The Orchestrator › Models › DeepSeek
DeepSeek: DeepSeek V4.1 Flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Specifications
| Provider | DeepSeek |
| Model ID | deepseek/deepseek-v4.1-flash |
| Context window | 1.0M tokens (1,048,576) |
| Modalities | text + image → text |
| Tokenizer | DeepSeek |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-09-10 |
| Tracked since | 2026-11-14 |
| Popularity | #2 by usage · peak 64.7% spend share in an OpenRouter category |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | deepseek/deepseek-v4.1-flash | $0.051 | $0.203 | 1.0M |
| batch | OpenRouter | deepseek/deepseek-v4.1-flash:batch | $0.112 | $0.336 | 1.0M |
| standard | TrustedRouter | deepseek/deepseek-v4p1-flash | $0.317 | $1.27 | 1.0M |
| standard | Vercel AI Gateway | deepseek/deepseek-v4.1-flash | $0.3 | $1.20 | 1.0M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.3 | $1.20 | 1.0M |
| 2026-11-14 | $0.317 | $1.27 | 1.0M |
| 2026-11-14 | $0.317 | $1.27 | 1M |
| 2026-11-14 | $0.011 | $0.127 | 1.0M |
| 2026-11-14 | $0.051 | $0.203 | 1.0M |
Capabilities
Vision (image input)Agentic tool useStructured outputsReasoning mode1M+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logit_bias, logprobs, 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_a, top_k, top_logprobs, top_p