---
title: "Claude Desktop and Claude Code with the Langfuse AI Gateway"
sidebarTitle: Claude Code (gateway)
seoTitle: "Trace Claude Desktop and Claude Code with the Langfuse AI Gateway (beta)"
description: Route Claude Desktop or Claude Code through the Langfuse AI Gateway to trace model calls, tokens, costs, and Claude Code sessions.
logo: /images/integrations/anthropic_icon.png
logoAppearance: dark
category: Integrations
---

# Claude Desktop and Claude Code with the Langfuse AI Gateway

  **Beta.** The Langfuse AI Gateway is in public beta and can still change.

Use the Langfuse AI Gateway with the Claude Desktop app or the Claude Code CLI. Both require an `ANTHROPIC` provider credential.

  This page routes Claude's model calls through the AI Gateway. For tracing
  Claude Code with hooks instead, see the [Claude Code
  integration](/integrations/developer-tools/claude-code).

## Claude Desktop [#claude-desktop]

<Steps>

### Create a gateway API key [#desktop-create-a-key]

Create a gateway API key under **Organization settings → AI Gateway → Gateway keys**. See [API keys](/docs/gateway/features/api-keys#create-a-key).

### Connect to the gateway [#desktop-configure]

Open **Developer → Configure Third-Party Inference**. If the **Developer** menu is unavailable, open **Help → Troubleshooting** and enable Developer Mode. Then, under **Connection**:

- Set **Inference provider** to **Gateway**.
- Set **Gateway base URL** to `https://gateway.cloud.langfuse.com/anthropic`. Do not add `/v1`; Claude Desktop appends it.
- Set **Credential kind** to **Static API key**, enter your Langfuse gateway key under **Gateway API key**, and select **Bearer** as the **Gateway auth scheme**.

### Set capabilities [#desktop-capabilities]

Under **Capabilities**:

- Under **General restrictions**, we recommend adding `*` to **Allowed egress hosts**. Otherwise, Claude can't reach websites or services outside the gateway, such as GitHub, and it won't ask you for permission.
- Optional: gateway mode uses a separate profile. To keep your existing claude.ai chats and sessions, turn on **Claude.ai data import**. After restarting, use **Settings → Import & export**. See [Import and export](https://claude.com/docs/third-party/claude-desktop/import).

### Save and restart [#desktop-save]

Select **Apply Changes**, then select **Save & Restart**. Start a new session so that the egress settings apply. For more information about these settings, see the [Claude Desktop third-party inference guide](https://claude.com/docs/third-party/claude-desktop/in-app-configuration).

  Use HTTPS git remotes or `gh` to push. SSH push fails in the macOS sandbox,
  see [anthropics/claude-code#98752](https://github.com/anthropics/claude-code/issues/98752).

  MCP servers connected through Claude Desktop are associated with your
  claude.ai subscription. They are unavailable while Claude Desktop uses
  third-party gateway credentials. Switch back to your Claude account to use
  those subscription-backed connectors.

### Verify [#desktop-verify]

Test the connection in **Developer → Configure Third-Party Inference**, or send a message in a new session. If Claude replies, it runs through the gateway.

</Steps>

## Claude Code CLI [#claude-code-cli]

**Requires** Claude Code 2.1 or later. Verified with Claude Code 2.1.282.

<Steps>

### Create a gateway API key [#create-a-key]

Create a gateway API key under **Organization settings → AI Gateway → Gateway keys**. See [API keys](/docs/gateway/features/api-keys#create-a-key).

### Log out of Claude [#log-out]

Remove existing subscription credentials:

```sh
claude /logout
```

An existing Claude login can send both `Authorization` and `x-api-key` credentials and cause `401 Conflicting gateway credentials in the Authorization and x-api-key headers`.

### Point Claude Code at the gateway [#setup]

Set the gateway variables in your shell:

```sh
export ANTHROPIC_BASE_URL="https://gateway.cloud.langfuse.com/anthropic"   # no /v1: Claude Code appends /v1/messages
export ANTHROPIC_AUTH_TOKEN="<your-gateway-key>"                          # sent as Authorization: Bearer
unset ANTHROPIC_API_KEY                                                    # a different value here causes a 401
export CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1                        # optional: /model lists gateway models
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1                          # optional
export ANTHROPIC_CUSTOM_HEADERS=$'langfuse-tags: claude-code,<team>\nlangfuse-environment: local\nlangfuse-metadata: repo:<repo>'   # optional
claude
```

To keep the setup across sessions, add the `export` lines to `~/.zshrc`. If `~/.zshrc` also sets `ANTHROPIC_API_KEY`, remove that line.

Alternatively, use `~/.claude/settings.json`:

```json
{
  "env": {
    "ANTHROPIC_BASE_URL": "https://gateway.cloud.langfuse.com/anthropic",
    "ANTHROPIC_AUTH_TOKEN": "<your-gateway-key>",
    "CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY": "1",
    "ANTHROPIC_CUSTOM_HEADERS": "langfuse-tags: claude-code\nlangfuse-environment: local"
  }
}
```

- `ANTHROPIC_CUSTOM_HEADERS` takes newline-separated `Name: value` pairs. See [request headers](/docs/gateway/features/tracing#request-headers).
- Pick models with `--model` or `/model`, using IDs from [`/models`](/docs/gateway/get-started/first-request#list-models). Bare `claude-…` IDs and `<credential>:<model>` IDs both work, see [model IDs](/docs/gateway/features/models#model-ids).
- MCP servers configured locally through the CLI remain available because Claude Code stores them in `.claude.json`.

### Verify [#verify]

Run a prompt:

```sh
claude -p "Reply with: hello gateway"
```

If Claude Code replies, it runs through the gateway.

</Steps>

## Turn grouping (beta) [#turn-grouping]

By default, every model call is its own trace. Claude Code can send a W3C `traceparent` header whose trace ID is its `claude_code.interaction` span, one per user prompt. The gateway adopts that trace ID, so every model call of a prompt lands in **one trace**, including subagent calls and retries.

This uses Claude Code's beta [OpenTelemetry tracing](https://code.claude.com/docs/en/monitoring-usage). All four settings are required:

```sh
export CLAUDE_CODE_ENABLE_TELEMETRY=1
export CLAUDE_CODE_ENHANCED_TELEMETRY_BETA=1
export CLAUDE_CODE_PROPAGATE_TRACEPARENT=1
export OTEL_TRACES_EXPORTER=otlp
export OTEL_EXPORTER_OTLP_ENDPOINT="<your-otel-collector>"
```

- Claude Code only sends `traceparent` when tracing is actually active. With `OTEL_TRACES_EXPORTER` unset or set to `none`, nothing is sent and each call stays its own trace.
- `OTEL_TRACES_EXPORTER=console` also works, but it prints span dumps to stdout, which makes the interactive UI unusable.
- **Do not point this OTLP export at Langfuse.** Claude Code's `claude_code.llm_request` spans would be recorded as a second generation next to the gateway's generation for every call. Use your own collector.
- Because Claude Code's own spans are not in Langfuse, the gateway generations of a prompt appear as top-level observations of the shared trace.
- A resumed session starts a new trace per prompt, in the same session.

## Troubleshooting and FAQ [#troubleshooting-and-faq]

### Why does a failed prompt show two ERROR generations? [#two-error-generations]

When a model call fails, Claude Code retries once without streaming, so a failed prompt shows **two** `ERROR` generations.

### Why aren't subagent calls linked to their parent? [#subagent-parent]

Subagent calls carry `agent.id` but no link to their parent, unless you enable [turn grouping](#turn-grouping).

### Why is the thinking text empty? [#empty-thinking]

Claude Code often omits thinking text (`thinking.display: "omitted"`), so time to first token is close to latency. Thinking tokens are counted inside output tokens.

### What is the HEAD /anthropic/api/hello 404 at startup? [#hello-404]

It's Claude Code's connectivity probe. It is harmless and not recorded.

### Why is the input missing on long sessions? [#missing-input]

Long sessions can exceed the 5 MiB input capture limit. See [known limitations](/faq/all/ai-gateway-known-limitations).

[Ask another question](/docs/ask-ai)

<!-- agent-instructions -->

---

## Agent Instructions

This page is part of the [Langfuse](https://langfuse.com) documentation, published as plain Markdown for AI agents. Every page is available as Markdown by appending `.md` to its URL, or by sending an `Accept: text/markdown` header. This page: `https://langfuse.com/integrations/developer-tools/claude-code-gateway.md`.

### Querying these docs

If the answer is not on this page, query the documentation instead of guessing:

- **Semantic search** across all Langfuse docs, returning an answer with the relevant pages and excerpts. Ask a specific, self-contained question:

  ```bash
  curl -sG "https://langfuse.com/api/search-docs" --data-urlencode "query=How do I trace a LangGraph agent?"
  ```

- **Index of every page**: <https://langfuse.com/llms.txt>, with per-section indexes [llms-docs.txt](https://langfuse.com/llms-docs.txt), [llms-integrations.txt](https://langfuse.com/llms-integrations.txt), and [llms-self-hosting.txt](https://langfuse.com/llms-self-hosting.txt).

### Before writing Langfuse code

- **Install the [Langfuse Agent Skill](https://langfuse.com/docs/api-and-data-platform/features/agent-skill).** It encodes Langfuse's own best practices for instrumentation, prompt management, and evaluation, and materially improves results.
- **Read [What does a good trace look like?](https://langfuse.com/docs/observability/best-practices.md)** before instrumenting an application.
- **Verify endpoints, parameters, and response fields** against the [API reference](https://api.reference.langfuse.com) instead of inferring them from code examples.
- **Use the [Langfuse CLI](https://langfuse.com/docs/api-and-data-platform/features/cli)** (`npx @langfuse/cli api <resource> <action>`) to read or write traces, prompts, datasets, and scores from the terminal.

Found an error in these docs? Please open an issue at <https://github.com/langfuse/langfuse-docs/issues>.