[JS] openAICompatible plugin: `NotFoundError: 404 error while getting model`, I have to declare the ModelID 2 times in the `generate` method

[k33g]

Describe the bug I'm working with Docker Model Runner (OpenAI API Compliant) and I need to declare the model id into the config param to get a completion

To Reproduce

import { genkit, modelRef, z } from 'genkit';
import { openAICompatible } from '@genkit-ai/compat-oai';

const ai = genkit({
  plugins: [
    openAICompatible({
      name: 'openai',
      apiKey: '',
      baseURL: 'http://localhost:12434/engines/v1/',
    }),
  ],
});

const myLocalModel = modelRef({
    name: 'openai/ai/qwen2.5:0.5B-F16',
});


const llmResponse = await ai.generate({
  model: myLocalModel,
  prompt: 'Who is Jean-Luc Picard?',
  config: {
    temperature: 0.9,
    model: 'ai/qwen2.5:0.5B-F16',
  },
});

console.log(llmResponse.text);

Expected behavior In theory it shoud be:

const llmResponse = await ai.generate({
  model: myLocalModel,
  prompt: 'Who is Jean-Luc Picard?',
  config: {
    temperature: 0.9,
  },
});

But if I do not add the modelId to the config object I get this error:

node:internal/modules/run_main:104
    triggerUncaughtException(
    ^

NotFoundError: 404 error while getting model: get model '"qwen2.5:0.5B-F16"': model not found

    at APIError.generate (file:///Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/compat-oai/node_modules/openai/error.mjs:50:20)
    at OpenAI.makeStatusError (file:///Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/compat-oai/node_modules/openai/core.mjs:295:25)
    at OpenAI.makeRequest (file:///Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/compat-oai/node_modules/openai/core.mjs:339:30)
    at process.processTicksAndRejections (node:internal/process/task_queues:105:5)
    at async /Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/compat-oai/lib/model.js:310:18
    at async /Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/core/lib/action.js:142:27
    at async /Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/core/lib/tracing/instrumentation.js:75:24
    at async runInNewSpan (/Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/core/lib/tracing/instrumentation.js:60:10)
    at async actionFn.run (/Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/core/lib/action.js:101:18)
    at async dispatch (/Users/k33g/Library/CloudStorage/Dropbox/genkit/getting-started-with-genkit/1st-steps-with-genkit-js/node_modules/@genkit-ai/core/lib/action.js:52:24) {
  status: 404,
  headers: {
    'content-length': '75',
    'content-type': 'text/plain; charset=utf-8',
    date: 'Sun, 09 Nov 2025 03:29:37 GMT',
    'x-content-type-options': 'nosniff'
  },
  request_id: undefined,
  error: undefined,
  code: undefined,
  param: undefined,
  type: undefined,
  traceId: 'e877c66b9ac2aaba996dd3d76be708d0',
  ignoreFailedSpan: true
}

If I add it, it works

Screenshots If applicable, add screenshots to help explain your problem.

Runtime (please complete the following information):

• OS: MacOS
• Version Tahoe 26.0.1

Node version

• v23.10.0

GenkitJS version

• v1.22.0
• v1.23.0

Additional context With Genkit Go and Docker Model Runner no issue:

func main() {
	ctx := context.Background()
	g := genkit.Init(ctx, genkit.WithPlugins(&openai.OpenAI{
		APIKey: "tada",
		Opts: []option.RequestOption{
			option.WithBaseURL("http://localhost:12434/engines/v1/"),
		},
	}))

	resp, err := genkit.Generate(ctx, g,
		ai.WithModelName("openai/ai/qwen2.5:0.5B-F16"),
		ai.WithMessages(
			ai.NewSystemTextMessage("You are the dungeon master of a D&D game."),
			ai.NewUserTextMessage("Generate a D&D NPC name."),
		),
		ai.WithConfig(map[string]any{"temperature": 0.7}),
	)
	if err != nil {
		log.Fatal(err)
	}

	fmt.Println(resp.Text())
}

[k33g]

The issue still exists with 1.23.0

[k33g]

The issue still exist with 1.24.0

Why I have to specify the model 2 times like this:

const response = await ai.generate({
  model: "openai/ai/qwen2.5:0.5B-F16",
  prompt: 'Who is Jean-Luc Picard?',
  config: {
    temperature: 0.9,
    model: 'ai/qwen2.5:0.5B-F16',
  },
});

Instead of this:

const response = await ai.generate({
  model: "openai/ai/qwen2.5:0.5B-F16",
  prompt: 'Who is Jean-Luc Picard?',
  config: {
    temperature: 0.9,
  },
});