DeepSeek V4 Flash
$0.14/M input
$0.28/M output
$0.0028/M cached input
Lowest-cost DeepSeek cache-miss/cache-hit seed.
Model comparison
DeepSeek V4 Flash vs GPT-5.4 Nano Cost Calculator
GPT-5.4 Nano
$0.2/M input
$1.25/M output
$0.02/M cached input
Lowest-cost OpenAI text seed.
Quick estimate
No API key needed. Pick a model, paste your question, choose the answer length, and get a close cost estimate.
$0.14/M input$0.28/M output1,000,000 ctxCache pricing
3. How long will the AI answer be?
Your estimate will appear here.
Paste a prompt, choose an answer length, and calculate.
Example request costs
Short prompt
DeepSeek V4 Flash: $0.000280
GPT-5.4 Nano: $0.000825
Long coding prompt
DeepSeek V4 Flash: $0.004900
GPT-5.4 Nano: $0.0113
App build planning prompt
DeepSeek V4 Flash: $0.001960
GPT-5.4 Nano: $0.004500
Which is cheaper, DeepSeek V4 Flash or GPT-5.4 Nano?
DeepSeek V4 Flash has the lower combined input plus output seed rate for this comparison.
Why might my bill differ from this comparison?
Cache usage, tools, search, long-context tiers, region multipliers, and provider-reported token counts can change the final bill.