MODELS / 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.

TEXTREASONINGREASONINGTOOL-USEIMPLICIT-CACHING
262.1K
CONTEXT WINDOW
131.1K
MAX OUTPUT TOKENS
$2 / 1M tokens
INPUT PRICE
$6 / 1M tokens
OUTPUT PRICE
QUICKSTART

Call it in one request.

OpenAI-compatible — change the base URL, and the setup is complete.

SHELL
curl https://enterprise.blackbox.ai/v1/chat/completions \
  -H "Authorization: Bearer $BLACKBOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/alibaba/qwen3.8-2.4t-a95b",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
INPUT: textOUTPUT: textRELEASED: 2026-08-03
RELATED MODELS

Also worth a look.

ALIBABA

Qwen 3 32B

128K context · $0.16 / 1M tokens input · $0.64 / 1M tokens output

ALIBABA

Qwen 3 Coder 30B A3B Instruct

262.1K context · $0.15 / 1M tokens input · $0.6 / 1M tokens output

ALIBABA

Qwen 3 Max Thinking

256K context · $1.20 / 1M tokens input · $6 / 1M tokens output