qwen3-235b-a22b-fp8

qwen3-235b-a22b-fp8 is a efficient-tier language model from Alibaba Cloud with 235B parameters. qwen3-235b-a22b-fp8 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 Alibaba Cloud'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.

qwen3-235b-a22b-fp8 is priced at $0.2/1M input tokens and $0.8/1M output tokens. Output tokens are 4× 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, qwen3-235b-a22b-fp8 costs approximately $0.60 per 1,000 API calls. Alibaba Cloud does not publish a prompt caching rate for this model, so repeated long contexts are billed at the standard $0.2/1M input rate.

Its 41K-token context window is sufficient for most production use cases, handling documents up to ~25,000 words or multi-turn conversations spanning dozens of exchanges. Median latency (P50 time-to-first-token) is approximately 500ms — suitable for interactive applications where sub-second response is acceptable. Throughput is approximately 130 tokens/second — adequate for streaming at comfortable reading speed. Maximum output length is 8K tokens — adequate for most generation tasks including essays, code functions, and detailed responses.

qwen3-235b-a22b-fp8 is best suited to cost, coding. 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 qwen3-235b-a22b-fp8 compares to similar models across these dimensions.

qwen3-235b-a22b-fp8 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, qwen3-235b-a22b-fp8 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 qwen3-235b-a22b-fp8 to alternatives, use the similar models section on this page to find models at comparable price points with different capability tradeoffs. The intelligence score (82/100) 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.