Context Window
131,072
Input tokens
Full-context input ≈ $0.02
Model Cost Profile
Developer: qwen· Tokenizer: Qwen3 · Instruct: qwen3 · Quantization: unknown
Canonical ID: qwen/qwen3-235b-a22b-thinking-2507
Pricing updated Apr 25, 2026
Live Pricing
Input: $0.1495
Output: $1.50
Last synced Apr 25, 2026 · MMLU score via public benchmark data
Qwen3 235B A22B Thinking 2507, developed by qwen, offers a substantial context window of 131,072 tokens, making it suitable for complex applications such as long-form content generation and large-scale data analysis. With a pricing structure that charges $0.00 per million tokens for both input and output, this model is particularly advantageous for teams looking to scale their operations without incurring significant costs. Its unique capabilities allow for effective handling of extensive datasets, making it ideal for industries requiring deep insights from large volumes of text.
Context Window
131,072
Input tokens
Full-context input ≈ $0.02
Max Output
—
Not specified
Input Price / 1M
$0.1495
Prompt tokens
Output Price / 1M
$1.50
Completion tokens
Top Benchmark
84.3
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Qwen: Qwen3 235B A22B Thinking 2507. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.1495
Current Output / 1M
$1.50
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.1495 |
| Output (Completion) | $1.50 |
Estimate monthly spend for Qwen: Qwen3 235B A22B Thinking 2507 based on your workload.
Estimated Monthly Cost
$22
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.