AI TOOLS RADAR
Esplora
Tutti i modelli / QWEN
qwen logo
qwen

Qwen: Qwen3.5-122B-A10B

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. $0.26 per million input tokens, $2.08 per million output tokens. 262,144 token context window, maximum output of 262,144 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

Vedi la fonte su OpenRouter Hugging Face
Panoramica

Specifiche del modello

Contesto
262.144 tokens
Output massimo
81.920 tokens
Architettura
text+image+video->text
Tokenizer
Qwen3
Limite di conoscenza
Non indicato
Moderato
No
OPENROUTER

Prezzi completi

Tariffe sincronizzate da OpenRouter, per milione di token.

Input
$0.26
/M tokens
Output
$2.08
/M tokens
API

Configurazione del modello

Parametri predefiniti

temperature
0.6
top_p
0.95
top_k
20

Ragionamento

Moderato
No
Parametri predefiniti
No
API

Avvio rapido

Chiama questo modello tramite l’API compatibile OpenAI di OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3.5-122b-a10b","messages":[{"role":"user","content":"Hello!"}]}'
Capacità e modalità

Input → Output

Input
textimagevideo
Output
text
Ragionamento

No

API

Parametri API supportati

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Provider disponibili

5 provider

Provider live su OpenRouter

Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.

OpenRouter

SiliconFlow

fp8
Contesto
262K
Output massimo
236K
Input
$0.260
Output
$2.08
Lettura cache
Non indicato
Scrittura cache
Non indicato

Alibaba

unknown
Contesto
262K
Output massimo
66K
Input
$0.260
Output
$2.08
Lettura cache
Non indicato
Scrittura cache
Non indicato

DeepInfra

fp4
Contesto
262K
Output massimo
82K
Input
$0.290
Output
$2.40
Lettura cache
Non indicato
Scrittura cache
Non indicato

AtlasCloud

fp8
Contesto
262K
Output massimo
66K
Input
$0.300
Output
$2.40
Lettura cache
$0.300
Scrittura cache
Non indicato

Novita

bf16
Contesto
262K
Output massimo
66K
Input
$0.400
Output
$3.20
Lettura cache
Non indicato
Scrittura cache
Non indicato
qwen

modelli

Tutti i modelli
qwen logoqwen

Qwen: Qwen3.8 Flash

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop interaction, chart analysis, and long-video analysis.

Contesto
1M
Input
text · image · video
Output
text
Input: $0.150Output: $0.470per milione di token
Vedi i dettagli del modello →
qwen logoqwen

Qwen: Qwen3.8 27B

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...

Contesto
1M
Input
text · image · video
Output
text
Input: $0.425Output: $2.55per milione di token
Vedi i dettagli del modello →
qwen logoqwen

Qwen3 Reranker 8B

Qwen3 Reranker 8B is a text reranking model from Alibaba Cloud built on the Qwen3 architecture. It evaluates query-document pairs to produce relevance scores for use in retrieval and RAG...

Contesto
41K
Input
text
Output
rerank
Input: GratuitoOutput: Gratuitoper milione di token
Vedi i dettagli del modello →
qwen logoqwen

Qwen: Qwen3 ASR 1.7B

Qwen3 ASR 1.7B is an automatic speech recognition model from Qwen. It supports multilingual language identification and transcription across 30 languages and 22 Chinese dialects, with streaming and offline inference...

Contesto
Non indicato
Input
audio
Output
transcription
Input: $7.50Output: Gratuitoper milione di token
Vedi i dettagli del modello →