Qwen3.5 397B A17B

qwen3.5-397b-a17b by Qwen Released February 16, 2026
ReasoningFunction callingStructured outputPrompt cachingWeb searchComputer useImage inputFile inputAudio inputVideo inputEU hostingFree endpointUp to 35% off
Input from
$0.39 / 1M
Output from
$2.34 / 1M
Cached input from
$0.22 / 1M
Context window
262K
Endpoints
8
from 8 providers
Regions
Monde, Europe, Switzerland, États-Unis

About Qwen3.5 397B A17B

Le modèle natif de vision-langage 397B-A17B de la série Qwen3.5 repose sur une architecture hybride qui intègre un mécanisme d’attention linéaire à un modèle « mixture-of-experts » clairsemé, permettant ainsi d’atteindre une efficacité d’inférence supérieure. Il offre des performances de pointe comparables à celles des modèles les plus avancés dans un large éventail de tâches, notamment la compréhension du langage, le raisonnement logique, la génération de code, les tâches basées sur des agents, la compréhension d'images, la compréhension de vidéos et les interactions avec les interfaces graphiques (GUI). Grâce à ses solides capacités de génération de code et de gestion d’agents, le modèle fait preuve d’une forte capacité de généralisation à divers types d’agents.

Qwen3.5 397B A17B est un modèle conversationnel développé par Qwen, disponible sur Eden AI via 8 endpoints chez 8 fournisseurs, à partir de 0,39 $ par million de tokens en entrée et 2,34 $ par million de tokens en sortie, avec une fenêtre de contexte allant jusqu'à 262K tokens.

Providers and prices

8 endpoints from 8 providers, cheapest first, in USD per million tokens. Every one is called with the same Eden AI key: pin one with its endpoint ID, or let Eden AI route for you. .

Endpoint
Region
Context
Input / 1M
Output / 1M
Cached / 1M
Supports
QwenOfficial−35%qwen/qwen3.5-397b-a17b
Monde
262K
$0.6$0.39
$2.34
$
ReasoningToolsJSONCacheVisionWeb
DeepInfra (États-Unis)Official−%deepinfra/Qwen/Qwen3.5-397B-A17B
États-Unis
262K
$0.45$0.45
$3
$0.22
ReasoningToolsJSONCacheVisionWeb
NebiusOfficial−%nebius/Qwen/Qwen3.5-397B-A17B
Monde
262K
$0.6$0.6
$3.6
$0.6
ReasoningToolsJSONCacheVisionWeb
IONOS (Europe)Official−%ionos/Qwen/Qwen3.5-397B-A17B
Europe
262K
$0.6752$0.6752
$4.0511
$
ReasoningToolsJSONCacheVisionWeb
Scaleway (Europe)Official−%scaleway/qwen3.5-397b-a17b
Europe
250K
$0.6752$0.6752
$4.0511
$
ReasoningToolsJSONCacheVisionWeb
OVHcloud (Europe)Official−%ovhcloud/Qwen3.5-397B-A17B
Europe
262K
$0.71$0.71
$4.25
$
ReasoningToolsJSONCacheVisionWeb
GreenPT (Europe)Official−%greenpt/qwen3.5-397b-a17b
Europe
250K
$0.7877$0.7877
$4.8951
$
ReasoningToolsJSONCacheVisionWeb
Infomaniak (Switzerland)Official−%infomaniak/Qwen/Qwen3.5-397B-A17B-FP8
Switzerland
200K
$0.9002$0.9002
$4.0511
$
ReasoningToolsJSONCacheVisionWeb

Performance

Measured on real Eden AI traffic over the last 30 days. Endpoints with too little traffic are not shown.

Fastest first token
0.28 s
Scaleway (Europe)
Lowest latency
33.06 s
Scaleway (Europe)
Highest throughput
104.08 tok/s
OVHcloud (Europe)
Best availability
100%
OVHcloud (Europe)
Endpoint
First token
Latency p50
Latency p95
Throughput
Availability
Cache hits
Tool errors
JSON errors
Qwen
s
s
s
tok/s
%
%
%
%
DeepInfra (États-Unis)
s
s
s
tok/s
%
%
%
%
Nebius
s
s
s
tok/s
%
%
%
%
IONOS (Europe)
s
123.98 s
325.86 s
52.8 tok/s
98.29%
0%
0%
0%
Scaleway (Europe)
0.28 s
33.06 s
149.62 s
89.44 tok/s
99.03%
0%
0%
1.39%
OVHcloud (Europe)
0.63 s
34.93 s
79.47 s
104.08 tok/s
100%
0%
0%
0%
GreenPT (Europe)
s
s
s
tok/s
%
%
%
%
Infomaniak (Switzerland)
s
s
s
tok/s
%
%
%
%

Estimate your monthly cost

Enter your expected volume to compare every endpoint at once.

Call Qwen3.5 397B A17B with Eden AI

Use the model ID to let Eden AI pick an endpoint, or an endpoint ID from the table above to pin one.

import requests

response = requests.post(
    "https://api.edenai.run/v3/chat/completions",
    headers={"Authorization": "Bearer YOUR_EDENAI_API_KEY"},
    json={
        "model": "",
        "messages": [{"role": "user", "content": "Hello!"}],
    },
)
print(response.json())

Questions about Qwen3.5 397B A17B

On Eden AI, prices for this model start at $0.39 per million input tokens and $2.34 per million output tokens. Prices differ by endpoint; the providers table lists each one. .

Up to 262K tokens, depending on the endpoint.

8 endpoints from 8 providers, available in: Monde, Europe, Switzerland, États-Unis. All of them are called with the same Eden AI API key.

Yes. At least one endpoint is hosted in Europe; pin it with its endpoint ID from the providers table to keep requests in the EU.

Over the last 30 days, the fastest first token was 0.28 s (Scaleway (Europe)) and the highest throughput was 104.08 tokens per second (OVHcloud (Europe)).