qwentext + image + video → text
Qwen: Qwen3.7 Flash
Canonical ID: qwen/qwen3.7-flash
Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...
Artificial Analysis Benchmarks
VerifiedNo standardized Artificial Analysis benchmark scores recorded for this variant yet.
Token Pricing & Economics
Prompt Input (1M Tokens)
Input$0.03
Completion Output (1M Tokens)
Output$0.13
Prompt KV-Cache Read (1M Tokens)
Cached$0.01
Context Window Capacity
Context976.563k tokens
Supported Parameters & Features
include_reasoninglogprobsmax_tokenspresence_penaltyreasoningresponse_formatseedtemperaturetool_choicetoolstop_logprobstop_p