Qwen3.8-Max
View website
Released August 2026, the hosted flagship of the Qwen3.8 family, built on the 2.4T-parameter Qwen3.8-2.4T-A95B checkpoint that activates 95B per token. Adds vision input, a non-thinking mode, and built-in tools over the open checkpoint, and defaults to xhigh reasoning effort, so thinking tokens bill as output.
At a glance
- Context window
- 1M tokens
- Max output
- 131K tokens
- Modalities
- Text Text Image Image Video Video → Text Text
Capabilities
Function calling
Connect to external tools, APIs, and systems.
Structured output
Return responses in structured formats like JSON.
Web search
Search the web for up-to-date information.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
|
Alibaba Cloud
|
$2.00 | $6.00 | View |
Novita
|
$2.00 | $6.00 | View |
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Compare with other models
Estimated prices shown. Actual costs may vary based on context length, batch size, caching, and provider-specific pricing tiers.