DeepSeek V4 Flash API Pricing Calculator
Compare what your prompts cost across every major LLM — with exact token counts for OpenAI models, right in your browser.
Prices verified 2026-07-24 · per 1M tokens · sources linked per provider
Input / 1M tokens
$0.14
Cached input / 1M
$0.0028
Output / 1M tokens
$0.28
deepseek-v4-flashAt DeepSeek V4 Flash's rates ($0.14 per 1M input tokens, $0.28 per 1M output), a call with 1,000 input and 500 output tokens costs $0.00028. At 10,000 requests a month, that workload runs $2.80. A heavier call — a 100,000-token prompt returning 2,000 tokens — costs $0.0146.
DeepSeek V4 Flash is the cheapest DeepSeek model at this workload — DeepSeek V4 Pro costs 3.1× as much per call.
Cache-read input is billed at $0.0028 per 1M tokens — 98% below the standard input rate, so a long system prompt reused across calls mostly bills at the discounted rate.
DeepSeek V4 Flash's context window is 1,000,000 tokens.
| Model | Cost / call | Cost / month | × best price |
|---|---|---|---|
| DeepSeek V4 Flashcheapest | $0.00042 | $0.42 | — |
| DeepSeek V4 Pro | $0.0013 | $1.31 | 3.1× |
More DeepSeek models: DeepSeek V4 Pro — or all DeepSeek pricing
Token counter
Token counts are exact for OpenAI models (tiktoken o200k_base, run in your browser). For other providers the count is an estimate — notably Claude Opus 4.7+/Sonnet 5 and similar newer models use a tokenizer that produces roughly 30% more tokens for the same text.
Related tools
Scaling AI content or ops? Elegant Atomics builds growth systems for B2B SaaS — Trevor’s company. Work with us →