diff --git a/providers/cloudflare-ai-gateway/curation.toml b/providers/cloudflare-ai-gateway/curation.toml
index 8772ea87336..697217a5ffb 100644
--- a/providers/cloudflare-ai-gateway/curation.toml
+++ b/providers/cloudflare-ai-gateway/curation.toml
@@ -39,6 +39,18 @@ skip = [
 structured_output = true
 reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
 
+# Claude Fable 5.1: adaptive thinking always on; caller control is effort only (no thinking toggle).
+# Wire: output_config.effort = low|medium|high|xhigh|max on the Anthropic Messages path.
+# https://platform.claude.com/docs/en/build-with-claude/effort
+# https://platform.claude.com/docs/en/about-claude/pricing
+[models."anthropic/claude-fable-5.1"]
+structured_output = true
+note = [
+  "Effort: output_config.effort = low|medium|high|xhigh|max (Anthropic Messages API; adaptive thinking always on).",
+  "Sources: https://platform.claude.com/docs/en/build-with-claude/effort ; https://platform.claude.com/docs/en/about-claude/pricing",
+]
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high", "xhigh", "max"] }]
+
 [models."anthropic/claude-haiku-4.5"]
 structured_output = true
 reasoning_options = [{ type = "budget_tokens", min = 1024 }]
diff --git a/providers/cloudflare-ai-gateway/models/anthropic/claude-fable-5.1.toml b/providers/cloudflare-ai-gateway/models/anthropic/claude-fable-5.1.toml
new file mode 100644
index 00000000000..56d384093a6
--- /dev/null
+++ b/providers/cloudflare-ai-gateway/models/anthropic/claude-fable-5.1.toml
@@ -0,0 +1,23 @@
+# Effort: output_config.effort = low|medium|high|xhigh|max (Anthropic Messages API; adaptive thinking always on).
+# Sources:
+# - https://platform.claude.com/docs/en/build-with-claude/effort
+# - https://platform.claude.com/docs/en/about-claude/pricing
+# - https://platform.claude.com/docs/en/models/overview
+base_model = "anthropic/claude-fable-5-1"
+structured_output = true
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high", "xhigh", "max"]
+
+[cost]
+input = 10
+output = 50
+cache_read = 0.25
+cache_write = 12.5
+
+[limit]
+context = 1_000_000
+
+[provider]
+npm = "@ai-sdk/anthropic"