diff --git a/README.md b/README.md
index 38cbbc0..e8c64f3 100644
--- a/README.md
+++ b/README.md
@@ -4,8 +4,8 @@
 
 Qflash is a standalone, single-binary gateway that exposes Qwen3.8 model spaces on Hugging Face through a standard OpenAI-compatible API. It automatically detects and supports multiple upstream protocols:
 
-- gradio `/respond` endpoints (such as `https://microhero-qwen3-8-27b-uncensored-chat.hf.space`, running live on ZeroGPU)
-- direct OpenAI `/v1/chat/completions` endpoints (such as `https://wanyamaelis-qwen3-8-27b.hf.space` and `https://apathy-exe-qwen3-8-flash-next.hf.space`, running `llama-server` on CPU)
+- direct OpenAI `/v1/chat/completions` endpoints (such as `https://wanyamaelis-qwen3-8-27b.hf.space` and `https://apathy-exe-qwen3-8-flash-next.hf.space`, running persistent `llama-server` instances on CPU with zero quota limits)
+- gradio `/respond` endpoints (supported for custom spaces such as `https://microhero-qwen3-8-27b-uncensored-chat.hf.space`)
 - gradio `/chat_response` endpoints (such as `https://halvo78-qwen3-8-flash-next-playground.hf.space`)
 
 It translates standard `/v1/chat/completions` and `/v1/models` requests and Server-Sent Events (SSE) stream protocols into upstream formats, allowing any standard OpenAI-compatible client, agent, or IDE to interface with Qwen3.8 models without modification.
@@ -13,7 +13,7 @@ It translates standard `/v1/chat/completions` and `/v1/models` requests and Serv
 ## Features
 
 - openai-compatible chat completions (streaming and non-streaming)
-- automatic upstream failover across ZeroGPU and non-ZeroGPU endpoints
+- automatic upstream failover across configured non-ZeroGPU endpoints
 - smart endpoint cooldown (5 minutes on quota exhaustion, 30 seconds on network errors)
 - automatic upstream endpoint detection (`respond`, `openai`, `chat_response`)
 - deep reasoning extraction with thinking trace passthrough (`<think>` tags and blockquotes mapped to `reasoning_content`)
@@ -30,21 +30,21 @@ It translates standard `/v1/chat/completions` and `/v1/models` requests and Serv
 
 | Space | Model | Hardware | Protocol | Notes |
 |---|---|---|---|---|
-| `MicroHERO/qwen3.8-27b-uncensored-chat` *(primary)* | Qwen3.8-27B Uncensored | ZeroGPU (A10G) | Gradio `/respond` | Fast live GPU inference (~2s), uncensored weights |
-| `Wanyamaelis/Qwen3.8-27B` *(fallback)* | Qwen3.8-27B (MTP) | CPU basic (8 vCPU) | Native OpenAI `/v1` | Non-ZeroGPU, no quota limits, fast speculative decoding (~5s) |
-| `apathy-exe/Qwen3.8-27B` | Qwen3.8-27B (MTP) | CPU (OpenMP/AVX512) | Native OpenAI `/v1` | Non-ZeroGPU, no quota limits, speculative decoding |
-| `apathy-exe/Qwen3.8-Flash-Next` | Qwen3.8-Flash-Next (~177B) | CPU (OpenMP/AVX512) | Native OpenAI `/v1` | Non-ZeroGPU, no quota limits, full 177B Flash-Next model |
+| `Wanyamaelis/Qwen3.8-27B` *(primary)* | Qwen3.8-27B (MTP) | CPU basic (8 vCPU) | Native OpenAI `/v1` | Default endpoint, non-ZeroGPU, no quota limits, fast speculative decoding (~5s) |
+| `apathy-exe/Qwen3.8-27B` *(fallback)* | Qwen3.8-27B (MTP) | CPU (OpenMP/AVX512) | Native OpenAI `/v1` | Non-ZeroGPU, no quota limits, speculative decoding |
+| `apathy-exe/Qwen3.8-Flash-Next` *(fallback)* | Qwen3.8-Flash-Next (~177B) | CPU (OpenMP/AVX512) | Native OpenAI `/v1` | Non-ZeroGPU, no quota limits, full 177B Flash-Next model |
+| `MicroHERO/qwen3.8-27b-uncensored-chat` | Qwen3.8-27B Uncensored | ZeroGPU (A10G) | Gradio `/respond` | Fast live GPU inference, can be configured via custom `-endpoints` |
 | `Halvo78/qwen3-8-flash-next-playground` | Qwen3.8-Flash-Next | CPU basic | Gradio `/chat_response` | Sandbox client; requires BYOK API key/base URL |
 
-### Auto-failover and ZeroGPU quota handling
+### Auto-failover and quota handling
 
-Spaces running on ZeroGPU provide free A10G compute, but anonymous requests share a small pool per IP address. When ZeroGPU runs limit is reached, upstream returns a quota error (`429` or `ZeroGPU runs limit`).
+Default endpoints run on persistent non-ZeroGPU hardware with no daily runs limit. When custom ZeroGPU spaces are configured, anonymous requests share a small pool per IP address. When runs limit is reached, upstream returns a quota error (`429` or `ZeroGPU runs limit`).
 
-Qflash handles this seamlessly:
+Qflash handles upstream reliability seamlessly:
 
-- with auto-failover enabled (default), when a ZeroGPU space hits its runs limit, it is placed on a 5-minute cooldown and the gateway automatically fails over to the next configured endpoint (e.g. `wanyamaelis-qwen3-8-27b`, which runs on CPU with zero quota limits)
-- transient network errors trigger a shorter 30-second cooldown before retrying
-- you can also provide a free Hugging Face personal access token (`https://huggingface.co/settings/tokens`) via the `HF_TOKEN` environment variable, the `-hf-token` CLI flag, or the `Authorization: Bearer hf_...` header to authenticate ZeroGPU requests directly
+- with auto-failover enabled (default), when an endpoint encounters an error or timeout, it is placed on cooldown and the gateway automatically fails over to the next configured endpoint
+- transient network errors trigger a 30-second cooldown, while quota limits trigger a 5-minute cooldown
+- optional ZeroGPU or private spaces can be authenticated using a Hugging Face personal access token (`https://huggingface.co/settings/tokens`) via the `HF_TOKEN` environment variable, the `-hf-token` CLI flag, or the `Authorization: Bearer hf_...` header
 
 ## Installation
 
@@ -80,9 +80,11 @@ The gateway advertises the following models under `/v1/models`:
 
 | Model ID | Target model | Description |
 |---|---|---|
-| `Qwen/Qwen3.8-27B-Uncensored` | `Qwen/Qwen3.8-27B-Uncensored` | Default primary live model |
+| `Qwen/Qwen3.8-27B` | `Qwen/Qwen3.8-27B` | Default primary live model |
+| `Qwen/Qwen3.8-27B-Uncensored` | `Qwen/Qwen3.8-27B-Uncensored` | Uncensored model identifier |
 | `Qwen/Qwen3.8-Flash-Next` | `Qwen/Qwen3.8-Flash-Next` | Flash-Next model identifier |
-| `qwen3.8-27b-uncensored` | `Qwen/Qwen3.8-27B-Uncensored` | Standard lowercase alias |
+| `qwen3.8-27b` | `Qwen/Qwen3.8-27B` | Standard lowercase alias |
+| `qwen3.8-27b-uncensored` | `Qwen/Qwen3.8-27B-Uncensored` | Uncensored lowercase alias |
 | `qwen3.8-flash-next` | `Qwen/Qwen3.8-Flash-Next` | Flash-Next lowercase alias |
 | `qwen-flash-next` | `Qwen/Qwen3.8-Flash-Next` | Shorthand alias |
 | `qwen-flash` | `Qwen/Qwen3.8-Flash-Next` | Quick convenience alias |
@@ -98,15 +100,15 @@ Run the gateway with default auto-failover endpoints:
 qflash
 ```
 
-By default, this listens on `http://127.0.0.1:8080` with failover configured across `MicroHERO` (ZeroGPU), `wanyamaelis` (CPU non-ZeroGPU), and `apathy-exe` endpoints.
+By default, this listens on `http://127.0.0.1:8080` with failover configured across persistent non-ZeroGPU endpoints (`wanyamaelis` and `apathy-exe`).
 
 Available flags:
 
 - `-port` — tcp port to listen on (default `8080`)
-- `-endpoints` / `-endpoint` — comma-separated upstream space or OpenAI URLs (default list of 4 endpoints, `QFLASH_ENDPOINTS` / `QFLASH_ENDPOINT` env)
+- `-endpoints` / `-endpoint` — comma-separated upstream space or OpenAI URLs (default list of 3 non-ZeroGPU endpoints, `QFLASH_ENDPOINTS` / `QFLASH_ENDPOINT` env)
 - `-failover` / `-auto-failover` — enable automatic failover across endpoints on quota exhaustion or error (default `true`, `QFLASH_FAILOVER` env)
 - `-mode` — upstream protocol mode: `auto`, `respond`, `chat_response`, `openai` (default `auto`, `QFLASH_MODE` env)
-- `-model` — exposed model name (default `Qwen/Qwen3.8-27B-Uncensored`, `QFLASH_MODEL` env)
+- `-model` — exposed model name (default `Qwen/Qwen3.8-27B`, `QFLASH_MODEL` env)
 - `-thinking` / `-enable-thinking` — enable chain-of-thought reasoning by default (default `true`)
 - `-hf-token` / `-token` — Hugging Face API token for ZeroGPU quota or private spaces (`HF_TOKEN` env)
 - `-api-key` — upstream inference engine API key for BYOK mode (`OPENAI_API_KEY` / `QWEN_API_KEY` env)
diff --git a/main.go b/main.go
index 0d88905..0f3d6cb 100644
--- a/main.go
+++ b/main.go
@@ -32,7 +32,6 @@ var (
   ConfiguredModel       string
   EnableThinkingDefault = true
   DefaultEndpoints      = []string{
-    "https://microhero-qwen3-8-27b-uncensored-chat.hf.space",
     "https://wanyamaelis-qwen3-8-27b.hf.space",
     "https://apathy-exe-qwen3-8-27b.hf.space",
     "https://apathy-exe-qwen3-8-flash-next.hf.space",
@@ -509,13 +508,15 @@ func EffectiveModelID(reqModel string, defaultModel string) string {
   switch strings.ToLower(clean) {
   case "qwen/qwen3.8-flash-next", "qwen3.8-flash-next", "qwen-flash-next", "qwen-flash", "qwen3.8-flash":
     return "Qwen/Qwen3.8-Flash-Next"
-  case "qwen/qwen3.8-27b-uncensored", "qwen3.8-27b-uncensored", "qwen-27b", "qwen3.8-27b":
+  case "qwen/qwen3.8-27b", "qwen3.8-27b", "qwen-27b":
+    return "Qwen/Qwen3.8-27B"
+  case "qwen/qwen3.8-27b-uncensored", "qwen3.8-27b-uncensored":
     return "Qwen/Qwen3.8-27B-Uncensored"
   case "qwen":
     if defaultModel != "" {
       return defaultModel
     }
-    return "Qwen/Qwen3.8-Flash-Next"
+    return "Qwen/Qwen3.8-27B"
   default:
     return clean
   }
@@ -1250,7 +1251,7 @@ func parseEndpointList(rawList []string) []*EndpointNode {
 
 func NewQwenService(endpoints []string, modelName, mode, token, apiKey, baseURL, socksProxy string, enableThinking, autoFailover bool) *QwenService {
   if modelName == "" {
-    modelName = "Qwen/Qwen3.8-27B-Uncensored"
+    modelName = "Qwen/Qwen3.8-27B"
   }
   if mode == "" {
     mode = "auto"
@@ -1287,13 +1288,15 @@ func (s *QwenService) ListModels() []ModelItem {
   now := time.Now().Unix()
   primaryID := s.modelName
   if primaryID == "" {
-    primaryID = "Qwen/Qwen3.8-27B-Uncensored"
+    primaryID = "Qwen/Qwen3.8-27B"
   }
 
   candidates := []string{
     primaryID,
+    "Qwen/Qwen3.8-27B",
     "Qwen/Qwen3.8-27B-Uncensored",
     "Qwen/Qwen3.8-Flash-Next",
+    "qwen3.8-27b",
     "qwen3.8-27b-uncensored",
     "qwen3.8-flash-next",
     "qwen-flash-next",
@@ -2204,7 +2207,7 @@ func main() {
   autoFailover := flag.Bool("failover", true, "Enable automatic failover across endpoints on error or quota limit")
   flag.BoolVar(autoFailover, "auto-failover", true, "Alias for -failover")
 
-  defaultModelVal := "Qwen/Qwen3.8-27B-Uncensored"
+  defaultModelVal := "Qwen/Qwen3.8-27B"
   if envModel := os.Getenv("QFLASH_MODEL"); envModel != "" {
     defaultModelVal = envModel
   }
diff --git a/qflash_test.go b/qflash_test.go
index ccc019c..9a78d67 100644
--- a/qflash_test.go
+++ b/qflash_test.go
@@ -71,8 +71,12 @@ func TestEffectiveModelID(t *testing.T) {
     "qwen3.8-flash-next":    def,
     "qwen-flash-next":       def,
     "qwen-flash":            def,
-    "qwen3.8-flash":         def,
     "Qwen/Qwen3.8-Flash-Next": def,
+    "qwen3.8-27b":           "Qwen/Qwen3.8-27B",
+    "qwen-27b":              "Qwen/Qwen3.8-27B",
+    "Qwen/Qwen3.8-27B":      "Qwen/Qwen3.8-27B",
+    "qwen3.8-27b-uncensored": "Qwen/Qwen3.8-27B-Uncensored",
+    "Qwen/Qwen3.8-27B-Uncensored": "Qwen/Qwen3.8-27B-Uncensored",
     "custom-org/my-model":   "custom-org/my-model",
   }