new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

alibaba/models

7 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Alibaba language model usage

Language models can be created using a provider instance. Example: `alibaba('qwen-plus')` or using factory methods `.chatModel('qwen-plus')` or `.languageModel('qwen-plus')`. Models can be used with the `generateText` and `streamText` functions.

Alibaba embedding model creation

Text embedding models can be created using the `.embedding()` factory method. Example: `const model = alibaba.embedding('text-embedding-v4');`

Alibaba embedding model capabilities

Embedding model capabilities: text-embedding-v4 has default dimensions 1024, flexible dimensions 64, 128, 256, 512, 768, 1024, 1536, 2048, max 10 values per call; text-embedding-v3 has default dimensions 1024, flexible dimensions 512, 768, 1024, max 10 values per call.

Alibaba video model creation

Video models can be created using the `.video()` factory method. Example: `alibaba.video('wan2.6-t2v')`. Alibaba supports three video generation modes: text-to-video, image-to-video (first frame), and reference-to-video.

Alibaba text-to-video model capabilities

Text-to-video models: wan2.6-t2v has audio, resolutions 720P/1080P, duration 2-15s; wan2.5-t2v-preview has audio, resolutions 480P/720P/1080P, duration 5s/10s; wan2.7-t2v has audio, resolutions 720P/1080P, duration 2-15s; wan2.7-t2v-2026-06-12 has audio, resolutions 720P/1080P, duration 2-15s.

Alibaba image-to-video model capabilities

Image-to-video (first frame) models: wan2.6-i2v-flash has optional audio, resolutions 720P/1080P, duration 2-15s; wan2.6-i2v has audio, resolutions 720P/1080P, duration 2-15s.

Alibaba reference-to-video model capabilities

Reference-to-video models: wan2.6-r2v-flash has optional audio, resolutions 720P/1080P, duration 2-10s; wan2.6-r2v has audio, resolutions 720P/1080P, duration 2-10s; wan2.7-r2v has audio, resolutions 720P/1080P, duration 2-10s (with video ref) or 2-15s; wan2.7-r2v-2026-06-12 has audio, resolutions 720P/1080P, duration 2-10s (with video ref) or 2-15s.

Give your agent this brain