Hey @samjs , I'd like to report a bug in the documentation of MeloTTS model: https://developers.clo

HHimanshu Hey @samjs , I'd like to report a bug in the documentation of MeloTTS model: ht...

S

samjs•9/11/25, 6:32 PM

Hey @Himanshu. Thanks for raising this. You're right it looks like we currently only download the weights for the english model.

Ssamjs Hey @Himanshu. Thanks for raising this. You're right it looks like we currently ...

H

HimanshuOP•9/11/25, 6:50 PM

I find the quality of the outputs with MeloTTS really good. Would request support for other languages and speaker accents for English - it allows US, UK, among others.

T

Tim•9/12/25, 5:21 AM

Is there any intention to support Kokoro TTS?

P

Proman4713 🇵🇸•9/12/25, 8:10 AM

when i run mistral ai it works fine, but if it asks for tool_calls, and i execute the calls, then give it back the

messages

messages

messages

messages array with the

{ role: "tool" }

{ role: "tool" }

{ role: "tool" }

{ role: "tool" } items, it shows me this error:

{"httpCode":500,"internalCode":3043,"message":"AiError: AiError: Internal server error (40099610-8d16-4868-9093-de9bafb5818f)","name":"AiError","skipSentry":true,"description":"Internal server error"}

{"httpCode":500,"internalCode":3043,"message":"AiError: AiError: Internal server error (40099610-8d16-4868-9093-de9bafb5818f)","name":"AiError","skipSentry":true,"description":"Internal server error"}

{"httpCode":500,"internalCode":3043,"message":"AiError: AiError: Internal server error (40099610-8d16-4868-9093-de9bafb5818f)","name":"AiError","skipSentry":true,"description":"Internal server error"}

{"httpCode":500,"internalCode":3043,"message":"AiError: AiError: Internal server error (40099610-8d16-4868-9093-de9bafb5818f)","name":"AiError","skipSentry":true,"description":"Internal server error"}

this is decoded from base64 network response, actual console error is just this:

[wrangler:error] AiError: 3043: Internal server error
    at Ai._parseError (cloudflare-internal:ai-api:212:24)
    at async Ai.run (cloudflare-internal:ai-api:190:19)
    at async runWorker (file:///home/proman4713/JavaScript%20Projects/MawjoodAPI/src/index.js:50:20)
    at async jsonError (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-miniflare3-json-error.ts:22:10)
    at async drainBody (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-ensure-req-body-drained.ts:5:10)

[wrangler:error] AiError: 3043: Internal server error
    at Ai._parseError (cloudflare-internal:ai-api:212:24)
    at async Ai.run (cloudflare-internal:ai-api:190:19)
    at async runWorker (file:///home/proman4713/JavaScript%20Projects/MawjoodAPI/src/index.js:50:20)
    at async jsonError (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-miniflare3-json-error.ts:22:10)
    at async drainBody (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-ensure-req-body-drained.ts:5:10)

[wrangler:error] AiError: 3043: Internal server error
    at Ai._parseError (cloudflare-internal:ai-api:212:24)
    at async Ai.run (cloudflare-internal:ai-api:190:19)
    at async runWorker (file:///home/proman4713/JavaScript%20Projects/MawjoodAPI/src/index.js:50:20)
    at async jsonError (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-miniflare3-json-error.ts:22:10)
    at async drainBody (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-ensure-req-body-drained.ts:5:10)

[wrangler:error] AiError: 3043: Internal server error
    at Ai._parseError (cloudflare-internal:ai-api:212:24)
    at async Ai.run (cloudflare-internal:ai-api:190:19)
    at async runWorker (file:///home/proman4713/JavaScript%20Projects/MawjoodAPI/src/index.js:50:20)
    at async jsonError (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-miniflare3-json-error.ts:22:10)
    at async drainBody (file:///home/proman4713/.nvm/versions/node/v22.13.1/lib/node_modules/wrangler/templates/middleware/middleware-ensure-req-body-drained.ts:5:10)

P

Proman4713 🇵🇸•9/12/25, 8:22 AM

oww man

P

Proman4713 🇵🇸•9/12/25, 8:23 AM

nah nevermind

P

Proman4713 🇵🇸•9/12/25, 8:23 AM

still errors

P

Proman4713 🇵🇸•9/12/25, 8:24 AM

is it because I'm putting

name

name

in the message element?

P

Proman4713 🇵🇸•9/12/25, 8:25 AM

well then, i think id should replace name

P

Proman4713 🇵🇸•9/12/25, 8:25 AM

nope

P

Proman4713 🇵🇸•9/12/25, 8:25 AM

still errors

P

Proman4713 🇵🇸•9/12/25, 8:26 AM

"pattern": "[a-zA-Z0-9]{9}"

"pattern": "[a-zA-Z0-9]{9}"

"pattern": "[a-zA-Z0-9]{9}"

"pattern": "[a-zA-Z0-9]{9}" makes sense, but it still doesnt work when i put 0s followed by 1

P

Proman4713 🇵🇸•9/12/25, 8:34 AM

i just wanna know

P

Proman4713 🇵🇸•9/12/25, 8:34 AM

is workers AI still in beta or something?

P

Proman4713 🇵🇸•9/12/25, 8:34 AM

why are the errors so ambiguous?

P

Proman4713 🇵🇸•9/12/25, 8:35 AM

the model does not return a tool ID, yet I'm expected to provide one? and providing one doesnt fix the issue anyway?

S

samjs•9/12/25, 1:39 PM

Hey @Proman4713

. FIrst of all, apologies for all the issues you're running into. While the Workers AI platform itself is very mature at this point, we have a fairly long tail of model/software specific nuances that can result in these confusing behaviours/errors.

In this case it seems like the underlying

mistral_common

mistral_common

mistral_common

mistral_common package is raising an exception: "Unexpected role 'tool' after role 'user'".

We should at the very least be propagating that error back to you, rather than giving you an opaque server error.

With regards to the error itself, have you tried following the Mistral docs? https://docs.mistral.ai/capabilities/function_calling/

Ssamjs Hey @Proman4713 🇵🇸 . FIrst of all, apologies for all the issues you're running...

P

Proman4713 🇵🇸•9/12/25, 2:30 PM

Thank you very much for your attention, I appreciate that.

So the issue was in the appearance of role "tool" after role "user", not in the message object itself? Alright, I guess.

I haven't followed the Mistral docs before, I will look into it in a bit and let you know if the issue is resolved.

PProman4713 🇵🇸Thank you very much for your attention, I appreciate that. So the issue was in ...

S

samjs•9/12/25, 2:40 PM

So the issue was in the appearance of role "tool" after role "user", not in the message object itself? Alright, I guess.

Supposedly, yes. Although it's not obvious to me what you would do differently. Searching for that error message comes up with similar github issues though: https://github.com/langchain-ai/langchain/issues/22928

Ssamjs > So the issue was in the appearance of role "tool" after role "user", not in th...

P

Proman4713 🇵🇸•9/12/25, 2:43 PM

I read the docs, and apparently it's pushing the

response.message

response.message

response.message

response.message string to the messages array, then after executing the tools adds the

{ role: "tool" }

{ role: "tool" }

{ role: "tool" }

{ role: "tool" } object(s)... But when the LLM chooses a tool to call it doesn't give a message in the first place

H

HimanshuOP•9/12/25, 6:01 PM

I've successfully integrated Aura and Nova models from Deepgram into OpenGPT. For anyone interested, you can try it here: https://opengpt.weblinq.dev/

For those interested in the implementation, you can check the source code: https://github.com/devhims/opengpt

P

Proman4713 🇵🇸•9/12/25, 8:32 PM

@samjs i did as they said and provided the assistant's response before running the tools. it didnt work:

[
  {
    "role": "system",
    "content": "My system prompt goes here."
  },
  {
      "role": "user",
      "content": "What's ابراهيم محمد ابراهيم الدسوقي's attendance percentage this year in class 10/A?"
  },
  {
      "role": "assistant",
      "content": "",
      "tool_calls": [{
          "name": "getClassRoster",
          "arguments": {
              "grade": 10,
              "classLetter": "A"
          }
      }]
  },
  {
    "role": "tool",
    "tool_call_id": "000000001",
    "name": "getClassRoster",
    "content": "{\"data\":[...TheResults]}"
  }
]

[
  {
    "role": "system",
    "content": "My system prompt goes here."
  },
  {
      "role": "user",
      "content": "What's ابراهيم محمد ابراهيم الدسوقي's attendance percentage this year in class 10/A?"
  },
  {
      "role": "assistant",
      "content": "",
      "tool_calls": [{
          "name": "getClassRoster",
          "arguments": {
              "grade": 10,
              "classLetter": "A"
          }
      }]
  },
  {
    "role": "tool",
    "tool_call_id": "000000001",
    "name": "getClassRoster",
    "content": "{\"data\":[...TheResults]}"
  }
]

[
  {
    "role": "system",
    "content": "My system prompt goes here."
  },
  {
      "role": "user",
      "content": "What's ابراهيم محمد ابراهيم الدسوقي's attendance percentage this year in class 10/A?"
  },
  {
      "role": "assistant",
      "content": "",
      "tool_calls": [{
          "name": "getClassRoster",
          "arguments": {
              "grade": 10,
              "classLetter": "A"
          }
      }]
  },
  {
    "role": "tool",
    "tool_call_id": "000000001",
    "name": "getClassRoster",
    "content": "{\"data\":[...TheResults]}"
  }
]

[
  {
    "role": "system",
    "content": "My system prompt goes here."
  },
  {
      "role": "user",
      "content": "What's ابراهيم محمد ابراهيم الدسوقي's attendance percentage this year in class 10/A?"
  },
  {
      "role": "assistant",
      "content": "",
      "tool_calls": [{
          "name": "getClassRoster",
          "arguments": {
              "grade": 10,
              "classLetter": "A"
          }
      }]
  },
  {
    "role": "tool",
    "tool_call_id": "000000001",
    "name": "getClassRoster",
    "content": "{\"data\":[...TheResults]}"
  }
]

and i get this error:

[wrangler:error] AiError: 3030: 3 validation errors for ValidatorIterator
0.id
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.function
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.type
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

[wrangler:error] AiError: 3030: 3 validation errors for ValidatorIterator
0.id
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.function
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.type
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

[wrangler:error] AiError: 3030: 3 validation errors for ValidatorIterator
0.id
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.function
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.type
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

[wrangler:error] AiError: 3030: 3 validation errors for ValidatorIterator
0.id
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.function
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing
0.type
  Field required [type=missing, input_value={'name': 'getClassRoster'...10, 'classLetter': 'A'}}, input_type=dict]
    For further information visit https://errors.pydantic.dev/2.10/v/missing

the link didnt give me any new info and the error doesnt tell me where these fields are missing

P

Proman4713 🇵🇸•9/12/25, 10:08 PM

@samjs is it just me or is cloudflare's schema pretty much unrelated to what the model wants?

P

Proman4713 🇵🇸•9/12/25, 10:08 PM

I'm not even supposed to have "name" in there

P

Proman4713 🇵🇸•9/12/25, 10:08 PM

mistral's videos say they want name, but not tool_call_id

P

Proman4713 🇵🇸•9/12/25, 10:10 PM

and this shows that:

P

Proman4713 🇵🇸•9/12/25, 10:11 PM

P

Proman4713 🇵🇸•9/12/25, 10:14 PM

apparently, I'm guessing it's checking the old reply from the assistant:

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "name": "getClassRoster",
        "arguments": {
          "grade": 10,
          "classLetter": "A"
        }
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "name": "getClassRoster",
        "arguments": {
          "grade": 10,
          "classLetter": "A"
        }
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "name": "getClassRoster",
        "arguments": {
          "grade": 10,
          "classLetter": "A"
        }
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "name": "getClassRoster",
        "arguments": {
          "grade": 10,
          "classLetter": "A"
        }
      }
    ]
  },

it's asking for type, function, and id, but it didnt provide these things when it first gave this result!

P

Proman4713 🇵🇸•9/12/25, 10:15 PM

fine, i'm converting it myself

P

Proman4713 🇵🇸•9/12/25, 10:15 PM

just get this thing to work

P

Proman4713 🇵🇸•9/12/25, 10:16 PM

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "type": "function",
        "function": {
          "name": "getClassRoster",
          "parameters": {
            "grade": 10,
            "classLetter": "A"
          }
        },
        "id": "000000001"
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "type": "function",
        "function": {
          "name": "getClassRoster",
          "parameters": {
            "grade": 10,
            "classLetter": "A"
          }
        },
        "id": "000000001"
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "type": "function",
        "function": {
          "name": "getClassRoster",
          "parameters": {
            "grade": 10,
            "classLetter": "A"
          }
        },
        "id": "000000001"
      }
    ]
  },

{
    "role": "assistant",
    "content": "",
    "tool_calls": [
      {
        "type": "function",
        "function": {
          "name": "getClassRoster",
          "parameters": {
            "grade": 10,
            "classLetter": "A"
          }
        },
        "id": "000000001"
      }
    ]
  },

oh GOD this worked and now it wants me to turn parameters into arguments

P

Proman4713 🇵🇸•9/12/25, 10:16 PM

why is this??

P

Proman4713 🇵🇸•9/12/25, 10:18 PM

oh god and now we're back at internal server error 3043

P

Proman4713 🇵🇸•9/12/25, 10:18 PM

I'm continuing in workers-aiany news?

P

Proman4713 🇵🇸•9/12/25, 10:18 PM

I'm flooding too much

O

omgwot•9/13/25, 10:03 AM

hey all, i'm getting 400s when using

@cf/openai/gpt-oss-120b

@cf/openai/gpt-oss-120b

@cf/openai/gpt-oss-120b

@cf/openai/gpt-oss-120b. is this a known thing? using the completions API:

import { createClient as createOpenAIClient } from "./client";
import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";

export async function callCloudflareAI(
  model: string,
  messages: ChatCompletionMessageParam[],
  options: {
    temperature?: number;
    max_tokens?: number;
  } = {}
): Promise<string> {
  const client = createOpenAIClient();

  const response = await client.chat.completions.create({
    model,
    messages,
    temperature: options.temperature,
    max_tokens: options.max_tokens
  });

  return response.choices[0]?.message?.content || "";
}

import { createClient as createOpenAIClient } from "./client";
import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";

export async function callCloudflareAI(
  model: string,
  messages: ChatCompletionMessageParam[],
  options: {
    temperature?: number;
    max_tokens?: number;
  } = {}
): Promise<string> {
  const client = createOpenAIClient();

  const response = await client.chat.completions.create({
    model,
    messages,
    temperature: options.temperature,
    max_tokens: options.max_tokens
  });

  return response.choices[0]?.message?.content || "";
}

import { createClient as createOpenAIClient } from "./client";
import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";

export async function callCloudflareAI(
  model: string,
  messages: ChatCompletionMessageParam[],
  options: {
    temperature?: number;
    max_tokens?: number;
  } = {}
): Promise<string> {
  const client = createOpenAIClient();

  const response = await client.chat.completions.create({
    model,
    messages,
    temperature: options.temperature,
    max_tokens: options.max_tokens
  });

  return response.choices[0]?.message?.content || "";
}

import { createClient as createOpenAIClient } from "./client";
import type { ChatCompletionMessageParam } from "openai/resources/chat/completions";

export async function callCloudflareAI(
  model: string,
  messages: ChatCompletionMessageParam[],
  options: {
    temperature?: number;
    max_tokens?: number;
  } = {}
): Promise<string> {
  const client = createOpenAIClient();

  const response = await client.chat.completions.create({
    model,
    messages,
    temperature: options.temperature,
    max_tokens: options.max_tokens
  });

  return response.choices[0]?.message?.content || "";
}

should I be using responses instead? thanks.

Oomgwot hey all, i'm getting 400s when using `@cf/openai/gpt-oss-120b`. is this a known ...

H

HimanshuOP•9/13/25, 10:41 AM

You're right, gpt-oss models support the responses API not the completions API. Try using that.

O

omgwot•9/13/25, 10:41 AM

feels like this should all just work seamlessly

HHimanshu I've successfully integrated Aura and Nova models from Deepgram into OpenGPT. F...

T

TuChutya•9/14/25, 4:06 AM

Wao

T

Tim•9/14/25, 10:14 PM

Hi, in relation to the deepgram tools Nova-3 and aura, are they wrappers connecting to deepgrams infrastructure? Or are you using the self-hosted platform and hosting it yourself?

TTim Hi, in relation to the deepgram tools Nova-3 and aura, are they wrappers connect...

I

Isaac McFadyen•9/14/25, 11:34 PM

Per the blog https://blog.cloudflare.com/workers-ai-partner-models/ it's on Cloudflare's own infra.

I

Isaac McFadyen•9/14/25, 11:35 PM

[...] partnered with Leonardo.Ai and Deepgram to bring their latest and greatest models to Workers AI, hosted on Cloudflare’s infrastructure

T

toadilywasted•9/16/25, 3:16 AM

What's the pricing for embeddinggemma-300m ? I can't find any on the page

R

robinsloan•9/16/25, 5:04 PM

I'm having the same issue exactly that @Object documented here, back in May 2025: workers-ai

Any ideas from the CF team?

H

HimanshuOP•9/16/25, 7:13 PM

I'm trying to use Cloudflare-hosted GPT OSS models with AI SDK v5. I integrated workers-ai-provider, but it doesn't seem to support these models, as I'm getting empty responses. @Sunil Pai any input?

HHimanshu I'm trying to use Cloudflare-hosted GPT OSS models with AI SDK v5. I integrated ...

I

Isaac McFadyen•9/16/25, 7:45 PM

Please do not ping people.

S

SuperHelpflare•9/16/25, 7:45 PM

Please do not ping community members for non-moderation reasons. Doing so will not solve your issue faster and will make people less likely to want to help you.

A

ajgeiss0702•9/17/25, 3:22 AM

:/

Aajgeiss0702 :/

S

samjs•9/17/25, 4:19 PM

Hey @ajgeiss0702 . Which gpt model is that? And can you share your account ID with me (by DM) and I can look into this for you.

Hey @samjs , I'd like to report a bug in the documentation of MeloTTS model: https://developers.clo

Similar Threads

Similar Threads

Similar Threads