Skip to content
OSMEXO
Sign inGet an API key
☰
Sign inGet an API key

DeepSeek V4.1 Flash

deepseek/deepseek-v4.1-flash
  • DeepSeek
  • Family · DeepSeek V4 Flash
  • Released 10 Sep 2026
  • Text · Image → Text
  • Reasoning · adjustable
  • Tools · JSON · Vision
Live on OSMEXO
Try nowRequest a discount
API setup & price →
Spec & list price
Context1M
Max output944K
Input / 1M$0.04
Output / 1M$0.5011.1× input
Scores · standing
Intelligence39.5#38/489
Usage
Tokens / day2.1T▼ 20% 7d
Usage rank#2
Requests / day49.9M
Tool calls / req0.37
Per request · 30 days
Avg input43.6K2.9× median
Avg output8811.3× median
Cache hit91%1.3× median
Reasoning share67%1.2× median
Tool-call failures0.9%0.5× median

Consumption

2.7T5.3T8.0T3 Oct17 Oct1 Nov
Peak 7.5T 7 OctLow 1.6T 1 NovRank today #2

News & trends

185 mentions this week ▲ 285%this model · videos, posts, articles · 30 days
Trending · 14 days
News

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis
Long-context reasoning#8 of 393
84.0%
SciCode#49 of 160
51.9%
Intelligence index#38 of 489
39.5
Humanity's Last Exam#56 of 465
39.2%
Terminal-Bench 4.0#27 of 152
26.8%
Speed · median across 37 providers, latest day
Output speed#34/334134 tok/s2.0× faster than median
Fastest provider278 tok/sbest of 37 providers
First token#830.6 s1.7× quicker than median

#3 cheapest of 18 with a similar score

Value
Intelligence Index
3035404550$0.02$0.05$0.1$0.2$0.5$1DeepSeek V4.1 Flash
Blended price per 1M tokens (log)
Family progress
Intelligence Index
20304050MayJunJulAugSepOctDeepSeek V4.1 Flash
  • Family releases45.1

Technical details

Reasoning
on · high
Tokenizer
DeepSeek
License
MIT
Moderation
none
Downloads · likes
2.1M · 4.8K
Reasoning effort
  • max
  • high · default
  • low
  • none
Request parameters 22
  • tools
  • tool_choice
  • parallel_tool_calls
  • response_format
  • structured_outputs
  • reasoning
  • reasoning_effort
  • include_reasoning
  • temperature
  • top_p
+12 more
  • top_k
  • min_p
  • max_tokens
  • stop
  • seed
  • frequency_penalty
  • logit_bias
  • logprobs
  • presence_penalty
  • repetition_penalty
  • top_a
  • top_logprobs

Interesting facts

  1. 7.3× the output room of similar models (943.7K against a 129.5K median).
  2. The most used of 4 DeepSeek V4 Flash models by tokens last month.
  3. Released 53 days ago.

When to use

Best for

  • Coding assistants with fast, low-cost responses
  • Research and summarization over very long documents
  • Image understanding in chat apps
  • Tool-calling workflows with structured output

Think twice for

  • Long autonomous agent runs (weakest suite)
  • Image generation
  • Audio input

Research papers

Same family

DeepSeek V4 Flash

Alternatives

other vendors · similar capability

Using DeepSeek V4.1 Flash at volume?

Sign in to ask for a volume discount. You will continue in the OSMEXO dashboard.

Request a discount