DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and high-throughput workloads, while maintaining strong reasoning and coding performance. The model includes hybrid attention for efficient long-context processing. Reasoning efforts high and xhigh are supported; xhigh maps to max reasoning. It is well suited for applications such as coding assistants, chat systems, and agent workflows where responsiveness and cost efficiency are important.
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| frequency_penalty | Some providers | - |
| include_reasoning | All providers | - |
| logit_bias | Some providers | - |
| logprobs | Some providers | - |
| max_tokens | All providers | - |
| min_p | Some providers | - |
| parallel_tool_calls | Some providers | - |
| presence_penalty | Some providers | - |
| reasoning | All providers | - |
| reasoning_effort | All providers | - |
| repetition_penalty | Some providers | - |
| response_format | Some providers | - |
| seed | Some providers | - |
| stop | Some providers | - |
| structured_outputs | Some providers | - |
| temperature | All providers | - |
| tool_choice | Some providers | - |
| tools | Some providers | - |
| top_a | Some providers | - |
| top_k | Some providers | - |
| top_logprobs | Some providers | - |
| top_p | All providers | - |