Alibaba Cloud Model Studio
Region matters: qwen3-rerank appears under the Singapore tab, qwen3-vl-rerank and gte-rerank-v2 under the Beijing tab (tab mapping inferred from page order).
Alibaba Cloud Model Studio rerankers - verified
Alibaba Cloud Model Studio reranker models
Alibaba Cloud Model Studio: 3 reranker models, read from the provider's own pages on October 18, 2026. Alibaba Cloud Model Studio rerankers are priced per 1M tokens, from $0.1 per 1M input tokens for qwen3-rerank and qwen3-vl-rerank.
Read from alibabacloud.com. Compare every reranker
- Models
- 3
- Current
- 3
- Older
- 0
- Open weights
- 0
Billing and caveats
Models
qwen3-rerank
qwen3-rerank - API - Per 1M tokens
- Price (provider's unit)
$0.1 per 1M input tokens
“qwen3-rerank · International · $0.1 · 1 million tokens”
alibabacloud.com Note: Billed by input tokens, output free; Singapore region, International deployment scope; 1 million free tokens valid 90 days.
- Status
GAinferred
“The gte-rerank model will be discontinued on May 30, 2026. Switch to qwen3-rerank.”
Status inferred from - alibabacloud.com - Context
4,000 tokens
per query or document; 120,000 per request
“qwen3-rerank · 500 · 4,000 · 120,000 · Over 100 major languages, such as Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, and Russian”
alibabacloud.com - Documents per request
500
hard limit
“qwen3-rerank · 500 · 4,000 · 120,000 · Over 100 major languages, such as Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, and Russian”
alibabacloud.com - Languages
Over 100 major languages
“qwen3-rerank · 500 · 4,000 · 120,000 · Over 100 major languages, such as Chinese, English, Spanish, French, Portuguese, Indonesian, Japanese, Korean, German, and Russian”
alibabacloud.com - Open weights
- Not stated
Note: Model Studio does not state the parameter size or whether this API model matches an open Qwen3-Reranker checkpoint.
Inputs over the per-item limit return HTTP 400 instead of being truncated. Supports a custom instruct parameter.
- Model Studio text rerank API: alibabacloud.com/help/en/model-studio/text-rerank-api
- Model Studio model pricing: alibabacloud.com/help/en/model-studio/model-pricing
qwen3-vl-rerank
qwen3-vl-rerank - API - Per 1M tokens
- Price (provider's unit)
$0.1 per 1M text input tokens; $0.258 per 1M image input tokens
“qwen3-vl-rerank · Text input: $0.1, Image input: $0.258”
alibabacloud.com Note: Listed under the China (Beijing) pricing tab.
- Status
GAinferred
Status inferred: the source lists the model but does not label it.
- Context
8,000 tokens
per item; 120,000 per request
“qwen3-vl-rerank · Text: 100, Image: 40, Video: 4 · 8,000 · 120,000 · 33 major languages, such as Chinese, English, Japanese, Korean, French, and German”
alibabacloud.com - Documents per request
100
hard limit for text documents (40 images, 4 videos)
“qwen3-vl-rerank · Text: 100, Image: 40, Video: 4 · 8,000 · 120,000 · 33 major languages, such as Chinese, English, Japanese, Korean, French, and German”
alibabacloud.com - Languages
33 major languages
“qwen3-vl-rerank · Text: 100, Image: 40, Video: 4 · 8,000 · 120,000 · 33 major languages, such as Chinese, English, Japanese, Korean, French, and German”
alibabacloud.com - Open weights
- Not stated
Note: Not stated.
Multimodal reranker for text, image and video documents; listed under the Beijing tab.
- Model Studio text rerank API: alibabacloud.com/help/en/model-studio/text-rerank-api
- Model Studio model pricing: alibabacloud.com/help/en/model-studio/model-pricing
gte-rerank-v2
gte-rerank-v2 - API - Per 1M tokens
- Price (provider's unit)
$0.115 per 1M text input tokens
“gte-rerank-v2 · Text input: $0.115”
alibabacloud.com Note: Listed under the China (Beijing) pricing tab.
- Status
GAinferred
Status inferred: the source lists the model but does not label it.
- Context
4,000 tokens
per item; 30,000 per request
“gte-rerank-v2 · 500 · 4,000 · 30,000 · Over 50 languages, such as Chinese, English, Japanese, Korean, Thai, Spanish, French, Portuguese, German, Indonesian, and Arabic”
alibabacloud.com - Documents per request
500
hard limit
“gte-rerank-v2 · 500 · 4,000 · 30,000 · Over 50 languages, such as Chinese, English, Japanese, Korean, Thai, Spanish, French, Portuguese, German, Indonesian, and Arabic”
alibabacloud.com - Languages
Over 50 languages
“gte-rerank-v2 · 500 · 4,000 · 30,000 · Over 50 languages, such as Chinese, English, Japanese, Korean, Thai, Spanish, French, Portuguese, German, Indonesian, and Arabic”
alibabacloud.com - Open weights
- Not stated
Note: Not stated.
Distinct from the older gte-rerank model, which Model Studio says was discontinued on May 30, 2026.
- Model Studio text rerank API: alibabacloud.com/help/en/model-studio/text-rerank-api
- Model Studio model pricing: alibabacloud.com/help/en/model-studio/model-pricing
FAQ
How much does Alibaba Cloud Model Studio reranking cost?
qwen3-rerank: $0.1 per 1M input tokens. qwen3-vl-rerank: $0.1 per 1M text input tokens; $0.258 per 1M image input tokens. gte-rerank-v2: $0.115 per 1M text input tokens. Prices are in Alibaba Cloud Model Studio's own units as of October 18, 2026.
What is the context length of Alibaba Cloud Model Studio rerankers?
qwen3-rerank: 4,000 tokens, per query or document; 120,000 per request. qwen3-vl-rerank: 8,000 tokens, per item; 120,000 per request. gte-rerank-v2: 4,000 tokens, per item; 30,000 per request.
Can I run Alibaba Cloud Model Studio rerankers myself?
No official open weights were found in the sources checked; Alibaba Cloud Model Studio documents these as hosted models.
Sources
Last verified from each provider's own docs, pricing pages and Hugging Face cards; every quote was string-matched against the page that day. Prices are shown in the provider's own unit and change without notice, so check the linked source before you commit a budget.
Newsletter
Know when a reranker API changes
One email per week. New model releases, retrieval and pricing updates and what they mean for what you build.