Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: qwen· Tokenizer: Qwen3 · Quantization: fp8
Canonical ID: qwen/qwen3-30b-a3b-thinking-2507
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.0800
Output: $0.4000
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Qwen3 30B A3B Thinking 2507, developed by qwen, offers a substantial context window of 32,768 tokens, making it suitable for complex tasks such as long-form content generation and detailed data analysis. With an input price of $0.05 per million tokens and an output price of $0.34 per million tokens, teams can effectively manage costs while leveraging its capabilities for applications in customer support automation and advanced natural language processing. This model's extensive context size allows for improved understanding of nuanced queries, enhancing user experience in interactive AI solutions.
Context Window
131,072
Input tokens
Full-context input ≈ $0.01
Max Output
131,072
Completion tokens
Input Price / 1M
$0.0800
Prompt tokens
Output Price / 1M
$0.4000
Completion tokens
Top Benchmark
80.5
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Qwen: Qwen3 30B A3B Thinking 2507. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.0800
Current Output / 1M
$0.4000
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
100.0%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0800 |
| Output (Completion) | $0.4000 |
| Cache Read | $0.0800 |
Estimate monthly spend for Qwen: Qwen3 30B A3B Thinking 2507 based on your workload.
Estimated Monthly Cost
$6.80
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.