Models
Price comparison

Qwen3.5-397B-A17B

Qwen3.5-397B-A17B by Alibaba Cloud: 14 offers. From €0.22 per 1M input tokens, with EU processing from €0.60.

Calculate costs for this modelCompare offersView price history

Profile

Profile
DeveloperAlibaba Cloud
TypeLanguage models
OriginCN
Input typestext+bild+video
Context (tokens)262,144
Max. output (tokens)235,929
Reasoningohne
Parameters (bn)403.4
Open weights✓ yes
LicenceApache-2.0
VRAM at 4-bit (GB)226 (4 × RTX PRO 6000)
Released18 Mar 2026

searchit Entity Extraction (24 Sept 2026): 45.2 %

Offers with processing in the EU (6)

ProviderCountryVariantInputOutputSourceAs of
IONOS AI Model HubDEstandard€0.60€3.58cloud.ionos.com6 Oct 2026
cortecsATstandard€0.60€3.60api.cortecs.ai14 Oct 2026
OVHcloudFRstandard€0.60€3.60www.ovhcloud.com13 Oct 2026
ScalewayFRstandard€0.60€3.60www.scaleway.com13 Oct 2026
HostYourAINLstandard€0.69€4.14hostyourai.com14 Oct 2026
GreenPTNLstandard€0.70€4.35docs.greenpt.ai12 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

Offers outside the EU (8)

ProviderCountryVariantInputOutputSourceAs of
ParasailUSbatch€0.22€1.61www.parasail.io2 Oct 2026
Chutes–standard€0.40€2.68llm.chutes.ai14 Oct 2026
DeepInfraUSstandard€0.40€2.68deepinfra.com14 Oct 2026
ParasailUSstandard€0.45€3.22www.parasail.io2 Oct 2026
ParasailUSserverless€0.45€3.22www.parasail.io2 Oct 2026
Nebius Token FactoryNLstandard€0.54€3.22tokenfactory.nebius.com14 Oct 2026
Novita AIUSstandard€0.54€3.22novita.ai13 Oct 2026
InfomaniakCHstandard€0.86€3.87www.infomaniak.com13 Oct 2026

€ per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 14 Oct 2026.

AI Act

Whether the developer has signed the Code of Practice for general-purpose AI models: unknown. What this means is explained under “EU and AI Act”. EU processing and AI Act

Benchmarks

Benchmarks
GPQA Diamond (Artificial Analysis)89.3
Humanity's Last Exam (Artificial Analysis)29
OTIS Mock AIME 2024-2025 (Epoch AI)88.89
FrontierMath Tiers 1-3 v2 (Epoch AI)31.2
HallusionBench (llm-stats-Abzug)0.71
MMMU-Pro (llm-stats-Abzug, Rang 1..50 von 69)0.79
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen30.2
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten60.2
MMLU-Pro (TIGER-Lab Leaderboard)87.8

Report an error on this page