# Sonnet-5.5 through \`ChatOpenAI\`

**URL:** <https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672>\
**Category:** LangChain\
**Tags:** python-help\
**Created:** [October 2, 2026, 12:42pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672 "2026-10-02T12:42:36Z")\
**Posts on this page:** 5\
**Page:** 1

<div class="post-metadata">

**Author:** ![saqlain2204](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/saqlain2204/32/3639_2.png) [@saqlain2204](https://forum.langchain.com/u/saqlain2204)\
**Post date:** [October 2, 2026, 12:42pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672/1 "2026-10-02T12:42:36Z")

</div>

Hi LangChain Community,

A while ago Anthropic launched 5.5 and I was trying to access to access it thorugh `ChatOpenAI` wrapper. The migration docs explicitly state that on passing `thinking.type` as `disabled` we would be encountering a 400 error. However, when i pass it as `disabled` via the `extra_params` arg, I dont see the 400 error. I want to know validate if this paramter is actually being picked up or not. Is there any abstraction to hide this error and continue with the default params?

Thanks

---

<div class="post-metadata">

**Author:** ![mdrxy](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/mdrxy/32/2481_2.png) [@mdrxy](https://forum.langchain.com/u/mdrxy)\
**Post date:** [October 2, 2026, 3:29pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672/2 "2026-10-02T15:29:04Z")

</div>

@saqlain2204 why are you using `ChatOpenAI` versus `ChatAnthropic`?

---

<div class="post-metadata">

**Author:** ![saqlain2204](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/saqlain2204/32/3639_2.png) [@saqlain2204](https://forum.langchain.com/u/saqlain2204)\
**Post date:** [October 2, 2026, 5:24pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672/3 "2026-10-02T17:24:32Z")

</div>

We are routing our requests through litellm proxy

---

<div class="post-metadata">

**Author:** ![saqlain2204](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/saqlain2204/32/3639_2.png) [@saqlain2204](https://forum.langchain.com/u/saqlain2204)\
**Post date:** [October 2, 2026, 5:25pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672/4 "2026-10-02T17:25:09Z")

</div>

because the apis are openAI compatible, we are using OpenAI ChatModels

---

<div class="post-metadata">

**Author:** ![keenborder786](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/keenborder786/32/1757_2.png) [@keenborder786](https://forum.langchain.com/u/keenborder786)\
**Post date:** [October 6, 2026, 1:42pm UTC](https://forum.langchain.com/t/sonnet-5-5-through-chatopenai/4672/5 "2026-10-06T13:42:09Z")

</div>

@saqlain2204  
Why don’t you directly use [ChatLiteLLM | langchain\_litellm | LangChain Reference](https://reference.langchain.com/python/langchain-litellm/chat_models/litellm/ChatLiteLLM)?