Qwen3.5 4B

Qwen3.5 4B is a low-cost multimodal reasoning model with 256K context, image and video input, function tools, and structured output.

JSON Embed chart Compare

Context

262,144

Max output

65,536

Input / 1M

$0.04

Output / 1M

$0.07

Providers

01 Profile 02 Capabilities 03 Pricing 04 History 06 Related

01Profile

Profile

Released

2026-03-02

Last updated

2026-03-03

Knowledge cutoff

—

Weights

Open

02Capabilities

Capabilities

Input

text · image · video

Output

text

Reasoning

Yes

Tool calling

Yes

Structured output

Yes

Attachments

Yes

Cache read

—

Cache write

—

03Pricing

Pricing across 1 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

Provider	Provider model id	Input	Output	Cache read	Context
empiriolabs	qwen3-5-4b	$0.04	$0.07	$0.02	262,144
qvac	qwen3.5-4b	Not listed	Not listed	Not listed	32,768
siliconflow-cn	Qwen/Qwen3.5-4B	Not listed	Not listed	Not listed	262,144

04History

Change history

5+ recent events since 2026-03-02

2026-09-16Removednano-gptofferingremoved→ new

2026-08-16Addednano-gptoffering→ new

2026-07-30Addedqvacoffering→ new

2026-06-21Addedempiriolabsoffering→ new

2026-03-08Addedsiliconflow-cnoffering→ new

Qwen3.5 4B

Profile

Capabilities

Pricing across 1 providers

Change history

Same family & alternatives