Qwen/Qwen3.5-35B-A3B

Qwen/Qwen3.5-35B-A3B is a efficient-tier language model from Deep Infra with 35B parameters. Qwen/Qwen3.5-35B-A3B is an open-weights model, meaning the weights are publicly available for self-hosting, fine-tuning, and deployment on your own infrastructure — not just through Deep Infra's API. Qwen is Alibaba's open-weights model family, with strong multilingual performance (especially Chinese/English) and a wide parameter range from 0.5B to 72B.

Qwen/Qwen3.5-35B-A3B is priced at $0.14/1M input tokens and $1/1M output tokens. Output tokens are 7.1× more expensive than input tokens — this ratio reflects the sequential nature of autoregressive generation, which requires a separate forward pass per output token versus parallel processing of all input tokens simultaneously. At a typical usage pattern of 1,000 input tokens and 500 output tokens per call, Qwen/Qwen3.5-35B-A3B costs approximately $0.64 per 1,000 API calls. Prompt caching reduces repeated input tokens to $0.05/1M — a 64% discount that compounds significantly for applications with long shared system prompts, multi-turn conversations, or document Q&A where the same context is reused across many queries.

Its 262K-token context window is in the top tier for production models, enabling full-document analysis, long multi-turn conversations, and large codebase understanding without chunking.

Qwen/Qwen3.5-35B-A3B is best suited to cost, coding, chat. Supported capabilities include function calling / tool use for agentic workflows, streaming token output for real-time UIs. Function calling support makes it suitable for building AI agents, structured data extraction pipelines, and any workflow requiring the model to invoke external APIs or return typed JSON. When evaluating this model for a specific workload, the most important factors are: context window (does your input fit?), output price (how long are your generations?), and latency (is this interactive or batch?). The pricing table above shows how Qwen/Qwen3.5-35B-A3B compares to similar models across these dimensions.

Qwen/Qwen3.5-35B-A3B sits in the efficient tier — optimized for speed and cost while maintaining solid quality, ideal for high-volume or latency-sensitive workloads. As an open-weights model, Qwen/Qwen3.5-35B-A3B can be self-hosted on GPU compute (see the GPU rental comparison on this site) to eliminate per-token API costs entirely — the break-even point versus API pricing depends on your volume and the GPU hourly rate. When comparing Qwen/Qwen3.5-35B-A3B to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (78/100) reflects aggregate benchmark performance — a useful proxy for general capability, though real-world performance varies significantly by task type. Always test with your specific prompts and use case before committing to a model for production.