Skip to content

Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI #7733

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI #7733

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
4c5d79e
Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI
diwakar-s-maurya Sep 6, 2025
d95de20
Update max tokens for Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI
diwakar-s-maurya Sep 6, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
10 changes: 10 additions & 0 deletions packages/types/src/providers/vertex.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,6 +294,15 @@ export const vertexModels = {
outputPrice: 1.15,
description: "Meta Llama 4 Maverick 17B Instruct model, 128K context.",
},
"qwen/qwen3-coder-480b-a35b-instruct-maas": {
Copy link
Contributor

@roomote roomote bot Sep 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I noticed the model ID uses a namespace prefix qwen/ while the other MaaS model llama-4-maverick-17b-128e-instruct-maas doesn't use any prefix. Is this intentional? Should we maintain consistency across MaaS models, or is the namespace required for Qwen models specifically?

Copy link
Author

@diwakar-s-maurya diwakar-s-maurya Sep 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This is intentional. The model name to be passed to vertex ai is "qwen/qwen3-coder-480b-a35b-instruct-maas".

https://console.cloud.google.com/vertex-ai/publishers/qwen/model-garden/qwen3-coder-480b-a35b-instruct-maas

ENDPOINT=us-south1-aiplatform.googleapis.com
REGION=us-south1
PROJECT_ID="YOUR_PROJECT_ID"

curl \
  -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" https://${ENDPOINT}/v1/projects/${PROJECT_ID}/locations/${REGION}/endpoints/openapi/chat/completions \
  -d '{"model":"qwen/qwen3-coder-480b-a35b-instruct-maas", "stream":true, "messages":[{"role": "user", "content": "Write a quick sort algorithm"}]}'

maxTokens: 65_536,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1,
outputPrice: 4,
description: "Qwen 3 Coder 480B Instruct",
Copy link
Contributor

@roomote roomote bot Sep 6, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could we make the description more detailed to match the pattern of other models? Consider:

Suggested change
description: "Qwen 3 Coder 480B Instruct",
description: "Qwen 3 Coder 480B Instruct model, 262K context.",

This would be consistent with the Llama model description above which includes the context window size.

},
} as const satisfies Record<string, ModelInfo>

export const VERTEX_REGIONS = [
Expand All @@ -306,6 +315,7 @@ export const VERTEX_REGIONS = [
{ value: "us-west2", label: "us-west2" },
{ value: "us-west3", label: "us-west3" },
{ value: "us-west4", label: "us-west4" },
{ value: "us-south1", label: "us-south1" },
{ value: "northamerica-northeast1", label: "northamerica-northeast1" },
{ value: "northamerica-northeast2", label: "northamerica-northeast2" },
{ value: "southamerica-east1", label: "southamerica-east1" },
Expand Down
Loading