Context Window
160,000
Input tokens
Full-context input ≈ $0.01
Model Cost Profile
Developer: qwen· Tokenizer: Qwen3 · Quantization: fp8
Canonical ID: qwen/qwen3-coder-30b-a3b-instruct
Pricing updated Apr 24, 2026
Live Pricing
Input: $0.0700
Output: $0.2700
Last synced Apr 24, 2026 · MMLU score via public benchmark data
Qwen3 Coder 30B A3B Instruct is designed for advanced coding tasks, making it ideal for software development teams that require high-context understanding and detailed code generation. With a context window of 160,000 tokens, this model can handle extensive codebases and complex queries, enhancing productivity in large-scale projects. The pricing structure, at $0.07 per million tokens for input and $0.27 for output, allows teams to manage costs effectively while leveraging the model's capabilities for extensive coding applications.
Context Window
160,000
Input tokens
Full-context input ≈ $0.01
Max Output
32,768
Completion tokens
Input Price / 1M
$0.0700
Prompt tokens
Output Price / 1M
$0.2700
Completion tokens
Top Benchmark
70.6
MMLU score — highest of MMLU, GPQA, MATH, HumanEval
Evaluation scores for Qwen: Qwen3 Coder 30B A3B Instruct. The “Top Benchmark” shown above is the highest score across MMLU, GPQA, MATH & HumanEval.
Price History
Current Input / 1M
$0.0700
Current Output / 1M
$0.2700
Performance History
Current TPS
0.00
Current Latency
0ms
Uptime
99.9%
| Usage Type | Price / 1M Tokens |
|---|---|
| Input (Prompt) | $0.0700 |
| Output (Completion) | $0.2700 |
Estimate monthly spend for Qwen: Qwen3 Coder 30B A3B Instruct based on your workload.
Estimated Monthly Cost
$4.99
25M input + 12M output tokens
Quick links for cost-down decisions before production rollout.