DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash

DeepSeek V4.1 Flash is a sparse mixture-of-experts model and the first built on DeepSeek's Causal Encoder-Decoder architecture, activating 8B parameters on input and 16B on output. It accepts text and images, holds a 1,048,576-token context, and supports tool calling, structured output and reasoning control. The asymmetric activation makes it unusually cheap on long inputs, which suits whole-repository code work, long document synthesis and agent runs that accumulate a large history.

Get an API key

Endpoints

Each row is one provider serving these weights at one precision. Prices are per million tokens.

Quantisation	Context	Max out	Input	Output	Cached in
Undisclosed	1024K	375K	$0.35	$1.25	$0.007

Prefix caching is enabled and the discount is passed through. If your agent replays the same system prompt each iteration, the repeated portion bills at the cached rate.

Agent config

Paste this into your coding agent and it can configure itself. The timeout is derived from this variant's measured throughput, not a guess — a long generation that outlives a client's default ceiling is the most common way a working request looks broken.

# Infersia — deepseek/deepseek-v4.1-flash
# Paste this to your agent. Values are measured, not aspirational.

provider:
  type: openai-compatible
  base_url: https://api.infersia.com/v1
  api_key: ${INFERSIA_API_KEY}   # from https://infersia.com/dashboard/keys
  model: deepseek/deepseek-v4.1-flash

limits:
  max_input_tokens: 1048576      # hard limit — over this returns HTTP 413
  max_output_tokens: 384000
  timeout_seconds: 600                  # no throughput measured yet; 600 is a safe default

features:
  streaming: true
  tools: true
  vision: true
  reasoning: true   # OFF by default; send chat_template_kwargs.enable_thinking=true to opt in
  prompt_caching: true   # automatic; reuse a stable prefix and it bills at the cache rate

pricing_usd_per_million_tokens:
  input: 0.35
  output: 1.25
  cached_input: 0.007

What Undisclosed means

This model is served on capacity we buy rather than hardware we operate, so we cannot verify the precision it is served at. We would rather say that than print a figure we are guessing at.

Call it

curlbash

curl https://api.infersia.com/v1/chat/completions \
  -H "Authorization: Bearer $INFERSIA_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v4.1-flash",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Pin a provider with deepseek/deepseek-v4.1-flash@infersia, or take the cheapest with the bare id. Add :free for the rate-limited free tier where one exists.