Models/Qwen/Qwen3 30B A3B Thinking 2507

Qwen3 30B A3B Thinking 2507

Qwen · Open weights · Released Aug 28, 2025 · qwen/qwen3-30b-a3b-thinking-2507
CompareEstimate cost
82K contextToolsReasoningStructured outputOpen weights
Available from 1 providerUSD / MTOK · VERIFIED 4 MINUTES AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
PROVIDERINPUTOUTPUTCACHECONTEXTQUANTTTFTTPSUPTIME
TTFT/TPS: median (P50) over trailing 72h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 43 hours ago
About

Qwen3-30B-A3B-Thinking-2507 is a 30B parameter Mixture-of-Experts reasoning model optimized for complex tasks requiring extended multi-step thinking. The model is designed specifically for “thinking mode,” where internal reasoning traces are separated...

Specifications
Context window81,920
Max output32,768
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedAug 28, 2025
Knowledge cutoff2025-06-30
TokenizerQwen3
WeightsHugging Face ↗
Open weights
Hugging FaceQwen/Qwen3-30B-A3B-Thinking-2507 ↗
Downloads76.2K
Likes380
Licenseapache-2.0
safetensors
Related
Qwen3.8 27B$0.35 / $2.55Qwen3.8 2.4T A95B$2.00 / $6.00Qwen3.8 Max$2.00 / $6.00Qwen3.7 Flash$0.03 / $0.13
Embed badge
Qwen3 30B A3B Thinking 2507 price and speed badge[![Qwen3 30B A3B Thinking 2507](https://modelindex.ai/badge/qwen/qwen3-30b-a3b-thinking-2507)](https://modelindex.ai/models/qwen/qwen3-30b-a3b-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.