DeepSeek V4 Flash (Reasoning, Max Effort)

by DeepSeek | Rank #45 of 570 | Proprietary

INTELLIGENCE
40.3
Input Price
$0.14
per 1M tokens
Output Price
$0.28
per 1M tokens
Speed
102.4 tok/s
output tokens/sec
Latency (TTFT)
0.87s
time to first token

Benchmark Scores

Intelligence Index40.3
Coding Index56.2
GPQA Diamond89.4%

Estimate Your Costs

See how DeepSeek V4 Flash (Reasoning, Max Effort) compares on price for your specific workload with our interactive calculator.

Open Cost Calculator

Similar Models

MiniMax-M3
MiniMax
44.4$0.30
GPT-5.3 Codex (xhigh)
OpenAI
44.3$1.75
DeepSeek V4 Pro (Reasoning, Max Effort)
DeepSeek
44.3$0.43
Kimi K2.6
Kimi
44.2$0.95
Claude Opus 4.6 (Adaptive Reasoning, Max Effort)
Anthropic
43.7$5.00
GPT-5.5 (low)
OpenAI
43.5$5.00

Related

Full LeaderboardCost CalculatorWhat are Tokens?LLM API PricingMethodology

Benchmark and pricing data provided by Artificial Analysis. Updated hourly. Last checked: 2026-07-10