Migrating from qwen3-next-80b-a3b-instruct to qwen3.7-plus

What changes when you move from qwen3-next-80b-a3b-instruct to qwen3.7-plus: input price +166.7%, output price +33.3%.

From: qwen3-next-80b-a3b-instruct
Status: Retired
Shutdown: Oct 10, 2026
Time left: —

To: qwen3.7-plus
Status: Active
Shutdown: none announced
Time left: —

Prices

USD per 1M tokens, standard tier

Type	qwen3-next-80b-a3b-instruct	qwen3.7-plus	Change
Input	$0.15first seen October 5, 2026 · source	$0.40first seen October 5, 2026 · source	+166.7%
Cached input	Not published	$0.08first seen October 5, 2026 · source	—
Output	$1.20first seen October 5, 2026 · source	$1.60first seen October 5, 2026 · source	+33.3%

At 1M input and 250K output tokens a month: $0.45 on qwen3-next-80b-a3b-instruct, $0.80 on qwen3.7-plus (+77.8%).

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens

Limit	qwen3-next-80b-a3b-instruct	qwen3.7-plus	Change
Context window	Not published	1,000,000 tokensin place when tracking began (October 6, 2026) · source	—
Max output tokens	Not published	131,072 tokensin place when tracking began (October 6, 2026) · source	—

Benchmarks

Same benchmark, source and setting on both sides

Benchmark	qwen3-next-80b-a3b-instruct	qwen3.7-plus	Change
Arena TextArena. Ranges don't overlap.	1398 ±5	1456 ±4	+58
Arena Text: CodingArena. Ranges don't overlap.	1444 ±9	1500 ±6	+56

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for qwen3-next-80b-a3b-instruct: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Not published for qwen3.7-plus: PDF input, Reasoning / thinking, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
qwen3-next-80b-a3b-instruct	Amazon Bedrock	qwen.qwen3-next-80b-a3b	not before Sep 11, 2026Active
qwen3-next-80b-a3b-instruct	Google Cloud Vertex AI	qwen3-next-80b-a3b-instruct-maas	Oct 21, 2026Deprecated	6 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

Change the model string from qwen3-next-80b-a3b-instruct to qwen3.7-plus.
Re-check costs: qwen3.7-plus costs more than qwen3-next-80b-a3b-instruct (input +166.7%, output +33.3%).

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: qwen3-next-80b-a3b-instruct, qwen3.7-plus.