diff --git a/docs/api/anthropic-compatibility.mdx b/docs/api/anthropic-compatibility.mdx
index 81ec04d47..299b44808 100644
--- a/docs/api/anthropic-compatibility.mdx
+++ b/docs/api/anthropic-compatibility.mdx
@@ -12,7 +12,6 @@ To use Ollama with tools that expect the Anthropic API (like Claude Code), set t
```shell
export ANTHROPIC_AUTH_TOKEN=ollama # required but ignored
-export ANTHROPIC_API_KEY="" # required but ignored
export ANTHROPIC_BASE_URL=http://localhost:11434
```
@@ -269,7 +268,7 @@ ollama launch claude --config
Set the environment variables and run Claude Code:
```shell
-ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 ANTHROPIC_API_KEY="" claude --model qwen3-coder
+ANTHROPIC_AUTH_TOKEN=ollama ANTHROPIC_BASE_URL=http://localhost:11434 claude --model qwen3-coder
```
Or set the environment variables in your shell profile:
@@ -277,7 +276,6 @@ Or set the environment variables in your shell profile:
```shell
export ANTHROPIC_AUTH_TOKEN=ollama
export ANTHROPIC_BASE_URL=http://localhost:11434
-export ANTHROPIC_API_KEY=""
```
Then run Claude Code with any Ollama model:
diff --git a/docs/api/openai-compatibility.mdx b/docs/api/openai-compatibility.mdx
index 27d3951d5..4c37d8192 100644
--- a/docs/api/openai-compatibility.mdx
+++ b/docs/api/openai-compatibility.mdx
@@ -6,7 +6,7 @@ Ollama provides compatibility with parts of the [OpenAI API](https://platform.op
## Usage
-### Simple `v1/chat/completions` example
+### Simple `/v1/chat/completions` example
@@ -57,7 +57,7 @@ curl -X POST http://localhost:11434/v1/chat/completions \
-### Simple `v1/responses` example
+### Simple `/v1/responses` example
@@ -103,7 +103,7 @@ curl -X POST http://localhost:11434/v1/responses \
-### v1/chat/completions with vision example
+### `/v1/chat/completions` with vision example