Qwen3.5-397B-A17B is a native vision-language model in the Qwen3.5 series. Its hybrid architecture combines a linear attention mechanism with a sparse mixture-of-experts approach for better inference efficiency. It performs comparably to leading models across language understanding, logical reasoning, code generation, agent tasks, image and video understanding, and GUI interaction. Its code generation and agent abilities generalize well across a wide variety of agents.
$0.195market price $0.39
$0.055market price $0.11
$1.17market price $2.34
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.
Qwen3.5-397B-A17B is a native vision-language model in the Qwen3.5 series. Its hybrid architecture combines a linear attention mechanism with a sparse mixture-of-experts approach for better inference efficiency.
On NagaAI, Qwen3.5 397B A17B costs $0.195 per 1M input tokens and $1.17 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3.5 397B A17B reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3.5 397B A17B 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 MaxQwenNot enough throughput data
Not enough TTFT data