deepseek-v4.1-flash:flex
DeepInfra/🇺🇸 US/chat
DeepSeek V4.1 Flash is a 552B parameter Mixture of Experts model built on a new Causal Encoder Decoder architecture that activates only 8B parameters for input and 16B for output, giving frontier level intelligence at a fraction of the cost. It is the smallest model in the new DeepSeek architecture family and the first Flash with native vision and multimodal understanding. V4.1 Flash beats DeepSeek V4 Pro on performance, cost, speed and task completion time and scores 88.1 on CyberGym. Its KV cache is compressed to 890 bytes per token, four times smaller than V4 Flash and over 400 times smaller than V1, cutting the cache hit costs that dominate agent workloads. 1M token context window, 384K max output, thinking and non thinking modes, tool calling, structured JSON output and prompt caching. Served on DeepInfra in FP8 at $0.20 input, $0.006 cache read and $0.60 output per 1M tokens, with a flex tier at 0.8x. Open weights are published on Hugging Face. Ideal for coding agents, long context RAG, high throughput batch processing and multimodal assistants.MoreLess
Which id to call
deepinfra/deepseek-v4.1-flash:flexThis exact deployment on DeepInfra, with no routing and no failover. Send it as the model field.
Input /1M
$0.16
$0.0048 cached
Output /1M
$0.48
3.0x input
Context
1.0M
tokens
Paid /1M
$0.03
measured, cache included
Capabilities 5/8
Provider rates
What deepseek-v4.1-flash:flex costs
Provider prices per 1M tokens, updated October 29, 2026.moreless
These are the upstream provider rates. Pay as you go adds 5%, or 0% if you bring your own keys, and there is no per-request fee. Prompt caching and routing change what you pay against these rates, not the rates themselves.
Input /1M
$0.16
Output /1M
$0.48
Cache write /1M
-
Cache read /1M
$0.0048
What a workload costs
- 100K input + 10K output
- $0.0208
- 1M input + 100K output
- $0.21
- 10M input + 1M output
- $2.08
At the rates above, before caching. A cache read costs $0.0048 per 1M, so repeated context lands under these figures.
model=
Which id to call
One base url, https://router.requesty.ai/v1, and one key for every id here.
deepinfra/deepseek-v4.1-flash:flexThis exact deployment on DeepInfra, with no routing and no failover. Send it as the model field.
OpenAI compatible
Call it in three lines
Change the base url, use your Requesty key, set the model to any id on the left. Existing OpenAI SDK code needs no other edit.
123456789101112131415from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1", ) response = client.chat.completions.create( model="deepinfra/deepseek-v4.1-flash:flex", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ], ) print(response.choices[0].message.content)
Live from production
DeepInfra on deepseek-v4.1-flash:flex, measured
What this provider was measured doing on deepseek-v4.1-flash:flex across Requesty traffic.moreless
Whole-window figures, because that is the grain published per provider. They cover DeepInfra serving this model in every region it serves it from, so a region-pinned deployment shares them with its siblings. A figure is absent where no qualifying sample exists.
First token
1.53s
median
p95 wait
5.73s
slowest 5%
Output speed
59/s
median tokens
Paid /1M
$0.03
blended, cache included
Cache hit
94.1%
of input tokens
Compare these against the other 10 providers serving deepseek-v4.1-flash.
Reference
Specs and data terms
What the catalog reports for this deployment, and what the provider does with the traffic.
Public leaderboards
Benchmark scores
Benchmarks measure the model, not this endpoint, so they are the same wherever these weights are served.
No benchmarks are published for this exact variant yet.
Region-specific deployments and highspeed tiers usually share scores with their base model. Try the base model page or the DeepInfra models overview.
Same provider
More from DeepInfra
Newest first, on the same provider and the same key.
Reference
deepseek-v4.1-flash:flex questions
How much does deepseek-v4.1-flash:flex cost?
deepseek-v4.1-flash:flex is priced at $0.16 per million input tokens and $0.48 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Those are the upstream provider rates: pay as you go adds 5% on top, or 0% if you bring your own provider keys.
What is the context window of deepseek-v4.1-flash:flex?
deepseek-v4.1-flash:flex has a context window of 1.0M tokens. That's roughly 1,398 words of input you can fit in a single prompt.
What can deepseek-v4.1-flash:flex do?
deepseek-v4.1-flash:flex supports vision input, tool calling, extended reasoning, prompt caching, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use deepseek-v4.1-flash:flex with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "deepinfra/deepseek-v4.1-flash:flex". The Quickstart above shows Python, JavaScript and cURL snippets.
Can I run deepseek-v4.1-flash:flex through Requesty?
Yes. deepseek-v4.1-flash:flex runs through Requesty's OpenAI-compatible API, served from DeepInfra. You do not host the model yourself: point base_url at Requesty, set the model to "deepinfra/deepseek-v4.1-flash:flex", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.
Call deepseek-v4.1-flash:flex through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover, caching built in.