Qwen: Qwen3 235B A22B Thinking 2507 pricing and limits

id qwen/qwen3-235b-a22b-thinking-2507 · listed 2025-07-25 · knowledge cutoff 2025-06-30

Input (per 1M tokens)	$0.450
Output (per 1M tokens)	$3.500
Context window	128,000 tokens
Max output	16,384 tokens
Modalities	text → text
Reasoning	yes

What 1,000 calls cost at 1,000 input and 300 output tokens each: $1.50.

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B parameters per forward pass and natively supports up to 262,144...

Cheaper on both input and output, with at least half the context

Model	In / 1M	Out / 1M	Context
Auto Router (Beta)	$-1000000.000	$-1000000.000	2,000,000
Pareto Code Router	$-1000000.000	$-1000000.000	2,000,000
Auto Router	$-1000000.000	$-1000000.000	2,000,000
Meta: Llama 4 Scout	$0.100	$0.300	1,310,720
OpenAI: GPT-6 Luna Pro	$0.100	$0.500	1,050,000
OpenAI: GPT-6 Luna Pro (batch)	$0.050	$0.250	1,050,000

Other qwen models

Qwen: Qwen3.7 Flash ($0.030 / $0.130) · Qwen: Qwen3.8 27B ($0.040 / $1.350) · Qwen: Qwen3.5-Flash ($0.065 / $0.260) · Qwen: Qwen3 Coder 30B A3B Instruct ($0.070 / $0.280) · Qwen: Qwen3.5-9B ($0.080 / $0.130) · Qwen: Qwen3 32B ($0.080 / $0.280) · Qwen: Qwen3 Next 80B A3B Instruct ($0.090 / $1.100) · Qwen: Qwen3 30B A3B Instruct 2507 ($0.090 / $0.300)

For software and AI agents: this sheet as JSON per call, no account: GET https://store.agentexchange.work/gw/models/model?id=qwen/qwen3-235b-a22b-thinking-2507 (0.002 USD), /gw/models/cheapest?min_context=128000, /gw/models/models?provider=qwen. Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

Prices as listed by the hosting providers through OpenRouter, refreshed hourly; a provider's own console may differ. Not affiliated with qwen. Agent Exchange