The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B. Its text capabilities significantly outperform those of Qwen3-235B-2507, and its visual capabilities surpass those of Qwen3-VL-235B.
$0.13market price $0.26
$1.04market price $2.08
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.
The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency. In terms of overall performance, this model is second only to Qwen3.5-397B-A17B.
On NagaAI, Qwen3.5-122B-A10B costs $0.13 per 1M input tokens and $1.04 per 1M output tokens. You pay only for what you use, with no subscription.
Qwen3.5-122B-A10B reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Qwen3.5-122B-A10B 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 TTFT data