Bai Qwen3 VL 235B A22B Instruct vs Qwen3.8 Max Preview

Output tokens cost $1.10 per million on Bai Qwen3 VL 235B A22B Instruct and $1.01 per million on Qwen3.8 Max Preview. Input tokens cost $0.27 per million on Bai Qwen3 VL 235B A22B Instruct and $0.34 per million on Qwen3.8 Max Preview. Cached input tokens are billed at $0.27 per million on Bai Qwen3 VL 235B A22B Instruct and $0.03 per million on Qwen3.8 Max Preview. Context lengths are 131,000 tokens on Bai Qwen3 VL 235B A22B Instruct and 983,616 tokens on Qwen3.8 Max Preview. Time to first token (TTFT) measured on AIHubMix is 1.1s on Bai Qwen3 VL 235B A22B Instruct and 2.4s on Qwen3.8 Max Preview. Measured output throughput is 41.7 tok/s on Bai Qwen3 VL 235B A22B Instruct and 48.1 tok/s on Qwen3.8 Max Preview. On the LMArena coding leaderboard Bai Qwen3 VL 235B A22B Instruct scores 1466 and Qwen3.8 Max Preview scores 1520.

Bai Qwen3 VL 235B A22B Instruct✕Qwen3.8 Max Preview✕

+ Add model · 2/4

Copy link

Bai Qwen3 VL 235B A22B Instruct

Qwen · → text

The Qwen3 series open-source models include hybrid models, thinking models, and non-thinking models, with both reasoning capabilities and general abilities reaching industry SOTA levels at the same scale.

Input$0.27 /M

Output$1.10 /M

Details

Qwen3.8 Max Preview

Qwen · text, image → text

Qwen 3.8 Max Preview(Qwen3.8-Max-Preview) is the latest-generation foundation model in the Qwen family, packing 2.4T parameters and still evolving. Compared with the previous flagship Qwen 3.7 Max, it delivers major gains in core capabilities like Coding and Cowork (professional productivity), with world-leading performance on complex, long-horizon tasks such as full-stack development, data analysis, and Office workflows. Launch offer: Credits are consumed at just 20% of the standard rate, effectively 5× your usage. Limited time only.

Input$0.34 /M

Output$1.01 /M

Details