> ## Documentation Index
> Fetch the complete documentation index at: https://docs.getimpala.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Anthropic SDKs and Claude Code

> Impala serves the Anthropic Messages API. Point the Anthropic SDKs, the Claude Agent SDK, or Claude Code at your endpoint.

Impala serves **`/v1/messages`** alongside its OpenAI-compatible endpoints, so Anthropic-format
tooling talks to it directly. That covers the Anthropic SDKs, the **Claude Agent SDK**, and
**Claude Code**.

## What you need

* `BASE_URL` — your Impala endpoint
* `API_KEY` — your Impala key
* `MODEL` — the model your endpoint serves

Either `Authorization: Bearer` or `x-api-key` is accepted, so the SDKs work with their own
defaults.

<Info>
  The Anthropic SDKs append `/v1/messages` to whatever base URL you give them. Pass the host root,
  not a URL that already ends in `/v1`.
</Info>

## Anthropic SDK

```python theme={null}
import anthropic

client = anthropic.Anthropic(
    base_url="<BASE_URL>",
    api_key="<API_KEY>",
)

message = client.messages.create(
    model="<MODEL>",
    max_tokens=256,
    messages=[{"role": "user", "content": "Summarize this ticket in one line."}],
)
print(message.content[0].text)
```

TypeScript is the same shape:

```javascript theme={null}
import Anthropic from "@anthropic-ai/sdk";

const client = new Anthropic({
  baseURL: process.env.BASE_URL,
  apiKey: process.env.API_KEY,
});

const message = await client.messages.create({
  model: process.env.MODEL,
  max_tokens: 256,
  messages: [{ role: "user", content: "Summarize this ticket in one line." }],
});
```

Or directly:

```bash theme={null}
curl -X POST "$BASE_URL/v1/messages" \
  -H "content-type: application/json" \
  -H "Authorization: Bearer $API_KEY" \
  -d '{
    "model": "'"$MODEL"'",
    "max_tokens": 256,
    "messages": [{"role": "user", "content": "Hello"}]
  }'
```

## Claude Agent SDK and Claude Code

Both read the standard Anthropic environment variables, so neither needs a code change:

```bash theme={null}
export ANTHROPIC_BASE_URL="<BASE_URL>"
export ANTHROPIC_AUTH_TOKEN="<API_KEY>"
export ANTHROPIC_MODEL="<MODEL>"
```

Then run your agent, or launch `claude`, from that same shell.

Set `ANTHROPIC_MODEL` explicitly. Clients that discover available models at startup expect
Anthropic's own catalog, and naming the model yourself avoids that lookup.

## Things to know

**Raise your timeouts.** A call takes seconds and can take longer under load, and an agent making
many sequential turns multiplies that. Raise the timeout in whatever runs your agent and keep turn
counts low — see [Run async and open source](/async-inference).

**This path is per-request.** That suits an agent loop, where each turn depends on the last. Where
the work is a rollout over a fixed input set, that part is cheaper as a
[batch](/run-your-first-batch).

Nothing here requires a proxy. If you want one for provider routing, key isolation, or central
budget controls, see [LiteLLM](/connect-litellm).

## Need help?

Reach out to your Impala contact directly.