diff --git a/README.md b/README.md
index aaaaade4ab..eac646a990 100644
--- a/README.md
+++ b/README.md
@@ -7,7 +7,7 @@
# ๐ OmniRoute โ The Free AI Gateway
-
+
@@ -17,9 +17,9 @@
-> Stacking free tiers by hand is painful โ dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **476 free-tier entries across 39 recurring pool keys** and computes the token headline from the **20 pools with a published positive monthly budget**, deduplicated by shared pool. The result stays visible on the dashboard (`/dashboard/free-tiers`).
+> Stacking free tiers by hand is painful โ dozens of SDKs, dozens of rate limits, and no idea how much you actually have. OmniRoute catalogs **476 free-tier entries across 39 recurring pool keys** and computes the token headline from the **21 pools with a published positive monthly budget**, deduplicated by shared pool. The result stays visible on the dashboard (`/dashboard/free-tiers`).
-
+
> Animated summary of the live `/dashboard/free-tiers` page. Full methodology (pool dedupe, credit tiers, provider terms): **[docs/reference/FREE_TIERS.md](docs/reference/FREE_TIERS.md)**.
>
@@ -648,7 +648,7 @@ of your shell history. โ [CLI Integrations](docs/guides/CLI-INTEGRATIONS.md)
-> **357 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **437 per-model rows**, **39 recurring pools** and **54 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
+> **357 registered providers** across the canonical chat, media, search, local, cloud-agent and system collections, including **152 carrying `hasFree: true` discovery metadata**. The chat model registry covers **229 providers / 2,554 distinct provider-model pairs / 1,283 raw model IDs**; the separate free-budget catalog has **476 per-model rows**, **39 recurring pools** and **54 recurring/keyless free-forever providers**. These are different denominators by design; definitions and pool-deduped calculations live in the [Provider Reference](docs/reference/PROVIDER_REFERENCE.md) and [Free Tiers](docs/reference/FREE_TIERS.md).
diff --git a/docs/diagrams/cli-terminal.svg b/docs/diagrams/cli-terminal.svg
index 377ec04fa4..ede06fa8e0 100644
--- a/docs/diagrams/cli-terminal.svg
+++ b/docs/diagrams/cli-terminal.svg
@@ -6,7 +6,7 @@
omniroute — 86 top-level commands
-
omniroute providers listOmniRoute Providers1f3a9c2e anthropic Claude Max 20x active8c2d5b1a codex Codex Pro (team) activef4e0a97b glm GLM Coding Plan active03bd6e5f kimi Kimi K2 free active… 351 more providers
+omniroute providers listOmniRoute Providers1f3a9c2e anthropic Claude Max 20x active8c2d5b1a codex Codex Pro (team) activef4e0a97b glm GLM Coding Plan active03bd6e5f kimi Kimi K2 free active… 353 more providers
$
omniroute providers list
@@ -14,7 +14,7 @@
-OmniRoute Providers1f3a9c2e anthropic Claude Max 20x active8c2d5b1a codex Codex Pro (team) activef4e0a97b glm GLM Coding Plan active03bd6e5f kimi Kimi K2 free active… 351 more providers
+OmniRoute Providers1f3a9c2e anthropic Claude Max 20x active8c2d5b1a codex Codex Pro (team) activef4e0a97b glm GLM Coding Plan active03bd6e5f kimi Kimi K2 free active… 353 more providers
$
@@ -32,7 +32,7 @@
-OmniRoute Health Status: healthy Uptime: 4d 12h 33m Requests (24h): 18,412 p95: 412ms Breakers: ● 24 closed ◒ 1 half-open ○ 0 open Providers: 355 registered 150+ free tiers… live: /dashboard · omniroute status
+OmniRoute Health Status: healthy Uptime: 4d 12h 33m Requests (24h): 18,412 p95: 412ms Breakers: ● 24 closed ◒ 1 half-open ○ 0 open Providers: 357 registered 150+ free tiers… live: /dashboard · omniroute status
diff --git a/docs/diagrams/comparison-table.svg b/docs/diagrams/comparison-table.svg
index f09279ba6d..3b3a595dc5 100644
--- a/docs/diagrams/comparison-table.svg
+++ b/docs/diagrams/comparison-table.svg
@@ -23,7 +23,7 @@
Providers
- 352
+ 357
40+
400+*
~5
diff --git a/docs/diagrams/readme-hero.svg b/docs/diagrams/readme-hero.svg
index edf29fcc7f..5fc2bcaff5 100644
--- a/docs/diagrams/readme-hero.svg
+++ b/docs/diagrams/readme-hero.svg
@@ -66,7 +66,7 @@
- 355
+ 357
AI PROVIDERS
150+
diff --git a/docs/reference/FREE_TIERS.md b/docs/reference/FREE_TIERS.md
index c51829a93c..ea05ef99ea 100644
--- a/docs/reference/FREE_TIERS.md
+++ b/docs/reference/FREE_TIERS.md
@@ -184,7 +184,7 @@ purpose.
---
-## Per-provider free-tier (refreshed 2026-06-17)
+## Per-provider free-tier (refreshed 2026-09-02)
> Regenerated from the per-model catalog (`open-sse/config/freeModelCatalog.ts`), pool-deduped. Sorted by recurring steady tokens/mo. `uncapped*` = permanently free but no published token cap (rate/concurrency-limited) โ real access, **not** summed into the headline. `โ` = credit-only / keyless / not token-quantifiable.
diff --git a/src/shared/constants/providers/apikey/gateways.ts b/src/shared/constants/providers/apikey/gateways.ts
index 66b0011e42..1c9aea3179 100644
--- a/src/shared/constants/providers/apikey/gateways.ts
+++ b/src/shared/constants/providers/apikey/gateways.ts
@@ -1351,7 +1351,7 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
authHint:
"Create a free account at xkiro.com and paste the key here (Bearer; x-api-key also accepted).",
apiHint:
- "OpenAI-compatible endpoint at https://api.xkiro.com/v1. Public /v1/models tags free rows with access_tier=free; paid models answer 403 on the free plan.",
+ "OpenAI-compatible endpoint at https://api.xkiro.com/v1. Public /v1/models tags free rows with access_tier=free; paid models are rejected on the free plan.",
},
regolo: {
id: "regolo",