Models/Qwen/Qwen3 235B A22B

Qwen3 235B A22B

Name: Qwen3 235B A22B API access
Brand: Qwen

Qwen · Open weights · Released Apr 28, 2025 · qwen/qwen3-235b-a22b

Best $0.455 in / $1.82 out via Alibaba

Compare Estimate cost

131K contextToolsReasoningStructured outputOpen weights

Available from 1 providerUSD / MTOK · PRICES 23 MINUTES AGO · SPEED 4 MINUTES AGO

EST. MONTHLY COSTclick a row for detail · click headers to sort

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Alibaba	$0.455	$1.82	—	131K	—	1.7s	47 tok/s	77.2%

TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 4 minutes ago

SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →

About

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Specifications

Context window131,072

Max output8,192

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedApr 28, 2025

Knowledge cutoff2025-03-31

TokenizerQwen3

WeightsHugging Face ↗

Open weights

Hugging FaceQwen/Qwen3-235B-A22B ↗

Downloads526.1K

Likes1.1K

Licenseapache-2.0

safetensors

Qwen3.8 Max Prime$4.00 / $12.00 Qwen3.8 Omni Flash$0.15 / $0.47 Qwen3.8 Max (0902)$2.00 / $6.00 Qwen3.8 Flash$0.15 / $0.47

Embed badge

[![Qwen3 235B A22B](https://modelindex.ai/badge/qwen/qwen3-235b-a22b)](https://modelindex.ai/models/qwen/qwen3-235b-a22b)

Sources

OpenRouter API23 minutes ago

AGGREGATOR

Hugging Face23 minutes ago

COMMUNITY

ModelIndex benchmarks4 minutes ago

MEASURED

Verified 23 minutes ago · list prices, not negotiated rates.