Tryingopen API

DeepSeek V4.1 Flash

by DeepSeek · 763B parameters

deepseek/deepseek-v4.1-flash

DeepSeek's newest quick model, and the first on a new design of theirs. It wakes only a small part of itself for each word, so it stays fast and cheap, and it reads pictures as well as text. Through the API it takes text only.

Credits are charged at these prices whoever answers: the highest price any route lists for this model, including OpenRouter endpoints not shown below.

Providers

With no provider, requests go to OpenRouter, with zero retention. Name one below to pin it; any provider preference goes through OpenRouter with zero retention.

Provider	Input / 1M	Output / 1M	Context	Zero retention	Slug to pin
OpenRouter (default)	Not listed		1M	Yes	None: send no provider
CoreWeave	20	65	1M	Yes	coreweave
DeepInfra	14	42	1M	Yes	deepinfra
Relace	13	52	1M	Yes	relace
Morph	13.5	54	1M	Yes	morph
Sail Research	20	60	1M	Yes	sail-research
Wafer	20	60	1M	Yes	wafer
Fireworks	22	66	1M	Yes	fireworks
Novita	28.5	114	1M	Yes	novita
Baseten	30	120	1M	Yes	baseten
DigitalOcean	30	120	1M	Yes	digitalocean
MaMakora	30	120	1M	Yes	makora
Modal	30	120	1M	Yes	modal
Parasail	30	120	1M	Yes	parasail
SiliconFlow	30	120	1M	Yes	siliconflow
Together	30	120	1M	Yes	together
Phala	34.5	138	1M	Yes	phala
Venice	37.5	150	1M	Yes	venice

Provider prices are their list prices, in credits, for comparison.

Code

curl https://www.tryingopen.com/v1/chat/completions \
  -H "Authorization: Bearer your-name" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v4.1-flash","max_tokens":1000,"messages":[{"role":"user","content":"Hello!"}]}'

Try it

The API isn't set up on this deployment yet.