ModelPriceWatch.com
Last scan 2026-08-09 Models tracked 198 Providers 30 Cheapest paid Granite 4.0 Micro $0.017/Mtok in Every price links to its source

Qwen3.5-397B-A17B

by Alibaba · 397B (A17B) parameters

Current mid tier open weights mid tier

Today's price · per 1M tokens

Input

$0.600

per 1M tokens

Output

$3.60

per 1M tokens

Blended

$1.35

blended $/1M — 3:1 weighted input:output

Source: official Alibaba pricing · read Aug 7, 2026 MODELPRICEWATCH.COM · 2026-08-09

Overview

Large open-weights Qwen MoE (397B total, 17B active) served by Alibaba, the model's maker, on Model Studio. $0.60/$3.60 per 1M tokens, a single 0–256K tier, with thinking-mode output billed at the same rate as non-thinking. 256K-token context, text-only.

Run it yourself

Deploy this open model on rented GPUs

Open weights mean you can self-host instead of paying per-token API prices. These platforms let you serve it on demand — often cheaper at scale.

Partner links — we may earn a commission if you sign up, at no cost to you. We only list platforms we'd recommend regardless.

Capabilities

struck through = not supported
Input 1/5
Text ✓ Image Audio Video PDF
Output 1/5
Text ✓ Image Audio Video Embedding
Features 2/9
Prompt caching Reasoning Coding Fast inference Long context ✓ Open weights ✓ Multimodal Web search Realtime

Benchmark performance

accuracy % · higher is better
Percentile vs all tracked models 30.7th3 independent measurements
Percentile per $/Mtok 22.7

We hold no per-benchmark accuracy scores for this model yet, so it has no accuracy average. That is a gap in our coverage, not a sign the model is untested — independent evaluators often publish a composite index for a new model long before releasing its per-benchmark numbers. The percentile above is its standing across the independent composites below.

Independent composite scores
  • AA Intelligence Index: 34.3 (Artificial Analysis composite across reasoning, knowledge and coding evals)
  • AA Agentic Index: 19.8 (Tool use, planning, autonomy)
  • AA-Omniscience Index: -30.8 (−100–100)
How it stacks up
  • Ranks #99 of 150 comparably-measured models by percentile score, across 3 independent measurements
  • Ranks #104 of 150 comparably-tested models by normalized performance per dollar

Source: Artificial Analysis · updated Aug 7, 2026 · See full rankings →

Specifications

Provider
Alibaba
Context window
262K tokens
Modality
text
Parameters
397B (A17B)
Open source
Yes — open weights available
Released
Feb 16, 2026
Status
Current
Last updated
Aug 7, 2026
Tags
mid-tieropen-weightsmoe

Availability verified: Aug 7, 2026 — listed on Alibaba's own page