Qwen3.7 Flash
Qwen · Proprietary · Released Jul 27, 2026 · qwen/qwen3.7-flash
Best $0.03 in / $0.13 out via Alibaba
1M contextVisionToolsReasoningStructured outputPrompt caching
Available from 1 providerUSD / MTOK · PRICES 15 MINUTES AGO · SPEED 16 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.03 | $0.13 | $0.006 | 1M | — | 1.2s | 104 tok/s | 99.9% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 16 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.03 / $0.13
per MTok in / out
CACHE READ $0.006CACHE WRITE $0.038
Recent changesRSS ↗
Nov 5, 2026endpoint removed · cheaperinference3 → 2
Oct 23, 2026endpoint added · cheaperinference2 → 3
About
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...
Specifications
Context window1,000,000
Max output65,536
Modalities intext, image, video
Modalities outtext
LicenseProprietary
ReleasedJul 27, 2026
TokenizerQwen
Related
Embed badge
[](https://modelindex.ai/models/qwen/qwen3.7-flash)Sources
OpenRouter API15 minutes ago
AGGREGATORModelIndex benchmarks16 days ago
MEASUREDVerified 15 minutes ago · list prices, not negotiated rates.