Skip to content
NINJA

Qwen3 235B A22B Instruct 2507

Released by Qwen on 21 Jul 2025.

API id qwen/qwen3-235b-a22b-2507

Input price
$0.14 / 1M tokens
Output price
$0.80 / 1M tokens
Context window
262K tokens
Longest reply
118K tokens

About this model

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pass. It is optimized for general-purpose text generation, including instruction following,...

Description from the model’s public catalogue listing.

Capabilities

Reads
Text
Writes
Text
Reasoning mode
No
Tool calling
Yes
Open weights
Yes
Cached input
$0.05 / 1M tokens

What it would cost

At list price, without caching or batch discounts.

1,000 chat replies2K tokens in, 500 out each
$0.68
Summarise 100 long reports50K tokens in, 1K out each
$0.78
A coding agent’s working day20M tokens in, 1M out
$3.60
Price your own workload on every model

Price history

Per 1M tokens, input then output. Tracked since 30 Sept 2026.

5 Nov 2026
$0.09 → $0.14+56%$0.55 → $0.80+45%
5 Nov 2026
$0.14 → $0.09-36%$0.80 → $0.55-31%
4 Nov 2026
$0.09 → $0.14+56%$0.55 → $0.80+45%
4 Nov 2026
$0.14 → $0.09-36%$0.80 → $0.55-31%
4 Nov 2026
$0.09 → $0.14+56%$0.55 → $0.80+45%
4 Nov 2026
$0.14 → $0.09-36%$0.80 → $0.55-31%
3 Nov 2026
$0.09 → $0.14+56%$0.55 → $0.80+45%
3 Nov 2026
$0.14 → $0.09-36%$0.80 → $0.55-31%
3 Nov 2026
$0.09 → $0.14+56%$0.55 → $0.80+45%
6 Oct 2026
$0.087 → $0.09+3%$0.35 → $0.55+57%

Alternatives at a similar price

From other labs, priced within about 40% of Qwen3 235B A22B Instruct 2507, with a comparable context window.

More from Qwen

See all