Infersia
Sign inGet an API key
ModelsPricingDocsStatusTransparency
← All models
DeepSeek logo

DeepSeek V4 Flash

deepseek/deepseek-v4-flash-0731

DeepSeek V4 Flash is a 284B mixture-of-experts model activating roughly 13B parameters per token, with a 1M context window. Compressed latent attention makes a very long prompt cost far less memory than its length suggests.

Get an API key

Endpoints

Launch offer· ends 10 August 2026

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

ProviderQuantisationContextMax outInputOutputCached in
InfersiaMXFP41024K32K$0.14$0.02$0.28$0.04$0.035$0.006

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-flash-0731
# 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-flash-0731

limits:
  max_input_tokens: 1048576      # hard limit — over this returns HTTP 413
  max_output_tokens: 32768
  timeout_seconds: 180                   # covers the full 32768 output budget at 366 tok/s, doubled for the tail
  # allow ~6s per 1,000 output tokens if you cap max_tokens lower

features:
  streaming: true
  tools: true
  vision: false
  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: 0.02
  output: 0.04
  cached_input: 0.006

What MXFP4 means

Microscaling 4-bit — the format these weights were trained to be served in.

The quantisation is returned on every request in the x-infersia-quantization response header — so you can assert on it in your own tests rather than trusting this page.

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-flash-0731",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Pin a provider with deepseek/deepseek-v4-flash-0731@infersia, or take the cheapest with the bare id. Add :free for the rate-limited free tier where one exists.