How much does Qwen: Qwen3.5 397B A17B cost per 1M tokens?

Qwen: Qwen3.5 397B A17B costs $0.600 per 1M input tokens and $3.60 per 1M output tokens on the standard tier. Cached input is $0.120 per 1M.

What is Qwen: Qwen3.5 397B A17B's context window?

Qwen: Qwen3.5 397B A17B accepts up to 262,144 tokens in a single request, and can return up to 64,000 output tokens.

Is there a cheaper OpenRouter model than Qwen: Qwen3.5 397B A17B?

Yes. Free Models Router is free per 1M input tokens versus $0.600 for Qwen: Qwen3.5 397B A17B, with a 200,000 token context window.

Where does this Qwen: Qwen3.5 397B A17B price come from?

From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

Qwen: Qwen3.5 397B A17B pricing

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. Qwen: Qwen3.5 397B A17B from OpenRouter costs $0.600 per 1M input tokens and $3.60 per 1M output tokens. Cached input is $0.120 per 1M. Context window 262,144 tokens.

API id qwen/qwen3.5-397b-a17b · OpenRouter · source · updated 2026-11-10 · general-purpose

$0.600

Input / 1M tokens

$3.60

Output / 1M tokens

$0.120

Cached input / 1M

262K

Context window

Qwen: Qwen3.5 397B A17B specifications

Provider: OpenRouter
API id: qwen/qwen3.5-397b-a17b
Model type: general-purpose
Context window: 262K tokens
Max output: 64K tokens
Currency: USD
Price source: Provider API
Last checked: 2026-11-10

Qwen3.5 397B A17B across providers

The same model, priced by every seller we track. Ranked by the cost of 1M input + 1M output tokens, standard tier; savings measured against buying from the vendor directly.

Provider	Input /1M	Cached /1M	Output /1M	1M in + 1M out	vs vendor
DeepInfraHostCheapest	$0.450	$0.220	$3.00	$3.45	−18%
Alibaba (Qwen)Vendor	$0.600	$0.120	$3.60	$4.20	—
OpenRouterHostviewing	$0.600	$0.120	$3.60	$4.20	—

What Qwen: Qwen3.5 397B A17B costs in practice

Estimated cost at common usage volumes
Workload	Input tokens	Output tokens	Estimated cost
Short chat turn	1,000	500	$0.0024
Document summary	50,000	2,000	$0.04
1M tokens in, 200K out	1,000,000	200,000	$1.32

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

Qwen: Qwen3.5 397B A17B price history

Recorded	Input /1M	Output /1M
2026-11-09	$0.600	$3.60
2026-10-22	$0.500	$3.60
2026-10-20	$0.390	$2.34
2026-10-14	$0.500	$3.60
2026-10-09	$0.550	$3.50
2026-10-06	$0.450	$3.00
2026-09-09	$0.550	$3.50
2026-09-07	$0.390	$2.34
2026-09-03	$0.550	$3.50
2026-08-27	$0.390	$2.34

Common questions

How much does Qwen: Qwen3.5 397B A17B cost per 1M tokens?: Qwen: Qwen3.5 397B A17B costs $0.600 per 1M input tokens and $3.60 per 1M output tokens on the standard tier. Cached input is $0.120 per 1M.
What is Qwen: Qwen3.5 397B A17B's context window?: Qwen: Qwen3.5 397B A17B accepts up to 262,144 tokens in a single request, and can return up to 64,000 output tokens.
Is there a cheaper OpenRouter model than Qwen: Qwen3.5 397B A17B?: Yes. Free Models Router is free per 1M input tokens versus $0.600 for Qwen: Qwen3.5 397B A17B, with a 200,000 token context window.
Where does this Qwen: Qwen3.5 397B A17B price come from?: From the OpenRouter catalogue, because OpenRouter does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from OpenRouter's own — verify before committing spend.

Head-to-head comparisons

Compare Qwen: Qwen3.5 397B A17B with another model →

Other OpenRouter models

See all OpenRouter pricing →