Alibaba LLM Models

19 Alibaba models on WaveSpeedAI — transparent per-token pricing, OpenAI-compatible endpoint, no cold starts.

Qwen3.8 27b API

qwen/qwen3.8-27b

$0.425/M in· $2.55/M out· 1M ctx

Qwen3.8 Flash API

qwen/qwen3.8-flash

$0.15/M in· $0.47/M out· 1M ctx

Qwen3.7 Flash API

qwen/qwen3.7-flash

$0.03/M in· $0.13/M out· 1M ctx

Qwen3.8 Max Prime API

qwen/qwen3.8-max-prime

$4/M in· $12/M out· 1M ctx

Qwen3.6 35b A3b API

qwen/qwen3.6-35b-a3b

$0.1/M in· $0.9/M out· 262K ctx

Qwen3.8 Max 0902 API

qwen/qwen3.8-max-0902

$2/M in· $6/M out· 1M ctx

Qwen3.7 Max API

qwen/qwen3.7-max

$1.475/M in· $4.425/M out· 1M ctx

$0.26/M in· $0.78/M out· 1M ctx

Qwen2.5 Vl 72b Instruct API

qwen/qwen2.5-vl-72b-instruct

$0.8/M in· $1/M out· 32K ctx

Qwen3 Coder API

qwen/qwen3-coder

$0.35/M in· $1.5/M out· 262K ctx

Qwen3 Coder Next API

qwen/qwen3-coder-next

$0.12/M in· $0.8/M out· 262K ctx

Qwen3 Vl 235b A22b Instruct API

qwen/qwen3-vl-235b-a22b-instruct

$0.21/M in· $1.9/M out· 262K ctx

Qwen3 Vl 30b A3b Instruct API

qwen/qwen3-vl-30b-a3b-instruct

$0.2/M in· $0.7/M out· 131K ctx

Qwen3.6 Plus API

qwen/qwen3.6-plus

$0.325/M in· $1.95/M out· 1M ctx

Qwen3.6 Flash API

qwen/qwen3.6-flash

$0.1875/M in· $1.125/M out· 1M ctx

Qwen3.6 27b API

qwen/qwen3.6-27b

$0.45/M in· $2.7/M out· 262K ctx

Qwen3.7 Plus API

qwen/qwen3.7-plus

$0.32/M in· $1.28/M out· 1M ctx

Qwen3.8 2.4t A95b API

qwen/qwen3.8-2.4t-a95b

$2/M in· $6/M out· 1.0M ctx

Qwen3.8 Omni Flash API

qwen/qwen3.8-omni-flash

$0.15/M in· $0.47/M out· 1M ctx

Browse all LLMs

Compare every Claude, GPT, Gemini, Qwen, DeepSeek, Llama, Grok and more.

wavespeed.ai/llm →

Open the Playground

Run any model live, see latency and cost in real time.

wavespeed.ai/llm/playground →

Seedream 5.5 is LIVE | Try in Image Generator →