DeepSeek V4 Flash

DeepSeek
Tool useReasoningPrompt cachingStructured output
Context
1M
Max output
384K
Serving providers
0
Cheapest input
n/a /1M

Benchmarks

independent evaluations · source: Artificial Analysis and Hugging Face leaderboards
Speed & latency
Output speed
111 t/s
tokens / second
Time to first token
3.47s
latency
Headline indices
56.2
of 100
31.1
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
AA-Briefcase16%
CritPt7%default
EvalComputeProxy4874.7default
GDPval1188.5default
GPQA Diamond89%default
Humanity's Last Exam32%default
IFBench79%default
IT-Bench SRE32%default
Long-Context Reasoning63%default
Omniscience-22.3high
SciCode45%default
SWE-bench Verified79%default
TerminalBench Hard39%high
TerminalBench v2.162%default
τ-bench Banking23%default
τ²-bench96%high

Pricing by serving provider

availability
No public price yet. Not offered on-demand at any tracked provider.

Price history

input + output $/1M since we started tracking
Input Output
Input down 29% since first tracked
$0.000$0.100$0.200$0.300Jun 10Jun 12Jun 16Jun 17Jun 18$0.200$0.100

Frequently asked questions

DeepSeek V4 Flash pricing, context and availability

What is the context window of DeepSeek V4 Flash?

DeepSeek V4 Flash accepts up to 1M tokens of context and can return up to 384K output tokens.

What can DeepSeek V4 Flash do?

DeepSeek V4 Flash supports tool use, reasoning, prompt caching and structured output.

Other DeepSeek models

compare pricing across the DeepSeek lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI