All Models
Qwen 3.8 Max
Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input and returns text,...
Benchmarks
Available Providers (46)
| Provider | Model ID | Input Cost | Output Cost | Context | Max Output | Docs |
|---|---|---|---|---|---|---|
 Alibaba Token Plan | qwen3.8-max-preview | $0/MTok | $0/MTok | 1M | 131.1K | |
| Alibaba Token Plan | qwen3.8-max | $0/MTok | $0/MTok | 1M | 131.1K | |
 Kenari | qwen3-8-max | $0/MTok | $0/MTok | 1M | 131.1K | |
 SCNet Token Plan | Qwen3.8-Max | $0/MTok | $0/MTok | 1M | 131.1K | |
 Alibaba Token Plan (China) | qwen3.8-max-preview | $0/MTok | $0/MTok | 1M | 131.1K | |
| Alibaba Token Plan (China) | qwen3.8-max | $0/MTok | $0/MTok | 1M | 131.1K | |
 Vancine | qwen3.8-max | $1.60/MTok | $4.80/MTok | 1M | 131.1K | |
 Deep Infra | Qwen/Qwen3.8-Max | $1.65/MTok | $4.95/MTok | 256K | 131.1K | |
 AIHubMix | qwen3.8-max | $1.69/MTok | $5.07/MTok | 991K | 128K | |
 Ofox | qwen/qwen3.8-max-0902 | $1.71/MTok | $5.14/MTok | 1M | 131.1K | |
| Ofox | qwen/qwen3.8-max | $1.71/MTok | $5.14/MTok | 1M | 131.1K | |
 Alibaba (China) | qwen3.8-max | $1.78/MTok | $5.33/MTok | 1M | 131.1K | |
 SCX.ai | Qwen3.8-Max | $1.81/MTok | $5.45/MTok | 1M | 131.1K | |
 CrossModel | qwen/qwen3.8-max | $1.88/MTok | $5.63/MTok | 1M | 131.1K | |
 NanoGPT | qwen/qwen3.8-max-0902 | $2/MTok | $6/MTok | 991.8K | 131.1K | |
| NanoGPT | qwen/qwen3.8-max | $2/MTok | $6/MTok | 991K | 65.5K | |
 DigitalOcean | qwen3.8-max | $2/MTok | $6/MTok | 1M | 262.1K | |
 LLM Gateway | alibaba/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
| LLM Gateway | scx-ai-gp/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
| LLM Gateway | novita/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 OrcaRouter | qwen/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Charm Hyper | qwen3.8-max | $2/MTok | $6/MTok | 1M | 65.5K | |
 Requesty | qwen3.8-max | $2/MTok | $6/MTok | 1.0M | 131.1K | |
 Alibaba | qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Vercel AI Gateway | alibaba/qwen3.8-max-0902 | $2/MTok | $6/MTok | 991K | 128K | |
| Vercel AI Gateway | alibaba/qwen3.8-max | $2/MTok | $6/MTok | 262.1K | 128K | |
 DevPass (LLM Gateway) | qwen3.8-max | $2/MTok | $6/MTok | 1M | 1M | |
 Cloudflare AI Gateway | alibaba/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Fireworks AI | accounts/fireworks/models/qwen3p8-max | $2/MTok | $6/MTok | 262.1K | 131.1K | |
 EmpirioLabs AI | qwen3-8-max-0902 | $2/MTok | $6/MTok | 1M | 131.1K | |
| EmpirioLabs AI | qwen3-8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Modal | Qwen/Qwen3.8-2.4T-A95B | $2/MTok | $6/MTok | 1.0M | 131.1K | |
 Kilo Gateway | qwen/qwen3.8-max-0902 | $2/MTok | $6/MTok | 1M | 131.1K | |
 Merge Gateway | qwen/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Abacus | qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 OpenRouter | qwen/qwen3.8-max-0902 | $2/MTok | $6/MTok | 1M | 131.1K | |
 ClinePass | cline-pass/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
| Ofox | bailian/qwen3.8-max-0902 | $2/MTok | $6/MTok | 1M | 131.1K | |
| Ofox | bailian/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 OpenCode Go | qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 Eden AI | qwen/qwen3.8-max-0902 | $2/MTok | $6/MTok | 1M | 131.1K | |
| Eden AI | qwen/qwen3.8-max | $2/MTok | $6/MTok | 1M | 131.1K | |
 302.AI | qwen3.8-max | $2.16/MTok | $6.36/MTok | 1M | 131.1K | |
 above.dev | qwen3.8-max | $2.20/MTok | $6.60/MTok | 1M | 32.8K | |
 Impossibl | qwen/qwen3.8-max-preview | $2.50/MTok | $7.50/MTok | 1M | 131.1K | |
 Venice AI | qwen-3-8-max | $2.50/MTok | $7.50/MTok | 1M | 131.1K |
Capabilities
Reasoning
Tool Calling
Attachments
Open Weights
Structured Output