Using Qwen3-235B-A22B-Instruct-2507 on GCP Vertex AI
Implementation guide · Qwen3 · Alibaba
GCP Vertex AI exposes Qwen3-235B-A22B-Instruct-2507 through model ID qwen3-235b-a22b-instruct-2507-maas. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.
Last refreshed 2026-10-19. Next refresh: weekly.
Quick Start
- 1
- 2Use the GCP Vertex AI SDK or REST API to call
qwen3-235b-a22b-instruct-2507-maas— see the documentation for request format. - 3
Code Examples
pip install google-cloud-aiplatformGOOGLE_CLOUD_PROJECTqwen3-235b-a22b-instruct-2507-maasFor Google-published models use the model name directly, e.g. "gemini-2.0-flash-001". For third-party publishers (Anthropic, Meta, etc.) use the full publisher path, e.g. "publishers/anthropic/models/claude-3-5-sonnet-v2@20241022".
import os
import vertexai
from vertexai.generative_models import GenerativeModel
# Reads GOOGLE_CLOUD_PROJECT from env; authenticates via Application Default Credentials
vertexai.init(project=os.environ["GOOGLE_CLOUD_PROJECT"], location="us-central1")
model = GenerativeModel("qwen3-235b-a22b-instruct-2507-maas")
response = model.generate_content("Hello")
print(response.text)Pricing on GCP Vertex AI
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.22 |
| Output tokens | $0.88 |
Capabilities
No model capability flags are currently sourced.
About Qwen3-235B-A22B-Instruct-2507
Qwen3-235B-A22B-Instruct-2507 is Alibaba Qwen's July 2025 non-thinking update of Qwen3-235B-A22B, a mixture-of-experts model with 22B active of 235B total parameters. Qwen dropped the hybrid thinking mode and trained separate Instruct and Thinking models; this is the Instruct release, with Apache-2.0 open weights on Hugging Face.