Provider

Alibaba

Models198in catalog

Largest context1.0MQwen3.8 2.4T A95B (batch)

Avg context

272K

Cheapest input

Free/M

Qwen3 4b Instruct 2507 Gguf

Largest output

909K

Qwen3.8 2.4T A95B (batch)

Speed tiers

balanced 110fast 66deep 22

Capabilities

What Alibaba models support across the catalog.

Vision

55 / 198

28% of models

Tool use

128 / 198

65% of models

Function calling

128 / 198

65% of models

Extended thinking

90 / 198

45% of models

Streaming

198 / 198

100% of models

Prompt caching

52 / 198

26% of models

Sorted by context window, largest first. Tap a row for full specs.

Model	Context	Max output	Input $/M	Speed
Qwen3.8 2.4T A95B (batch)Qwen	1.0M	909K	$2.00/M	balanced
Qwen3.5-FlashQwen	1M	66K	$0.065/M	fast
Qwen3.5 Plus 2026-02-15Qwen	1M	66K	$0.260/M	balanced
Qwen3.6 FlashQwen	1M	66K	$0.188/M	fast
Qwen3.6 PlusQwen	1M	66K	$0.325/M	balanced
Qwen3.6 Plus (free)Qwen	1M	66K	—	balanced
Qwen3.7 FlashQwen	1M	66K	$0.030/M	fast
Qwen3.7 MaxQwen	1M	66K	$1.25/M	balanced
Qwen3.7 PlusQwen	1M	66K	$0.320/M	balanced
Qwen3.8 FlashQwen	1M	131K	$0.150/M	fast
Qwen3.8 MaxQwen	1M	131K	$1.65/M	balanced
Qwen3.8 Max (0902)Qwen	1M	131K	$1.65/M	balanced
Qwen3.8 Max PrimeQwen	1M	131K	$4.00/M	balanced
Qwen CoderQwen	1M	16K	$0.300/M	balanced
Qwen Plus 0728 (thinking)Qwen	1M	33K	—	deep
Qwen Turbo 2024 11 01Qwen	1M	8K	$0.050/M	balanced
Qwen Turbo 2025 04 28Qwen	1M	16K	$0.050/M	balanced
Qwen Turbo LatestQwen	1M	16K	$0.050/M	balanced
Qwen3 Coder FlashQwen	998K	66K	$0.195/M	fast
Qwen3 Coder Flash 2025 07 28Qwen	998K	66K	—	fast
Qwen3 Coder PlusQwen	998K	66K	$0.650/M	balanced
Qwen3 Coder Plus 2025 07 22Qwen	998K	66K	—	balanced
Qwen FlashQwen	998K	33K	—	fast
Qwen Flash 2025 07 28Qwen	998K	33K	—	fast
Qwen Plus 0728Qwen	998K	33K	$0.260/M	balanced

Showing 25 of 198 models

How Alibaba models rank against the full catalog.