Qwen3.8-Max
MoE premier2.4T total params, ~95B active per token (MoE). Built on the Qwen 3.5 architectural foundation with a hybrid attention mechanism; roughly 4% expert activation per forward pass. Native 1M context, 131K max output, 262K max reasoning. Multimodal: text + image in, text out. Reasoning controls: reasoning_effort (xhigh default / medium / low), enable_thinking, preserve_thinking.
Launched 2026-08-03 on Alibaba Cloud Model Studio (DashScope) and QwenWork - the first Max-class Qwen to get a public per-token API. List price $2/M input (flat across the full 1M context), $6/M output, $0.25/M implicit cache hit - cheaper than the Qwen3.7-Max list price ($2.50/$7.50). OpenAI- and Anthropic-protocol compatible; three regional endpoints (Beijing, Singapore, US-Virginia). First shown 2026-07-19 at WAIC Shanghai.
Open weights promised ~2026-08-10 on HuggingFace and ModelScope (Apache-2.0) - the first open-weight Max-class Qwen ever. Until the checkpoint ships, no model_variants are seeded (quant sizes unknown) and the model is cloud-only, so it does not appear on the local-run pages (e.g. /dgx-spark) and the “Run it locally” / “Download options” sections stay off the model card.
Vendor benchmarks: GPQA-Diamond 92.6, PaperBench 93.0, IFBench 82.8, MathVision 95.2, LogicVista 91.9, OSWorld-Verified 86.1. Weakest flagship scores: HLE 43.6, SWE-bench Pro 67.7, FrontierSWE 73.5 (Fable 5 leads both at 80.0 / 88.8). Arena: 5th Text, 2nd Vision, 4th Frontend Code. Treat the agentic-coding figures as vendor-reported pending independent replication.
AI-generated content marks
This model embeds text watermarks in generated text and adds C2PA provenance metadata to supported files such as .png, .jpg, and .svg. Marks can be lost through editing, screenshots, or format conversion, so their absence does not prove a file is human-made.
- 2400.0B
- 1000k
- apache 2.0
- 🇨🇳 China
- Aug 2026
Benchmark scores
Vendor-reported - from the developer's own model card / tech report
Vendor-reported - from the developer's own model card / tech report
Ran this model on your own hardware? Join free and add your measured tok/s to the community numbers.
Score per dollar
46 pts per $/M input
general_score (91) divided by cheapest input price ($2.00/M). Higher is better value. See live pricing.
Related models
Save your hardware and every model page answers the real question: will it run on your machine, and how fast?
Join free - save your rig →Or run it in the cloud
Live per-provider pricing, throughput and uptime - refreshed about 2 months ago via OpenRouter. Click a column to sort.
some pricing may be stale - last verified 2026-08-15
| Provider | Type | Input $/M | Output $/M | Cache $/M | Tok/s | Latency | Uptime | Value |
|---|---|---|---|---|---|---|---|---|
| API | 2.00 | 6.00 | 0.250 | - | - | - | cheapest | |
|
DigitalOcean
stale
|
API | 2.00 | 6.00 | 0.200 | - | - | - | |
| Sub | - | - | - | - | - | - | $6.00/mo Token Plan Lite (Individual) | |
| Sub | - | - | - | - | - | - | $10.00/mo Go ($5 first month) | |
| Sub | - | - | - | - | - | - | $18.00/mo Token Plan Standard (Individual) | |
| Sub | - | - | - | - | - | - | $20.00/mo Token Plan Standard Seat (Team) | |
| Sub | - | - | - | - | - | - | $68.00/mo Token Plan Pro (Individual) | |
| Sub | - | - | - | - | - | - | $75.00/mo Token Plan Pro Seat (Team) | |
| Sub | - | - | - | - | - | - | $200.00/mo Token Plan Max Seat (Team) |
Default order: throughput among 95%+ uptime providers, then latency; subscriptions last. Sort by any column. Subscription rows show $/mo in the Value column - per-token columns are "-". Affiliate links are marked sponsored / nofollow. Confirm current pricing on the provider's site before committing.
Detailed API pricing page + JSON endpoint →
See who runs Alibaba in production →
Inference cost over time
Data accumulates from the first daily sync - longer ranges populate over time. Prices come from OpenRouter snapshots, not a historical API.