# Unable to pass maxTokens and extract Resoning Summary in AzureChatOpenAI

**URL:** <https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843>\
**Category:** LangChain\
**Tags:** js-help\
**Created:** [October 16, 2025, 1:53pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843 "2025-10-16T13:53:59Z")\
**Posts on this page:** 8\
**Page:** 1

<div class="post-metadata">

**Author:** ![Nikfury](https://avatars.discourse-cdn.com/v4/letter/n/3ec8ea/32.png) [@Nikfury](https://forum.langchain.com/u/Nikfury)\
**Post date:** [October 16, 2025, 1:53pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/1 "2025-10-16T13:53:59Z")

</div>

## Azure OpenAI: maxTokens Error and Reasoning Summary Extraction

I’m experiencing issues with Azure OpenAI using LangChain’s `AzureChatOpenAI`  
class and wanted to share my findings.

### The Problem

When using `AzureChatOpenAI` with GPT-5, I’m getting this error:

400 Unsupported parameter: ‘maxTokens’ is not supported with this model. Use  
‘max\_completion\_tokens’ instead.

However, even when I rswitch to `maxCompletionTokens`, the error persists. Only after I remove `maxTokens` entirely from the constructor it works

### Azure vs OpenAI Configuration Differences

I’ve noticed some key differences between `ChatOpenAI` and `AzureChatOpenAI`:

**For OpenAI (works):**

```javascript
const model = new ChatOpenAI({
  model: "gpt-5",
  useResponsesApi: true,
  maxTokens: 16384, // Works fine
});

const response = await model.invoke(messages, {
  reasoning: { effort: "low", summary: "detailed" }
});

```

#### For Azure (error with max\_tokens):

```javascript
const model = new AzureChatOpenAI({
    azureOpenAIApiKey: process.env.INTERNAL_AZURE_OPENAI_API_KEY,
    azureOpenAIApiInstanceName: "resource-name",
    azureOpenAIApiDeploymentName: "gpt-5",
    azureOpenAIApiVersion: "2024-10-01-preview",
    reasoning: { effort: "low" }, // Must be in constructor for Azure
    // Cannot use maxTokens or maxCompletionTokens - causes 400 error
  });

```

### Questions

1. Is maxTokens supported for Azure OpenAI GPT-5 deployments? The error suggests  
it isn’t, but I can’t find this documented anywhere.
2. Can we extract reasoning summaries from Azure OpenAI? For OpenAI, passing  
reasoning to the invoke method works ([as mentioned in the original post)](https://forum.langchain.com/t/how-to-extract-gpt-5-reasoning-summaries-with-langchain-openai/1802/2). For  
Azure, the documentation suggests putting reasoning in the constructor, but I  
cannot verify if reasoning summaries are actually extractable from  
additional\_kwargs.
3. Is this a LangChain bug? Could LangChain be sending max\_tokens to Azure OpenAI  
even when it’s not specified in the constructor?

Environment

- @langchain/openai: 0.6.14
- Azure OpenAI API Version: 2024-10-01-preview
- Model: gpt-5

Has anyone successfully used Azure OpenAI GPT-5 with LangChain and extracted  
reasoning summaries? Any insights would be appreciated!

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 16, 2025, 3:33pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/2 "2025-10-16T15:33:13Z")

</div>

Hi @Nikfury

have you tried this:

```ts
import { AzureChatOpenAI } from "@langchain/openai";

const llm = new AzureChatOpenAI({
  azureOpenAIApiKey: process.env.INTERNAL_AZURE_OPENAI_API_KEY,
  azureOpenAIApiInstanceName: "resource-name",
  azureOpenAIApiDeploymentName: "gpt-5",
  azureOpenAIApiVersion: "2024-10-01-preview",
  useResponsesApi: true,
  maxTokens: 2048,
  reasoning: { effort: "low" },
});

const ai = await llm.invoke(messages, {
  reasoning: { summary: "detailed" },
});

```

---

<div class="post-metadata">

**Author:** ![Nikfury](https://avatars.discourse-cdn.com/v4/letter/n/3ec8ea/32.png) [@Nikfury](https://forum.langchain.com/u/Nikfury)\
**Post date:** [October 16, 2025, 11:26pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/3 "2025-10-16T23:26:30Z")

</div>

Thanks @pawel-twardziak for responding again! I tested this exact code with my  
Azure OpenAI gpt-5 deployment and here are the results:

1. Your suggested code fails with 404 error:

```auto
const llm = new AzureChatOpenAI({
    azureOpenAIApiKey:
  process.env.INTERNAL_AZURE_OPENAI_API_KEY,
    azureOpenAIApiInstanceName:
  process.env.INTERNAL_AZURE_OPENAI_RESOURCE_NAME,
    azureOpenAIApiDeploymentName: "gpt-5",
    azureOpenAIApiVersion: "2024-10-01-preview",
    useResponsesApi: true,
    maxTokens: 2048,
    reasoning: { effort: "low" },
  });

  const ai = await llm.invoke(messages, {
    reasoning: { summary: "detailed" },
  });

```

Output:  
`error: { code: '404', message: 'Resource not found' }`

1. Commenting out specific parts makes it work:

Removing useResponsesApi, reasoning from initialization, AND  
the reasoning parameter from invoke():

```auto
const llm = new AzureChatOpenAI({
    azureOpenAIApiKey:
  process.env.INTERNAL_AZURE_OPENAI_API_KEY,
    azureOpenAIApiInstanceName:
  process.env.INTERNAL_AZURE_OPENAI_RESOURCE_NAME,
    azureOpenAIApiDeploymentName: "gpt-5",
    azureOpenAIApiVersion: "2024-10-01-preview",
    // useResponsesApi: true, ← Removed
    maxTokens: 2048,
    // reasoning: { effort: "low" }, ← Removed
  });

  const ai = await llm.invoke(messages); // ← No reasoning 
  parameter

```

Output:

```auto
  ✓ Success without useResponsesApi!
  Response: "Response text"

```

1. The same Azure deployment works perfectly with the  
official OpenAI SDK:

```auto
import { AzureOpenAI } from "openai";

  const client = new AzureOpenAI({
    apiKey: process.env.INTERNAL_AZURE_OPENAI_API_KEY,
    endpoint: `https://${process.env.INTERNAL_AZURE_OPENAI_RESO
  URCE_NAME}.openai.azure.com`,
    apiVersion: "2024-10-01-preview",
  });

  const response = await client.chat.completions.create({
    model: "gpt-5",
    messages: [{ role: "user", content: "what is the meaning of
   life, think hard" }],
    max_completion_tokens: 2048,
    reasoning_effort: "low",
  });

```

Output:

```auto
✓ Success with Responses API!
  Usage: {
    "reasoning_tokens": 192, ← Reasoning IS working!
    "completion_tokens": 737,
    "total_tokens": 760
  }

```

Let me know if I am missing something or if you want me to try something else

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 17, 2025, 6:12pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/4 "2025-10-17T18:12:31Z")

</div>

Hi @Nikfury

try this:

```js
const ai = await llm.invoke(messages, {
    reasoning: {
        effort: "high",
        summary: "auto" /* summary config if desired */,
    },
});

```

Your issue might be related to that [How to extract GPT-5 reasoning summaries with @langchain/openai? - #15 by pawel-twardziak](https://forum.langchain.com/t/how-to-extract-gpt-5-reasoning-summaries-with-langchain-openai/1802/15) since it is still OpenAI class that is being exetended.

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 17, 2025, 6:16pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/5 "2025-10-17T18:16:45Z")

</div>

If you are still getting `404`, that is another issue which you might need to debug.

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 17, 2025, 6:20pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/6 "2025-10-17T18:20:51Z")

</div>

Likely the `404` error is triggered by the source error. See that [How to extract GPT-5 reasoning summaries with @langchain/openai? - #2 by pawel-twardziak](https://forum.langchain.com/t/how-to-extract-gpt-5-reasoning-summaries-with-langchain-openai/1802/2)

---

<div class="post-metadata">

**Author:** ![Nikfury](https://avatars.discourse-cdn.com/v4/letter/n/3ec8ea/32.png) [@Nikfury](https://forum.langchain.com/u/Nikfury)\
**Post date:** [October 17, 2025, 8:15pm UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/7 "2025-10-17T20:15:33Z")

</div>

Hi @pawel-twardziak

let me know if im missing something but the solution you suggested in [How to extract GPT-5 reasoning summaries with @langchain/openai? - #2 by pawel-twardziak](https://forum.langchain.com/t/how-to-extract-gpt-5-reasoning-summaries-with-langchain-openai/1802/2). Suggests

1. passing `useResponsesApi: true` in llm initialiation
2. and passing `reasoning` config in invoke

```auto
reasoning: {
        effort: "high",
        summary: "auto" /* summary config if desired */,
    },

```

- Using that with `AzureChatOpenAI ` gives `error: { code: '404', message: 'Resource not found' }` however the same azure gpt-5 resource work if i remove both the above parameters but then I am not able to extract reasoning summary

- Also, I am able to extract reasoning summar when calling the azure gpt-5 resource using offical OpenAI Responses API

---

<div class="post-metadata">

**Author:** ![pawel-twardziak](https://yyz1.discourse-cdn.com/flex007/user_avatar/forum.langchain.com/pawel-twardziak/32/960_2.png) [@pawel-twardziak](https://forum.langchain.com/u/pawel-twardziak)\
**Post date:** [October 20, 2025, 8:26am UTC](https://forum.langchain.com/t/unable-to-pass-maxtokens-and-extract-resoning-summary-in-azurechatopenai/1843/8 "2025-10-20T08:26:31Z")

</div>

Hi @Nikfury

bullets 1. and 2. should be sufficient.  
If it’s still not working for AzureChatOpenAI … then I don’t actually knowy why.

Have you tried with `ChatOpenAI` from langchain? It should work following that [How to extract GPT-5 reasoning summaries with @langchain/openai? - #14 by AMuresan](https://forum.langchain.com/t/how-to-extract-gpt-5-reasoning-summaries-with-langchain-openai/1802/14)