qwen logo
qwen

Qwen: Qwen3 30B A3B Instruct 2507

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. $0.04815 per million input tokens, $0.1931 per million output tokens. 262,144 token context window, maximum output of 32,000 tokens. Higher uptime with 5 providers. Includes independent benchmarks from Artificial Analysis.

Resumen

Especificaciones del modelo

Contexto
262.144 tokens
Salida máxima
32.000 tokens
Arquitectura
text->text
Tokenizador
Qwen3
Corte de conocimiento
2025-06-30
Moderado
No
OPENROUTER

Precios completos

Tarifas sincronizadas desde OpenRouter, por millón de tokens.

Entrada
$0.0481
/M tokens
Salida
$0.193
/M tokens
API

Inicio rápido

Usa este modelo mediante la API compatible con OpenAI de OpenRouter.

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"qwen/qwen3-30b-a3b-instruct-2507","messages":[{"role":"user","content":"Hello!"}]}'
Capacidades y modalidades

EntradaSalida

Entrada
text
Salida
text
API

Parámetros API compatibles

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Proveedores disponibles

5 proveedores

Proveedores en vivo en OpenRouter

Disponibilidad, latencia, rendimiento y enrutamiento cambian continuamente. Consulta la fuente para datos actuales.

OpenRouter

StreamLake

unknown
Contexto
128K
Salida máxima
32K
Entrada
$0.048
Salida
$0.193
Lectura de caché
No indicado
Escritura de caché
No indicado

SiliconFlow

fp8
Contexto
262K
Salida máxima
236K
Entrada
$0.090
Salida
$0.300
Lectura de caché
No indicado
Escritura de caché
No indicado

CoreWeave

bf16
Contexto
262K
Salida máxima
236K
Entrada
$0.100
Salida
$0.300
Lectura de caché
$0.100
Escritura de caché
No indicado

Nebius

fp8
Contexto
262K
Salida máxima
236K
Entrada
$0.100
Salida
$0.300
Lectura de caché
No indicado
Escritura de caché
No indicado

Alibaba

unknown
Contexto
131K
Salida máxima
33K
Entrada
$0.130
Salida
$0.520
Lectura de caché
No indicado
Escritura de caché
No indicado
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.

Contexto
1M
Entrada
text · image · video
Salida
text
Entrada: $0.150Salida: $0.470por millón de tokens
Ver detalles del modelo
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...

Contexto
1M
Entrada
text · image · video
Salida
text
Entrada: $0.425Salida: $2.55por millón de tokens
Ver detalles del modelo
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...

Contexto
41K
Entrada
text
Salida
rerank
Entrada: GratisSalida: Gratispor millón de tokens
Ver detalles del modelo
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...

Contexto
No indicado
Entrada
audio
Salida
transcription
Entrada: $7.50Salida: Gratispor millón de tokens
Ver detalles del modelo