Skip to main content
Alibaba

Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B by Alibaba — compare inference API pricing across providers.

Input from
$2.00 / 1M tokens
across 3 providers

API Pricing

Cheapest on Deep Infra 8% below avg
ProviderInput / 1MOutput / 1MCached / 1M
$2.00$6.00$0.200
$2.00$6.00$0.250
$2.50$6.25-

Prices updated daily. Last check: Aug 14, 2026

Qwen3.8 2.4T A95B pricing by provider

Input, output, and batch rates, plus alternatives, for one provider at a time.

Performance & Benchmarks

Source: Artificial Analysis →
Intelligence
57.7 / 100
Coding
71.9 / 100
Output Speed
50.3 t/s
Latency (TTFT)
1.7s

Reasoning & Knowledge

  • GPQA Diamond93.5%
  • Humanity's Last Exam42.4%

Coding

  • SciCode51.6%

Agentic & Tool Use

  • Terminal-Bench v2.182.0%
  • τ-bench Banking49.1%

Instruction & Long Context

  • Long-Context Reasoning75.3%

Benchmarks measured Aug 2026. Scores are independent evaluations, not vendor-reported.

Model Details

General

Creator
Alibaba
Modalities
Text

Capabilities

Tool Calling
No
Open Source
No