Skip to content
AnyRouter

DeepSeek V4.1 Flash

Tools
deepseek/deepseek-v4.1-flash

1M context · Sep 2026 · 17 upstreams

DeepSeek V4.1 Flash is the cost-efficient sparse MoE tier of the V4.1 family, built on the Causal Encoder-Decoder (CED) architecture: 552B total parameters with 8B active on input and 16B on output. Native vision in, text out, 1M context. Compressed KV cache needs roughly a quarter of the previous Flash's HBM. This is the original September 2026 checkpoint, listed by OpenRouter as `deepseek/deepseek-v4.1-flash`. The official API id `deepseek-flash` now serves the October 17 snapshot, which has its own listing `deepseek/deepseek-v4.1-flash-1017`.

Bring your own keyAnyRouter has no platform route for DeepSeek V4.1 Flash. Requests use your key and bill your provider account. AnyRouter adds no fee.
context
1M
input / 1M (list)
$0.04
output / 1M (list)
$0.14
routes
17
speed, 24h
—

Upstreams

17
  1. 1NVIDIAYour key · not addedyour planTPS —TTFT ——
  2. 2OpenRouterYour key · not addedyour planTPS —TTFT ——
  3. 3Ollama CloudYour key · not addedyour planTPS —TTFT ——
  4. 4AIHubMixYour key · not addedyour planTPS —TTFT ——
  5. 5DeepInfraYour key · not addedyour planTPS —TTFT ——
  6. 6Ramp RouterYour key · not addedyour planTPS —TTFT ——
  7. 7Vercel AI GatewayYour key · not addedyour planTPS —TTFT ——
  8. 8NovitaAIYour key · not addedyour planTPS —TTFT ——
  9. 9SiliconFlowYour key · not addedyour planTPS —TTFT ——
  10. 10GMICloudYour key · not addedyour planTPS —TTFT ——
  11. 11Hugging FaceYour key · not addedyour planTPS —TTFT ——
  12. 12Venice AIYour key · not addedyour planTPS —TTFT ——
  13. 13Nous ResearchYour key · not addedyour planTPS —TTFT ——
  14. 14BasetenYour key · not addedyour planTPS —TTFT ——
  15. 15FireworksYour key · not addedyour planTPS —TTFT ——
  16. 16WaferYour key · not addedyour planTPS —TTFT ——
  17. 17OneTokenYour key · not addedyour planTPS —TTFT ——
  • Up
  • No traffic
  • Down

Try it

Send a prompt

Details

Owner
DeepSeek
Kind
Vision
Released
Sep 2026
Context
1M
Data policy
Provider retention
Endpoint
/api/v1/chat/completions

Quick start

curl https://anyrouter.dev/api/v1/chat/completions \
  -H "Authorization: Bearer $ANYROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Say hi in 3 words."
    }
  ]
}'