Models
Price comparison

Qwen3.5-35B-A3B

Qwen3.5-35B-A3B by Alibaba Cloud: 5 offers. From €0.13 per 1M input tokens. No offer with EU processing is listed.

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)65,536
Reasoningmit
Parameters (bn)35.95
Open weights✓ yes
LicenceApache-2.0
VRAM at 4-bit (GB)24 (RTX PRO 4000)
Released–

searchit Entity Extraction (–): 41 %

Offers with processing in the EU (0)

No offers in this group.

Offers outside the EU (5)

ProviderCountryVariantInputOutputSourceAs of
DeepInfraUSstandard€0.13€0.89deepinfra.com14 Oct 2026
ParasailUSstandard€0.13€0.89www.parasail.io2 Oct 2026
ParasailUSserverless€0.13€0.89www.parasail.io2 Oct 2026
Venice.aiUSstandard€0.13€0.89docs.venice.ai14 Oct 2026
Novita AIUSstandard€0.22€1.79novita.ai13 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)84.5
Humanity's Last Exam (Artificial Analysis)21
OTIS Mock AIME 2024-2025 (Epoch AI)70
Vectara HHEM-2.310.5
Vectara HHEM-2.3 – antwortrate99.8
Vectara HHEM-2.3 – halluzination10.5
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer beziehungen20.3
searchit Extraktions-Messlauf REPO-9 (PROMPT-CRAWLER-TEXT-START, 8 Dokumente × 3 Läufe) – treffer entitaeten61.6

Report an error on this page