DeepSeek V4.1 Flash (batch)

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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time.

ChatDeepSeek1M tokens$0.0545 / $0.1635 · 1M

deepseek/deepseek-v4.1-flash:batch

Context
1M tokens
Completion cap
384,000
Tools
Yes
JSON
Yes
Released
2026-09-10

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash:batch",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is DeepSeek V4.1 Flash (batch)?
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 output from a 552B-parameter backbone, an asymmetric split that keeps per-token compute low relative to the model's total size. Image understanding is native to the architecture, with visual and text embeddings trained jointly from the start of pre-training rather than added afterward as in the earlier experimental V4 Flash Vision Exp. It is suited for coding, terminal, and computer-use agents, along with long-horizon tasks that must run to completion across many steps and long-context analysis. Compressed KV caching cuts cache memory to roughly a quarter of the previous Flash generation, significantly reducing costs on agentic workloads. DeepSeek positions it as the cost-efficient tier of the V4.1 family and reports that it exceeds V4 Pro on performance, speed, and task completion time. DeepSeek V4.1 Flash (batch) runs on the Geek Hub API (OpenAI-compatible). Model id: deepseek/deepseek-v4.1-flash:batch.
Is DeepSeek V4.1 Flash (batch) free?
No. Input is $0.0545 per 1M tokens and output is $0.1635 per 1M tokens on Geek Hub (markup included).
What is the context length of DeepSeek V4.1 Flash (batch)?
DeepSeek V4.1 Flash (batch) has a 1M tokens context window. It supports up to 384,000 completion tokens.
Does DeepSeek V4.1 Flash (batch) support tool calling and structured outputs?
DeepSeek V4.1 Flash (batch) accepts tools and tool_choice for function calling. It also supports structured outputs via a JSON schema in response_format.
When was DeepSeek V4.1 Flash (batch) released?
DeepSeek V4.1 Flash (batch) was released on 2026-09-10.

More models from DeepSeek