From 0d8486fc4f83c1b53d5241b53e483c88adfd57cc Mon Sep 17 00:00:00 2001
From: "github-actions[bot]"
 <41898282+github-actions[bot]@users.noreply.github.com>
Date: Tue, 15 Sep 2026 07:42:34 +0000
Subject: [PATCH] fix: Add deepseek-v4.1-flash to the international Alibaba
 Token Plan provider

---
 .../models/deepseek-v4.1-flash.toml           | 22 +++++++++++++++++++
 1 file changed, 22 insertions(+)
 create mode 100644 providers/alibaba-token-plan/models/deepseek-v4.1-flash.toml

diff --git a/providers/alibaba-token-plan/models/deepseek-v4.1-flash.toml b/providers/alibaba-token-plan/models/deepseek-v4.1-flash.toml
new file mode 100644
index 00000000000..f32c843d2e8
--- /dev/null
+++ b/providers/alibaba-token-plan/models/deepseek-v4.1-flash.toml
@@ -0,0 +1,22 @@
+# Reasoning HTTP format (accessed 2026-09-15):
+# Toggle: enable_thinking = true|false. Chat Completions `reasoning_effort`
+# accepts low, high (default), and max; medium and xhigh map to high.
+# Reasoning streams on `reasoning_content`.
+# Model availability: Token Plan Personal and Team editions (Singapore).
+# Sources:
+# https://docs.qwencloud.com/api-reference/chat/openai-chat
+# https://www.alibabacloud.com/help/en/model-studio/deepseek-api
+# https://www.alibabacloud.com/help/en/model-studio/token-plan-personal-overview
+# https://www.alibabacloud.com/help/en/model-studio/token-plan-team-overview
+base_model = "deepseek/deepseek-v4.1-flash"
+
+reasoning_options = [{ type = "toggle" }, { type = "effort", values = ["low", "high", "max"] }]
+
+[interleaved]
+field = "reasoning_content"
+
+[cost]
+input = 0
+output = 0
+cache_read = 0
+cache_write = 0