Models/Qwen/Qwen3 235B A22B Thinking 2507

Qwen3 235B A22B Thinking 2507

Name: Qwen3 235B A22B Thinking 2507 API access
Brand: Qwen

Qwen · Open weights · Released Jul 25, 2025 · qwen/qwen3-235b-a22b-thinking-2507

Compare Estimate cost

131K contextToolsReasoningStructured outputOpen weights

Available from 3 providersUSD / MTOK · VERIFIED 4 MINUTES AGO

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

PROVIDER	INPUT	OUTPUT	CACHE	CONTEXT	QUANT	TTFT	TPS	UPTIME
Alibaba	$0.23	$2.30	—	131K	—	1.7s	81 tok/s	100.0%
Novita	$0.30	$3.00	—	131K	fp8	101.9s	17 tok/s	99.5%
Venice	$0.45	$3.50	—	128K	fp8	1.4s	40 tok/s	100.0%

TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago

Recent changesRSS ↗

Aug 24, 2026context changed262144 → 131072

Aug 24, 2026endpoint removed4 → 3

About

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Specifications

Context window131,072

Max output—

Modalities intext

Modalities outtext

LicenseOpen weights

ReleasedJul 25, 2025

Knowledge cutoff2025-06-30

TokenizerQwen3

WeightsHugging Face ↗

Open weights

Hugging FaceQwen/Qwen3-235B-A22B-Thinking-2507 ↗

Downloads27.6K

Likes406

Licenseapache-2.0

safetensors

Qwen3.8 27B$0.35 / $2.55 Qwen3.8 2.4T A95B$2.00 / $6.00 Qwen3.8 Max$2.00 / $6.00 Qwen3.7 Flash$0.03 / $0.13

Embed badge

Qwen3 235B A22B Thinking 2507 price and speed badge

[![Qwen3 235B A22B Thinking 2507](https://modelindex.ai/badge/qwen/qwen3-235b-a22b-thinking-2507)](https://modelindex.ai/models/qwen/qwen3-235b-a22b-thinking-2507)

Sources

OpenRouter API4 minutes ago

AGGREGATOR

Hugging Face4 minutes ago

COMMUNITY

ModelIndex benchmarks43 hours ago

MEASURED

Verified 4 minutes ago · list prices, not negotiated rates.