Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

docs: register DeepSeek Harness (#17751)

Parth Sareen78e818e3ceb3
diff --git a/docs/docs.json b/docs/docs.json
index 0d673939d..727e3ef26 100644
--- a/docs/docs.json
+++ b/docs/docs.json
@@ -168,6 +168,7 @@
"pages": [
"/integrations/claude-code",
"/integrations/opencode",
+ "/integrations/deepseek-harness",
"/integrations/cline-cli",
"/integrations/codex-app",
"/integrations/codex",
diff --git a/docs/integrations/deepseek-harness.mdx b/docs/integrations/deepseek-harness.mdx
index b22719ce5..c09ff9817 100644
--- a/docs/integrations/deepseek-harness.mdx
+++ b/docs/integrations/deepseek-harness.mdx
@@ -15,8 +15,8 @@ ollama launch dsh
Ollama installs `@deepseek-ai/dsh` if needed. To choose a model:
```shell
-ollama launch dsh --model qwen3.5
-ollama launch dsh --model qwen3.5:cloud
+ollama launch dsh --model qwen3.8
+ollama launch dsh --model deepseek-v4-flash:cloud
```
To configure without starting: