Qwen3.8-2.4T-A95B
View website
Released August 2026 under Apache 2.0, the open-weight checkpoint behind Qwen3.8-Max: a 2.4T-parameter MoE activating 95B per token across 92 hybrid Gated DeltaNet and Gated Attention layers, with 512 experts (10 routed plus 1 shared active). Requires thinking mode for all interactions, while the hosted Qwen3.8-Max variant adds vision input, a non-thinking mode, and built-in tools.
At a glance
- Context window
- 262K tokens
- Max output
- 131K tokens
- Modalities
- Text Text → Text Text
Capabilities
Function calling
Connect to external tools, APIs, and systems.
Structured output
Return responses in structured formats like JSON.
Pricing by provider
| Provider | Input / 1M tokens | Output / 1M tokens | |
|---|---|---|---|
Together
|
$2.50 | $6.25 | 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.