AI TOOLS RADAR
Explorer
Tous les modèles / QWEN
qwen logo
qwen

Qwen: Qwen3.8 2.4T A95B

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out of 2.4 trillion total. It is...

Voir la source sur OpenRouter Hugging Face
Présentation

Caractéristiques du modèle

Context
1 048 576 tokens
Sortie maximale
262 144 tokens
Architecture
text->text
Tokenizer
Qwen
Limite des connaissances
Not provided
Modéré
Non
Capacités et modalités

Input → Output

Input
text
Output
text
Raisonnement

Oui · xhigh · medium · low

API

Paramètres API pris en charge

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Fournisseurs disponibles

7 fournisseurs

DeepInfra

fp4
Context
262K
Sortie maximale
131K
Input
$2.00
Output
$6.00
Lecture du cache
$0.200
Écriture du cache
Not provided

Modal

unknown
Context
1M
Sortie maximale
262K
Input
$2.00
Output
$6.00
Lecture du cache
$0.250
Écriture du cache
Not provided

Novita

unknown
Context
1M
Sortie maximale
131K
Input
$2.00
Output
$6.00
Lecture du cache
$0.250
Écriture du cache
Not provided

SiliconFlow

fp8
Context
1.0M
Sortie maximale
131K
Input
$2.00
Output
$6.00
Lecture du cache
$0.250
Écriture du cache
Not provided

Alibaba

unknown
Context
1M
Sortie maximale
131K
Input
$2.00
Output
$6.00
Lecture du cache
$0.250
Écriture du cache
$2.50

Together

unknown
Context
1.0M
Sortie maximale
909K
Input
$2.50
Output
$6.25
Lecture du cache
$0.500
Écriture du cache
Not provided

Venice

unknown
Context
262K
Sortie maximale
66K
Input
$2.50
Output
$7.50
Lecture du cache
$0.313
Écriture du cache
Not provided
qwen

models

Tous les modèles
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.

Context
1M
Input
text · image · video
Output
text
Input: $0.150Output: $0.470per 1M tokens
Voir la fiche du modèle →
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...

Context
1M
Input
text · image · video
Output
text
Input: $0.425Output: $2.55per 1M tokens
Voir la fiche du modèle →
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...

Context
41K
Input
text
Output
rerank
Input: FreeOutput: Freeper 1M tokens
Voir la fiche du modèle →
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...

Context
Not provided
Input
audio
Output
transcription
Input: $7.50Output: Freeper 1M tokens
Voir la fiche du modèle →