Qwen3-30B-A3B is a Mixture-of-Experts (MoE) model in the Qwen3 series, with 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and support for up to 131K token contexts with YaRN. Qwen3 features both dense and MoE architectures for reasoning, multilingual support, and advanced agent tasks, and can switch between a thinking mode for complex reasoning and a non-thinking mode for efficient dialogue. It significantly outperforms prior models like QwQ and Qwen2.5 in mathematics, coding, commonsense reasoning, creative writing, and interactive dialogue.
$0.06market price $0.12
$0.25market price $0.50
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Qwen3-30B-A3B is a Mixture-of-Experts (MoE) model in the Qwen3 series, with 30.5 billion parameters (3.3 billion activated), 48 layers, 128 experts (8 activated per task), and support for up to 131K token contexts with YaRN.
On NagaAI, Qwen3 30B A3B costs $0.06 per 1M input tokens and $0.25 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3 30B A3B reads up to 41.0k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3 30B A3B can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Qwen3.8 Max PrimeQwenQwen3.8 Omni FlashQwenQwen3.8 FlashQwenQwen3.8 27BQwenQwen3.8 2.4T A95BQwenQwen3.8 MaxQwenNot enough throughput data
Not enough TTFT data