diff --git a/CLAUDE.md b/CLAUDE.md
index d184e01..05a5c6e 100644
--- a/CLAUDE.md
+++ b/CLAUDE.md
@@ -121,7 +121,7 @@ Server configuration:
 
 Model name prefixes determine routing:
 - **OpenAI**: gpt-4.1, gpt-5, gpt-5-mini, gpt-5.2, gpt-5.6-sol/terra/luna, o4-mini; image generation: gpt-image-2
-- **Anthropic**: claude-sonnet-4-0/4-5/4-6, claude-sonnet-5, claude-haiku-4-5, claude-opus-4-5/4-6/4-7/4-8, claude-opus-5, claude-fable-5, claude-3-7-sonnet, claude-3-5-haiku
+- **Anthropic**: claude-sonnet-4-0/4-5/4-6, claude-sonnet-5, claude-haiku-4-5, claude-opus-4-5/4-6/4-7/4-8, claude-opus-5, claude-fable-5, claude-fable-5-1, claude-3-7-sonnet, claude-3-5-haiku
 - **Google**: gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.5-pro, gemini-3-pro-preview, gemini-3-flash-preview, gemini-3.1-pro-preview, gemini-3.5-flash; image generation: gemini-2.5-flash-image, gemini-3.1-flash-image
 - **xAI**: grok-2, grok-3, grok-3-mini, grok-4, grok-4.3, grok-4.5, grok-4.6, grok-4-fast, grok-4-1-fast; image generation: grok-2-image
 - **ByteDance** (BytePlus ModelArk, OpenAI-compatible, ap-southeast): seed-1.6, seed-1.8, seed-2.0-lite, deepseek-v4-flash, deepseek-v4-pro, glm-5.2 (Z.ai's model served via a ModelArk deployment endpoint); image generation: seedream-4.0, seedream-5.0-lite, seedance-4.5, seedance-5.0
diff --git a/README.md b/README.md
index c0c00ff..ee4c2e4 100644
--- a/README.md
+++ b/README.md
@@ -34,7 +34,7 @@ The gateway solves this by running inside a hardware-isolated Nitro Enclave wher
 | Provider | Models |
 |----------|--------|
 | OpenAI | gpt-4.1, gpt-5, gpt-5-mini, gpt-5.6-sol, gpt-5.6-terra, gpt-5.6-luna, o4-mini |
-| Anthropic | claude-sonnet-4-5, claude-sonnet-4-6, claude-haiku-4-5, claude-opus-4-5, claude-opus-4-6 |
+| Anthropic | claude-fable-5-1, claude-sonnet-4-5, claude-sonnet-4-6, claude-haiku-4-5, claude-opus-4-5, claude-opus-4-6 |
 | Google | gemini-3.8-flash, gemini-3.7-flash, gemini-3.6-flash, gemini-3.5-flash-lite, gemini-2.5-flash, gemini-2.5-flash-lite, gemini-2.5-pro, gemini-3-pro-preview, gemini-3-flash-preview |
 | xAI | grok-4.6, grok-4.5, grok-4.3, grok-4, grok-4-fast, grok-4-1-fast, grok-4-1-fast-non-reasoning |
 | ByteDance | seed-1.6, seed-1.8, seed-2.0-lite, deepseek-v4-flash, deepseek-v4-pro |
diff --git a/tee_gateway/model_registry.py b/tee_gateway/model_registry.py
index 67121d5..1b69f76 100644
--- a/tee_gateway/model_registry.py
+++ b/tee_gateway/model_registry.py
@@ -313,6 +313,18 @@ class SupportedModel(Enum):
         output_price_usd=Decimal("0.00005"),
         supports_temperature=False,
     )
+    # Claude Fable 5.1 — supersedes Fable 5 as Anthropic's most capable widely
+    # released model (GA 2026-09-01). Same sticker input/output pricing as
+    # Fable 5; the only pricing change is a 75%-cheaper cached-token read rate,
+    # which this registry doesn't model (base input/output only). Adaptive-
+    # thinking-only; like Opus 4.7+/Fable 5 it rejects `temperature` (HTTP 400).
+    CLAUDE_FABLE_5_1 = ModelConfig(
+        provider="anthropic",
+        api_name="claude-fable-5-1",
+        input_price_usd=Decimal("0.00001"),
+        output_price_usd=Decimal("0.00005"),
+        supports_temperature=False,
+    )
 
     # ── Google Gemini ───────────────────────────────────────────────────
     # Note: gemini-2.5-flash, gemini-2.5-pro, and gemini-2.5-flash-lite are scheduled
@@ -681,6 +693,7 @@ class SupportedModel(Enum):
     "claude-opus-4-8": SupportedModel.CLAUDE_OPUS_4_8,
     "claude-opus-5": SupportedModel.CLAUDE_OPUS_5,
     "claude-fable-5": SupportedModel.CLAUDE_FABLE_5,
+    "claude-fable-5-1": SupportedModel.CLAUDE_FABLE_5_1,
     # Google
     "gemini-2.5-flash": SupportedModel.GEMINI_2_5_FLASH,
     "gemini-2.5-pro": SupportedModel.GEMINI_2_5_PRO,
diff --git a/tests/test_pricing.py b/tests/test_pricing.py
index 1a8a4d3..467a66f 100644
--- a/tests/test_pricing.py
+++ b/tests/test_pricing.py
@@ -145,6 +145,15 @@ def test_claude_fable_5_resolves(self):
         # Adaptive-thinking-only; rejects the `temperature` field (HTTP 400)
         self.assertFalse(cfg.supports_temperature)
 
+    def test_claude_fable_5_1_resolves(self):
+        cfg = get_model_config("claude-fable-5-1")
+        self.assertEqual(cfg.provider, "anthropic")
+        self.assertEqual(cfg.api_name, "claude-fable-5-1")
+        self.assertEqual(cfg.input_price_usd, Decimal("0.00001"))
+        self.assertEqual(cfg.output_price_usd, Decimal("0.00005"))
+        # Adaptive-thinking-only; rejects the `temperature` field (HTTP 400)
+        self.assertFalse(cfg.supports_temperature)
+
     # ── OpenAI ──────────────────────────────────────────────────────────────
 
     def test_gpt_4_1_resolves(self):
@@ -710,6 +719,13 @@ def test_claude_opus_5_cost(self):
         # Same price tier as opus-4-5/4-6/4-7/4-8: 1000*0.000005 + 500*0.000025 = 0.0175 USD
         self.assertEqual(cost, 17_500_000_000_000_000)
 
+    def test_claude_fable_5_1_cost(self):
+        cost = self._calc("claude-fable-5-1", 1000, 500)
+        expected = _expected_cost_opg("claude-fable-5-1", 1000, 500)
+        self.assertEqual(cost, expected)
+        # Same price tier as fable-5: 1000*0.00001 + 500*0.00005 = 0.035 USD
+        self.assertEqual(cost, 35_000_000_000_000_000)
+
     # ── Google Gemini ────────────────────────────────────────────────────────
 
     def test_gemini_2_5_flash_cost(self):