Qwen language model

Qwen3.7 Flash

retired 17 September 2026

live models in this family: Qwen3.8 Omni Flash, Qwen3.7 Plus, Qwen3.5 397B, Qwen4 Max, Qwen3.8 Max.

Qwen3.7 Flash was the lowest-cost tier of Alibaba's Qwen3.7 line, below Qwen3.7 Plus and Max: a vision-language model taking text, image and video input. Alibaba positioned it as an upgrade on Qwen3.6 Flash for multimodal and agent work.

01

historical price

$0.03/M

input tokens

$0.13/M

output tokens

$0.006/M

cached input

historical listed price per 1M tokens.

  • Alibaba tiers the rate by prompt length (breaks at 32K and 256K tokens); the listed price is the lowest tier.

02

specs

provider
Qwen
context window
1M tokens — ≈ 1,500 pages of prose or 100,000 lines of code
max output
131k tokens
input
text, images, video
output
text
structured output
yes — JSON schema
reasoning mode
yes
prompt caching
yes — cache hits at $0.006/M
weights
closed
released
July 2026
status
retired 17 September 2026
model id
qwen3.7-flash

03

what it was for

pick it if

  • you wanted the cheapest Qwen3.7 tier for high-volume work
  • you needed a 1M-token window with image and video input
  • your prompts repeated, since cache hits billed at a fraction of input

04

compare Qwen3.7 Flash

all model comparisons →

05

similar models

nearest live models by listed input price.

view all models →

06

Qwen3.7 Flash faq

how much does Qwen3.7 Flash cost?

Qwen3.7 Flash listed at $0.03/M input, $0.13/M output, $0.006/M cached input per 1M tokens before it retired on 17 September 2026.

what is the context window of Qwen3.7 Flash?

1M tokens, ≈ 1,500 pages of prose or 100,000 lines of code. a single reply can run to 131k tokens.

does Qwen3.7 Flash accept images?

yes. it takes text, images and video as input and returns text.

is Qwen3.7 Flash open source?

no. Qwen3.7 Flash is a closed-weights model, available only through Qwen's api and hosted gateways such as octohub.

when was Qwen3.7 Flash released?

July 2026, by Qwen.

is Qwen3.7 Flash still available?

no. it retired on 17 September 2026. current models in the family: Qwen3.8 Omni Flash, Qwen3.7 Plus, Qwen3.5 397B, Qwen4 Max and Qwen3.8 Max.

use Qwen3.7 Flash in octomind

explore the live models in this family above to choose a current replacement.