Qwen: Qwen3.8 2.4T A95B
alibaba/qwen3.8-2.4t-a95bQwen3.8 2.4T A95B is the open-weight release of Alibaba's Qwen3.8 Max-class model, a sparse Mixture-of-Experts with 2.4 trillion total and about 95 billion active parameters, published in August 2026 as the first Qwen-Max-class open model. It targets coding, professional work, research and long-horizon agentic tasks, with tunable reasoning depth. Alibaba's hosted Qwen3.8 Max builds on it and adds vision input, a non-thinking mode and official built-in tools.
- Input price
- $2.00USD / 1M tokens
- Output price
- $6.00USD / 1M tokens
- Context window
- 1M
- Max output
- 52.4K
Try the model
Playground
Try a prompt
Your response will appear here
Choose an example or write a prompt, then click Run.
Model card
Specifications
Pricing
- Input
- $2 / 1M tokens
- Output
- $6 / 1M tokens
- Cache read
- $0.25 / 1M tokens
- Cache write
- $2.50 / 1M tokens
Context & modalities
- Context window
- 1,000,000 tokens
- Max output
- 52,429 tokens
- Input
- Text
- Output
- Text
Capabilities
- Chat
- Supported
- Vision
- Not supported
- Reasoning
- Supported
- Structured output
- Supported
- Function calling
- Supported
- Audio input
- Not supported
Access
- Provider
- Alibaba
- Model ID
- alibaba/qwen3.8-2.4t-a95b
- Execution
- sync
- Base URL
- https://api.sandbase.ai
- API
- Chat Completions API
- Endpoint
- /v1/chat/completions
Independent evaluations
Benchmarks
Scores on standardized evaluations, compared with other models on SandBase.
Metrics sourced from Artificial Analysis · Intelligence Index v4.3
Start building
Send your first request
OpenAI-compatible endpoint with unified authentication and usage tracking.
# The quoted heredoc keeps Unicode and shell metacharacters unchanged.
result=$(curl --fail-with-body --silent \
-X POST "https://api.sandbase.ai/v1/chat/completions" \
-H "Authorization: Bearer $SANDBASE_API_KEY" \
-H "Content-Type: application/json" \
--data-binary @- <<'SANDBASE_JSON'
{
"model": "alibaba/qwen3.8-2.4t-a95b",
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2048
}
SANDBASE_JSON
)
printf '%s\n' "$result"Choose your model
Compare models
| Model | Context | Input / 1M | Output / 1M | Released |
|---|---|---|---|---|
Qwen3.8 2.4T A95BThis model Alibaba | 1M | $2.00 | $6.00 | Aug 12, 2026 |
Alibaba | 1M | $4.00 | $12.00 | Sep 23, 2026 |
Alibaba | 1M | $0.15 | $0.47 | Sep 18, 2026 |
Alibaba | 1M | $2.00 | $6.00 | Sep 3, 2026 |
Alibaba | 1M | $0.50 | $3.00 | Aug 14, 2026 |
Alibaba | 1M | $2.00 | $6.00 | Aug 3, 2026 |
Questions
FAQ
How do I call Alibaba Qwen3.8 2.4T A95B through SandBase?
Create a SandBase API key, then send requests with the model ID "alibaba/qwen3.8-2.4t-a95b" to Chat Completions API (/v1/chat/completions) at https://api.sandbase.ai. The request examples on this page show the exact payload.
How much does Alibaba Qwen3.8 2.4T A95B cost?
$2 per 1M input tokens and $6 per 1M output tokens, billed per request from your SandBase balance. Discounts, when available, are shown in the pricing on this page.
What is the context window of Alibaba Qwen3.8 2.4T A95B?
1M tokens of context, with up to 52.4K output tokens per response.
How does Alibaba Qwen3.8 2.4T A95B score on benchmarks?
Alibaba Qwen3.8 2.4T A95B scores 39.9 on the Artificial Analysis Intelligence Index (v4.3), ranking #21 of 84 models on SandBase; Coding Index 71.9, Agentic Index 50.1. Source: Artificial Analysis, measured as Qwen3.8 2.4T A95B.
Which features does Alibaba Qwen3.8 2.4T A95B support?
Alibaba Qwen3.8 2.4T A95B supports reasoning, function calling, structured output. See Specifications above for the full list.
Do I need a separate Alibaba account?
No. One SandBase API key and balance gives you access to Alibaba Qwen3.8 2.4T A95B and the other models in the catalog; you do not need to sign up with Alibaba separately.