# ChatAnthropic in LangChain: import, base_url, streaming, tools and errors

`ChatAnthropic` from the `langchain-anthropic` package is LangChain's Claude chat model. It wraps the official Anthropic Python SDK, so pointing it at a gateway takes one argument, `base_url`, set to the host root. Everything else in your chains, agents and tools stays the same.

## Install and import

```bash
pip install -U langchain-anthropic
```

```python
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="claude-sonnet-5",
    base_url="https://aiprimetech.io",           # host root: the SDK adds /v1/messages
    api_key="your_gateway_key",   # or set ANTHROPIC_API_KEY
)

print(llm.invoke("Say hello in one word.").text)
```

> No `/v1` in `base_url` here. The Anthropic SDK underneath appends `/v1/messages` itself; adding `/v1` produces `/v1/v1/messages` and a `404 page not found`.

## Configure it from the environment

`base_url` is an alias of `anthropic_api_url`, and `api_key` an alias of `anthropic_api_key`. When you don't pass them, ChatAnthropic reads `ANTHROPIC_API_URL` first, then `ANTHROPIC_BASE_URL`, and the key from `ANTHROPIC_API_KEY`. Explicit arguments always win.

```bash
export ANTHROPIC_API_KEY=your_gateway_key
export ANTHROPIC_API_URL=https://aiprimetech.io
```

```python
from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(model="claude-sonnet-5")   # picks up the gateway from the environment
```

## Streaming

```python
for chunk in llm.stream("Explain backpressure in two sentences."):
    print(chunk.text, end="", flush=True)
```

`.text` collects only the text blocks of each chunk, so it stays clean when the model also emits thinking or tool-use blocks. Use streaming for long answers: a long non-streaming request is the usual cause of timeouts.

## Tools and structured output

```python
from langchain_core.tools import tool

@tool
def get_time(city: str) -> str:
    """Return the current local time in a city."""
    return "12:00"

msg = llm.bind_tools([get_time]).invoke("What time is it in Tokyo?")
print(msg.tool_calls)
```

```python
from pydantic import BaseModel

class Weather(BaseModel):
    city: str
    temperature_c: float

print(llm.with_structured_output(Weather).invoke("It is 21 degrees in Lisbon today."))
```

## Retries, timeouts and max_tokens

`max_retries` defaults to 2, the same as the Anthropic SDK, which retries connection errors, 429 and 5xx responses. `timeout` (alias of `default_request_timeout`) is in seconds. If you leave `max_tokens` unset, it comes from the model's profile.

```python
llm = ChatAnthropic(
    model="claude-sonnet-5",
    base_url="https://aiprimetech.io",
    max_retries=4,
    timeout=120,
    max_tokens=8000,
)
```

For batches, cap parallelism so you stay inside your key's concurrency: `llm.batch(inputs, config={"max_concurrency": 3})`.

## The ChatOpenAI alternative

If your code is standardised on `ChatOpenAI`, the gateway's OpenAI-compatible endpoint serves Claude too. This route wants `/v1` on the end, the opposite of ChatAnthropic.

```python
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="claude-sonnet-5", base_url="https://aiprimetech.io/v1", api_key="your_gateway_key")
```

Prefer ChatAnthropic for Claude: it keeps native features such as prompt caching and thinking blocks.

## Troubleshooting

| What you see | Cause | Fix |
| --- | --- | --- |
| `404 page not found` | `/v1` in ChatAnthropic's `base_url` | Use the host root, `https://aiprimetech.io` |
| `Model "..." is not supported` | An ID your key's group doesn't serve, or an old dated name | Use a current ID from the table below |
| `AuthenticationError` | `ANTHROPIC_API_KEY` empty in the running process, or a key for another endpoint | Pass `api_key=` explicitly to test |
| `RateLimitError: Concurrency limit exceeded` | Too many parallel calls (`batch`, async gather) | `max_concurrency` in the batch config |
| `APITimeoutError` | Long non-streaming generations | Stream, or raise `timeout` |

| Model ID | Use it for |
| --- | --- |
| `claude-sonnet-5` | Default for coding and agent work: fast, strong, mid-priced. |
| `claude-opus-5-5` | Harder reasoning, large refactors, long agent runs. |
| `claude-fable-5-1` | Most capable and most expensive; save it for the hardest tasks. |
| `claude-haiku-4-5` | Cheap and quick: titles, summaries, classification, small steps. |

## FAQ

### How do I import ChatAnthropic?

pip install -U langchain-anthropic, then from langchain_anthropic import ChatAnthropic.

### Does ChatAnthropic's base_url need /v1?

No. Pass the host root, e.g. https://aiprimetech.io; the Anthropic SDK appends /v1/messages. ChatOpenAI is the opposite and needs /v1.

### Which environment variables does ChatAnthropic read?

ANTHROPIC_API_KEY for the key, and ANTHROPIC_API_URL, then ANTHROPIC_BASE_URL, for the endpoint when base_url isn't passed.

### Is base_url the same as anthropic_api_url?

Yes. base_url is an alias of anthropic_api_url, and api_key is an alias of anthropic_api_key.

---

Source: https://aiprimetech.io/learn/use-claude-api-with-langchain/
Provider: AI Prime Tech — independent Anthropic-compatible API gateway (not affiliated with Anthropic).