cloud
+
+ …
- $10 OpenRouter top-up → +24M/mo
+ $10 OpenRouter top-up → +24M/mo
surfaced separately — never inflates the headline
diff --git a/docs/diagrams/readme-hero.svg b/docs/diagrams/readme-hero.svg
index 56c61abbb2..bb20ee7b90 100644
--- a/docs/diagrams/readme-hero.svg
+++ b/docs/diagrams/readme-hero.svg
@@ -1,4 +1,4 @@
-
+
Animated hero card: a pulse travels the divider line and a compression bar demo repeatedly shrinks a prompt by up to 95 percent; all headline content is static and readable on the first frame.
@@ -72,7 +72,7 @@
90+
FREE TIERS
- ~1.51B
+ ~1.50B
FREE TOKENS / MO
15β95%
diff --git a/docs/getting-started/FREE-TIERS-GUIDE.md b/docs/getting-started/FREE-TIERS-GUIDE.md
index fe7ebbcc49..a689315dd8 100644
--- a/docs/getting-started/FREE-TIERS-GUIDE.md
+++ b/docs/getting-started/FREE-TIERS-GUIDE.md
@@ -1,6 +1,6 @@
# Free Tiers Guide: Understand and Combine Free AI Access
-> **TL;DR**: OmniRoute registers 351 provider IDs, with **152 provider-catalog entries marked `hasFree`**. The stricter audited free-model catalog covers **39 recurring pool keys / 445 entries** (438 active + 7 discontinued). Connect several suitable providers for broader fallback capacity; every quota, approval rule, privacy policy, and paid-overage condition still applies.
+> **TL;DR**: OmniRoute registers 351 provider IDs, with **152 provider-catalog entries marked `hasFree`**. The stricter audited free-model catalog covers **35 recurring pool keys / 451 entries** (444 active + 7 discontinued). Connect several suitable providers for broader fallback capacity; every quota, approval rule, privacy policy, and paid-overage condition still applies.
---
@@ -161,9 +161,9 @@ The live, pool-deduplicated catalog currently reports:
| Metric | Current audited value | Interpretation |
| ---------------------------------------------------- | -----------------------------------------------: | ----------------------------------------------------------------------------------------- |
-| Recurring quantified grant | **~1.51B tokens/month** | Shared pools counted once; excludes uncapped providers from the sum |
+| Recurring quantified grant | **~1.50B tokens/month** | Shared pools counted once; excludes uncapped providers from the sum |
| First month with signup grants | **~2.13B tokens** | Recurring total plus one-time and recurring credits |
-| Audited free-model inventory | **39 recurring pool keys / 445 catalog entries** | 438 active + 7 discontinued; distinct from the 351-provider catalog |
+| Audited free-model inventory | **35 recurring pool keys / 451 catalog entries** | 444 active + 7 discontinued; distinct from the 351-provider catalog |
| Recurring/keyless free-forever providers represented | **55** | Unique providers across recurring daily/monthly/credit/uncapped and keyless catalog types |
| Provider catalog entries marked `hasFree` | **152 / 351** | Broader provider metadata; not all have a quantifiable recurring quota |
diff --git a/docs/reference/FREE_TIERS.md b/docs/reference/FREE_TIERS.md
index de03e3712b..298bb24c11 100644
--- a/docs/reference/FREE_TIERS.md
+++ b/docs/reference/FREE_TIERS.md
@@ -1,35 +1,37 @@
---
title: "Free Tiers & Free-Token Budget"
version: 3.8.50
-lastUpdated: 2026-08-31
+lastUpdated: 2026-09-02
---
# Free Tiers & Free-Token Budget
> **For Users**: Looking for a simple guide? See the [Free Tiers Guide](../getting-started/FREE-TIERS-GUIDE.md) for step-by-step instructions on getting free AI.
-> **Last researched:** 2026-06-17 β per-provider web research (official docs + last-7-days news, 50-agent pass with adversarial verification) refreshing every free-tier quota + ToS.
+> **Last researched:** 2026-06-17 β per-provider web research (official docs + last-7-days news, 50-agent pass with adversarial verification) refreshing every free-tier quota + ToS. **Partial re-audit 2026-09-02** (`gemini`, `ollama-cloud`, `groq`, `nara`, `mistral` β see the dated note below).
> **Source of truth (catalog):** `open-sse/config/freeModelCatalog.ts` (per-MODEL budgets, pool-deduped). The token-budget numbers below come from live web research and are an **approximation** β see [Methodology & caveats](#methodology--caveats).
## TL;DR β how much free inference does OmniRoute actually aggregate?
-| Metric | Tokens / month | Meaning |
-| ------------------------------------------- | ----------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| **Documented recurring grant (steady)** | **~1.51B** | Free-tier **pools** (per-model catalog), each shared pool counted **once**. The live source behind `/api/free-tier/summary` and the dashboard's Free-Tier Budget page. **Use this number.** |
-| **+ first month with signup credits** | **~2.13B** | Steady + one-time signup credits (Together $25, Z.AI 20M, DeepSeek 5M, β¦), deduped per account. **First month only** β does not recur. |
-| **+ permanently free, no published cap** | _un-quantifiable_ | `siliconflow`, `glm-cn` (GLM-4-Flash), `tencent`, `baidu`, `kilo-gateway`, `opencode-zen` β real recurring access, rate/concurrency-limited, **no token cap to count**. Listed, never summed (counting them at `RPMΓ24/7` is the inflation we reject). |
-| **+ deposit-unlock boost** | **+~24M** | A one-time **$10** OpenRouter top-up raises its free pool from 50 β 1000 req/day. Reported separately so it never inflates the steady number. |
-| Theoretical ceiling (all rate limits, 24/7) | ~10B | Sum of every provider rate limit extrapolated to non-stop use. **Not a guarantee** β do not headline this. |
+| Metric | Tokens / month | Meaning |
+| ------------------------------------------- | ----------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| **Documented recurring grant (steady)** | **~1.50B** | Free-tier **pools** (per-model catalog), each shared pool counted **once**. The live source behind `/api/free-tier/summary` and the dashboard's Free-Tier Budget page. **Use this number.** |
+| **+ first month with signup credits** | **~2.13B** | Steady + one-time signup credits (Together $25, Z.AI 20M, DeepSeek 5M, β¦), deduped per account. **First month only** β does not recur. |
+| **+ permanently free, no published cap** | _un-quantifiable_ | `siliconflow`, `glm-cn` (GLM-4-Flash), `tencent`, `baidu`, `kilo-gateway`, `opencode-zen`, `gemini`, `ollama-cloud` β real recurring access, rate/concurrency-limited, **no token cap to count**. Listed, never summed (counting them at `RPMΓ24/7` is the inflation we reject). |
+| **+ deposit-unlock boost** | **+~24M** | A one-time **$10** OpenRouter top-up raises its free pool from 50 β 1000 req/day. Reported separately so it never inflates the steady number. |
+| Theoretical ceiling (all rate limits, 24/7) | ~10B | Sum of every provider rate limit extrapolated to non-stop use. **Not a guarantee** β do not headline this. |
-**Honest headline:** _OmniRoute aggregates **~1.51B documented free tokens per month** (up to ~2.13B in your first month with signup credits) across 38 free-tier pools β plus a long tail of permanently-free, no-cap providers β and RTK + Caveman compression (15β95% token savings) stretches that further._
+**Honest headline:** _OmniRoute aggregates **~1.50B documented free tokens per month** (up to ~2.13B in your first month with signup credits) across 35 free-tier pools β plus a long tail of permanently-free, no-cap providers β and RTK + Caveman compression (15β95% token savings) stretches that further._
> **Why this dropped from the previous ~1.94B.** The 2026-06-17 refresh is an honesty correction, not a loss: `gemini` is now pool-deduped (was inflated by counting each Flash variant separately, 462M β 60M), `cloudflare-ai` corrected to its real 10k-Neurons/day (122M β 30M), `doubao` reclassified as a one-time signup credit (not recurring), and shut-down tiers removed (`chutes`/`phind`/`kluster` discontinued). Partly offset by `llm7` (correct 5M/day β 150M) and new free providers (Kilo, OpenCode Zen, Z.AI GLM-Flash).
>
> **Further corrected to ~1.37B in v3.8.42:** `longcat` was reclassified from a 150M/mo recurring grant to a one-time 10M signup credit after its free preview ended. Same honesty rule β no provider was dropped by mistake.
>
-> **Updated on 2026-08-26 after retiring Felo Web:** the source now reports 38 recurring pool keys. Felo Web is excluded while its GPL-derived provenance/licensing remains on HOLD. This is the live, CI-gated number (`check:docs-counts` fails the build if this drifts from `computeFreeModelTotals()`).
+> **Updated on 2026-08-26 after retiring Felo Web:** Felo Web is excluded while its GPL-derived provenance/licensing remains on HOLD; the source reported 38 pool keys at the time. The pool count is live and CI-gated (`check:docs-counts` fails the build if the numbers above drift from `computeFreeModelTotals()`).
+>
+> **Re-audited on 2026-09-02 against the providers' own pages** (sources: the `// evidence:` comments next to each entry in `open-sse/config/freeModelCatalog.data.ts`): `gemini` and `ollama-cloud` no longer publish a token figure (Google removed the per-model free table on 2025-12-23; Ollama's Free plan is "starter usage credits") and are now listed as **uncapped**, never summed (β80M); `groq` is five **per-model** 200K-TPD caps (6M each, +15M) with three retired IDs dropped; `nara` is one 7M/day bucket (+60M, 210M). `mistral`'s 1B is visible only in the account console β see _Evidence classes_ under Methodology. The source now reports 35 recurring pool keys (β3: `gemini` and `ollama-cloud` moved to the uncapped list, and Groq's per-model caps are not a shared pool) and ~1.50B steady.
-Biggest **documented** contributors: `mistral` 1.00B, `llm7` 150M, `nara` 150M, `gemini` 60M, `cerebras` 30M, `cloudflare-ai` 30M, `api-airforce` 24M. (`longcat` is excluded β its 10M LongCat-2.0 grant is a one-time, KYC-gated signup credit, not a recurring monthly budget.)
+Biggest **documented** contributors: `mistral` 1.00B, `nara` 210M, `llm7` 150M, `groq` 30M (five per-model caps), `cerebras` 30M, `cloudflare-ai` 30M, `api-airforce` 24M. (`longcat` is excluded β its 10M LongCat-2.0 grant is a one-time, KYC-gated signup credit, not a recurring monthly budget.)
> β οΈ The theoretical ceiling (~10B) is inflated by rate-limit-only providers with **no published token cap** (`tencent`, `siliconflow`, `nvidia`, `baidu`, `glm-cn`, `sparkdesk`) whose figures would be `RPM/TPM Γ 24/7 Γ 30d` β a theoretical maximum no single account will sustain. They are **excluded** from the defensible number (shown in the "permanently free, no cap" row instead). This is the same inflation that makes competitors' multi-billion claims unreliable.
@@ -72,8 +74,9 @@ purpose.
- **What an entry actually vouches for.** No entry carries a per-row confidence rating, and the API serves none β treat every figure above as an estimate of the same, unstated quality. Two facts are different, because they are curated by hand rather than inferred: 7 entries carry an independently documented hard stop, and 13 entries carry a prompt-training disclosure. `hardStopGuaranteed` is set only when the provider's own terms say that exceeding the free allowance refuses the request rather than silently starting to bill you, with the source in a comment next to the entry; it is never defaulted to `true`, and an entry nobody has verified stays unset. So a missing hard-stop flag means "not established", not "known to bill you".
- `estMonthlyFreeTokens` = recurring monthly tokens only. **One-time signup credits do not recur** and count as 0. Discontinued tiers are also 0.
- Daily token cap β `monthly = daily Γ 30`. Only RPD documented β `RPD Γ ~800 output tokens Γ 30`. Only RPM/TPM (no daily cap) β **uncapped** (see below).
-- **Permanently free, but no published token cap** (`siliconflow`, `glm-cn`, `tencent`, `baidu`, `kilo-gateway`, `opencode-zen`): these are real recurring free access, rate/concurrency-limited. We classify them `recurring-uncapped` and **never sum them** β multiplying `RPM Γ 24/7 Γ 30d` would produce a fantasy ceiling (the inflation we reject). They are listed so you know they exist.
+- **Permanently free, but no published token cap** (`siliconflow`, `glm-cn`, `tencent`, `baidu`, `kilo-gateway`, `opencode-zen`, `gemini`, `ollama-cloud`): these are real recurring free access, rate/concurrency-limited. We classify them `recurring-uncapped` and **never sum them** β multiplying `RPM Γ 24/7 Γ 30d` would produce a fantasy ceiling (the inflation we reject). They are listed so you know they exist.
- **Deposit-unlock boost:** a one-time small top-up that permanently raises a free quota (OpenRouter: $10 β 1000 req/day β +24M/mo). Reported as a separate figure, kept out of the steady headline.
+- **Evidence classes.** Every number in the catalog cites its source in a comment next to the entry: `public-page` (a provider page anyone can read), `api-public` (an unauthenticated endpoint of the provider, e.g. NaraRouter `/api/plans`), or `console-verified por ` (the figure is only visible inside an account console; the comment records who saw it and when, and the public page that says the cap exists). Today only `mistral` is console-verified. A number with no evidence comment is a bug.
---
@@ -190,14 +193,13 @@ purpose.
| Provider | Free type | Steady tokens/mo | First-month credit | ToS | Models |
| ---------------- | ------------- | ---------------- | ------------------ | --------- | ------ |
| `mistral` | recurring | ~1.00B | β | caution | 5 |
+| `nara` | recurring | ~210M | β | caution | 8 |
| `llm7` | recurring | ~150M | β | caution | 4 |
| `longcat` | one-time | β | 10M | caution | 1 |
-| `gemini` | recurring | ~60M | β | caution | 4 |
| `cerebras` | recurring | ~30M | β | caution | 2 |
| `cloudflare-ai` | recurring | ~30M | β | caution | 9 |
+| `groq` | recurring | ~30M | β | caution | 5 |
| `api-airforce` | recurring | ~24M | β | caution | 7 |
-| `ollama-cloud` | recurring | ~20M | β | ambiguous | 8 |
-| `groq` | recurring | ~15M | β | caution | 5 |
| `bluesminds` | recurring | ~7M | β | ambiguous | 22 |
| `sambanova` | recurring | ~6M | β | caution | 5 |
| `arcee-ai` | recurring | ~5M | β | caution | 1 |
@@ -210,7 +212,9 @@ purpose.
| `kiro` | recurring | ~25K | β | avoid | 12 |
| `glm-cn` | uncapped | uncapped\* | ~20M | ok | 4 |
| `baidu` | uncapped | uncapped\* | β | caution | 1 |
+| `gemini` | uncapped | uncapped\* | β | caution | 4 |
| `kilo-gateway` | uncapped | uncapped\* | β | caution | 7 |
+| `ollama-cloud` | uncapped | uncapped\* | β | ambiguous | 8 |
| `opencode-zen` | uncapped | uncapped\* | β | caution | 6 |
| `siliconflow` | uncapped | uncapped\* | β | caution | 10 |
| `tencent` | uncapped | uncapped\* | β | caution | 1 |