DeepSeek: DeepSeek V4.1 Flash

deepseek41-flash

DeepSeek V4.1 Flash is an open-weight reasoning model with a 1M context window, hosted by Reka. It is served as an OpenAI-compatible passthrough with native tool calling, structured outputs, reasoning, logprobs, and streaming.

Modalities
→
In / out price
$0.30 / $1.20 per 1M
Context
1M
Max output
393,216 tokens
ChatMulti-turn conversations via /v1/chat/completions.ChatStreamingTokens arrive as they are generated with stream: true.StreamingImage inputAccepts images alongside text in the prompt.Image inputTool callingNative tool calls, including parallel calls.Tool callingReasoningThinks before answering; the trace is billed as output.ReasoningStructured outputsJSON Schema responses; JSON mode on most models.Structured outputsLogprobsReturns token log-probabilities with logprobs: true.LogprobsPrompt cachingRepeated prompt prefixes bill at the cache-read rate.Prompt caching
Loading live metrics…

Next steps