The Orchestrator › Models › Alibaba
Alibaba: Qwen3.8 2.4T A95B
Open-weights release of the Qwen3.8 flagship (2.4T MoE, ~95B active); thinking always on with reasoning_effort low/medium/xhigh. The hosted Qwen 3.8 Max (vision, non-thinking, 1M default context) is Alibaba-only.
Specifications
| Provider | Alibaba |
| Model ID | alibaba/qwen3.8-2.4t-a95b |
| Context window | 262K tokens (262,144) |
| Modalities | text + image → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-08-03 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | alibaba/qwen3.8-2.4t-a95b | $2.00 | $6.00 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $2.00 | $6.00 | 262K |
Capabilities
Vision (image input)Agentic tool useStructured outputs256K+ context windowControllable reasoning
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs