The Orchestrator › Models › DeepSeek

DeepSeek: DeepSeek V4.1 Flash 1017

DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. V4.1 Flash is a sparse mixture-of-experts model...

Specifications

ProviderDeepSeek
Model IDdeepseek/deepseek-v4.1-flash-1017
Context window1.0M tokens (1,048,576)
Modalitiestext + image → text
TokenizerDeepSeek
Router sourcesOpenRouter, TrustedRouter, Vercel AI Gateway, Cloudflare
Released2026-10-17
Tracked since2026-11-14
PopularityNot in the ranked set
ReasoningOn by default

Pricing (per million tokens)

VariantSourceAPI IDInputOutputContext
standardOpenRouterdeepseek/deepseek-v4.1-flash-1017$0.038$0.51.0M
batchOpenRouterdeepseek/deepseek-v4.1-flash-1017:batch$0.05$0.151.0M
standardTrustedRouterdeepseek/deepseek-v4p1-flash-1017$0.317$1.271.0M
standardVercel AI Gatewaydeepseek/deepseek-v4.1-flash-1017$0.3$1.201.0M
standardCloudflaredeepseek/deepseek-v4.1-flash-1017$0.3$1.20—

Recorded price history

DateInput / 1MOutput / 1MContext
2026-11-14$0.3$1.20—
2026-11-14$0.3$1.201.0M
2026-11-14$0.317$1.271.0M
2026-11-14$0.317$1.271M
2026-11-14$0.032$0.1271.0M
2026-11-14$0.038$0.51.0M

Capabilities

Vision (image input)Agentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)Zero data retention

Trust flags come from TrustedRouter's per-provider attestations.

Supported parameters

frequency_penalty, include_reasoning, logit_bias, logprobs, max_completion_tokens, max_tokens, min_p, parallel_tool_calls, presence_penalty, reasoning, reasoning_effort, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_logprobs, top_p