Qwen: Qwen3.7 Flash
Released Jul 27, 2026text+image+video→text
Set alertTry it on:
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...
Best overall rank
-
Across all subsets · overall
Total arena votes
0
Across 0 (subset, category) entries
Providers on OR
0
None yet
First seen
-
Awaiting first snapshot
Trend
No snapshot history yet - trends appear after the first daily refresh.
Pricing
Per token
- Input (per 1M)
- $0.030
- Output (per 1M)
- $0.130
- Cache Read (per 1M)
- $0.0060
- Cache Write (per 1M)
- $0.038
Capabilities
Modality
text+image+video->textContext
1M tokens
Tokenizer
Qwen
Max output
66K tokens
Moderation
Unmoderated
Supported parameters
include_reasoning
logprobs
max_tokens
presence_penalty
reasoning
response_format
seed
temperature
tool_choice
tools
top_logprobs
top_p
Providers
No provider endpoint data yet.
Per-category ranks
No leaderboard entries for this model.