Post-Cutoff
Search For AI agents

DeepSeekDeepSeek V4 familyCurrentReasoning modelReleased 10 Sep 2026

DeepSeek-V4.1-Flash

DeepSeek’s cheapest current model: agentic coding, long-context (1M) work and image understanding at very low cost. Schedule batch jobs off-peak for 50% off.

Model iddeepseek-flash

Price$0.30 in, $1.20 out per 1M tokens

Checked17 October 2026

No published training cutoff

At least1,530events since its release on 10 September 2026

62 historic, 329 major. 64 days of news.

DeepSeek doesn’t publish a training cutoff, so we count from its release date. The real gap is larger.

Five things it has never heard of

How to call it

6 ways to use DeepSeek-V4.1-Flash, with the model id each provider expects.

Providers, model ids, endpoints and docs for DeepSeek-V4.1-Flash
ProviderModel idEndpointDocs
DeepSeek API deepseek-flash https://api.deepseek.com api-docs.deepseek.com
DeepSeek API (Anthropic format) deepseek-flash https://api.deepseek.com/anthropic api-docs.deepseek.com
Alibaba Cloud Model Studio deepseek-v4.1-flash alibabacloud.com
OpenRouter deepseek/deepseek-v4.1-flash openrouter.ai
Hugging Face huggingface.co
Web app chat.deepseek.com

Pricing

Prices for DeepSeek-V4.1-Flash
Input$0.30 per 1M tokens
Output$1.20 per 1M tokens
Cache read$0.006 per 1M tokens

As published: “per 1M tokens (USD), peak-hour list price; off-peak is half (input 0.15, output 0.6, cache hit 0.003). Peak = 01:00-04:00 and 06:00-10:00 UTC Mon-Fri”.

Source: api-docs.deepseek.com, checked 17 October 2026.

Specs

Input
Text and images
Output
Text
Context window
1,000,000 tokens
Max output
384,000 tokens
Open weights
Yes
Licence
MIT
Training cutoff
Not published
Released
10 September 2026
Status
Current
Type
Reasoning model

What stands out

What its maker marketed at launch, and what people found later, each with its source.

  • Native vision in the Flash tier

    First DeepSeek Flash model with native multimodal (image) understanding built in; replaced the separate V4-Flash-Vision-Exp.

    Source: api-docs.deepseek.com

  • Causal Encoder-Decoder (CED) architecture

    552B-backbone MoE that activates only ~8B params per token in prefill and ~16B in decode, aimed at input-heavy agentic workloads.

    Source: huggingface.co

  • Tiny KV cache (CSA2 + FP4 KV)

    Compressed Sparse Attention 2 and FP4 main KV cache cut the global KV cache to ~890 bytes/token, about 1/4 of V4-Flash.

    Source: huggingface.co

  • Hybrid thinking with effort levels

    One model id serves thinking (default) and non-thinking modes; reasoning effort low/high/max.

    Source: api-docs.deepseek.com

  • Multiple API protocols

    Same model served via OpenAI Chat Completions, OpenAI Responses (Codex-adapted) and Anthropic Messages formats.

    Source: api-docs.deepseek.com

Notes

Call as deepseek-flash (since Oct 17, 2026 it serves the DeepSeek-V4.1-Flash-1017 snapshot, same price; weights at huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017, OpenRouter id deepseek/deepseek-v4.1-flash-1017). Legacy ids deepseek-v4-flash and deepseek-v4-flash-vision-exp are routed here and billed at Flash price. Knowledge cutoff not published.

curl https://api.deepseek.com/chat/completions \
 -H "Authorization: Bearer $DEEPSEEK_API_KEY" -H "Content-Type: application/json" \
 -d '{"model":"deepseek-flash","messages":[{"role":"user","content":"Hello"}]}'

Sources: https://api-docs.deepseek.com/quick_start/pricing · https://api-docs.deepseek.com/updates · https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash