The Qwen3.5 Series 35B-A3B is a native vision-language model with a hybrid architecture that combines linear attention mechanisms and a sparse mixture-of-experts model for higher inference efficiency. Its overall performance is comparable to Qwen3.5-27B.
$0.0325market price $0.065
$0.0163market price $0.0325
$0.375market price $0.75
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.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
The Qwen3.5 Series 35B-A3B is a native vision-language model with a hybrid architecture that combines linear attention mechanisms and a sparse mixture-of-experts model for higher inference efficiency. Its overall performance is comparable to Qwen3.5-27B.
On NagaAI, Qwen3.5-35B-A3B costs $0.0325 per 1M input tokens and $0.375 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3.5-35B-A3B reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3.5-35B-A3B can call your functions as tools and can answer in a JSON schema you give it.
It takes text and images 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 MaxQwen