Back to models
available

Qwen3.5 Flash

qwen/qwen3-5-flash

Prices

Input

$0.0282 per 1M tokens

low
Input (>128k ctx)

$0.1126 per 1M tokens

low
Input (>256k ctx)

$0.169 per 1M tokens

low
Input (cache write, >128k ctx)

$0.1408 per 1M tokens

low
Input (cache write, >256k ctx)

$0.2113 per 1M tokens

low
Input (cache write)

$0.0353 per 1M tokens

low
Input (cached read, >128k ctx)

$0.0113 per 1M tokens

low
Input (cached read, >256k ctx)

$0.0169 per 1M tokens

low
Input (cached read)

$0.00282 per 1M tokens

low
Output

$0.282 per 1M tokens

low
Output (>128k ctx)

$1.13 per 1M tokens

low
Output (>256k ctx)

$1.69 per 1M tokens

low

Also available on

The same model, sold by someone else. The price above is the maker's own.

7 sales channels for this model.
ChannelWhatPrice
Alibaba Model StudioInput$0.10 per 1M tokens
Input (cache write)$0.125 per 1M tokens
Input (cached read)$0.01 per 1M tokens
Output$0.40 per 1M tokens
Alibaba Model Studio · alibaba-cnInput$0.029 per 1M tokens
Input (>128k ctx)$0.115 per 1M tokens
Input (>256k ctx)$0.172 per 1M tokens
Output$0.287 per 1M tokens
Output (>128k ctx)$1.15 per 1M tokens
Output (>256k ctx)$1.72 per 1M tokens
Output (reasoning) (kind: reasoning)$0.287 per 1M tokens
Output (reasoning) (kind: reasoning)$1.15 per 1M tokens
Output (reasoning) (kind: reasoning)$1.72 per 1M tokens
Other · merge-gatewayInput$0.029 per 1M tokens
Input (cached read)$0.0058 per 1M tokens
Output$0.287 per 1M tokens
Other · nano-gptInput$0.10 per 1M tokens
Input (cached read)$0.05 per 1M tokens
Output$0.40 per 1M tokens
Other · ofoxInput$0.10 per 1M tokens
Input (cache write)$0.125 per 1M tokens
Input (cached read)$0.01 per 1M tokens
Output$0.40 per 1M tokens
Other · orcarouterInput$0.10 per 1M tokens
Output$0.40 per 1M tokens
Other · zenmuxInput$0.10 per 1M tokens
Output$0.40 per 1M tokens

Specifications

Provider
qwen
Context window
1,000,000
Max output tokens
65,536
Open weights
no
Released
02/23/2026
Retires
no date announced
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input
0.0282 per 1M tokens, unchanged since 09/29/2026
Output
0.282 per 1M tokens, unchanged since 09/29/2026
Input (cached read)
0.00282 per 1M tokens, unchanged since 09/29/2026
Input (cache write)
0.0353 per 1M tokens, unchanged since 09/29/2026
Input (>128k ctx)
0.1126 per 1M tokens, unchanged since 09/29/2026
Output (>128k ctx)
1.13 per 1M tokens, unchanged since 09/29/2026
Input (cached read, >128k ctx)
0.0113 per 1M tokens, unchanged since 09/29/2026
Input (cache write, >128k ctx)
0.1408 per 1M tokens, unchanged since 09/29/2026
Input (>256k ctx)
0.169 per 1M tokens, unchanged since 09/29/2026
Output (>256k ctx)
1.69 per 1M tokens, unchanged since 09/29/2026
Input (cached read, >256k ctx)
0.0169 per 1M tokens, unchanged since 09/29/2026
Input (cache write, >256k ctx)
0.2113 per 1M tokens, unchanged since 09/29/2026

Last updated 10/03/2026, 02:10