DeepSeek V4.1 Flash API pricing — what it really costs
DeepSeek V4.1 Flash (DeepSeek) costs $0.300 per 1M input tokens and $1.20 per 1M output tokens — with prompt caching, cached input drops to $0.006. Peak-hour price (01-04 and 06-10 UTC, Mon-Fri); off-peak costs half. Replaced DeepSeek V4 Flash. Prices verified 2026-10-17; we track the price you are actually billed today, including promotional rates.
Price per 1M tokens
| Input | Output | Cached input |
|---|---|---|
| $0.300 | $1.20 | $0.006 |
Real monthly costs on DeepSeek V4.1 Flash
Three realistic workloads, computed from the prices above (cached share billed at the cache-read rate where the provider offers one):
Customer-support chatbot
$0.847/mo
2M input + 0.5M output tokens/month, 60% of input served from prompt cache
RAG / document Q&A
$3.08/mo
20M input + 1M output tokens/month, 70% cached (shared context)
Agentic coding assistant
$9.24/mo
50M input + 5M output tokens/month, 80% cached (long sessions)
Want exact numbers for your usage? Open the calculator — same verified prices, your token volumes.
Compare DeepSeek V4.1 Flash
- DeepSeek V4.1 Flash vs Gemini 3.1 Flash-Lite — which is cheaper?
- DeepSeek V4.1 Flash vs Claude Haiku 5.5 — which is cheaper?
- DeepSeek V4.1 Flash vs DeepSeek V4 Pro — which is cheaper?
FAQ
How much does the DeepSeek V4.1 Flash API cost?
DeepSeek V4.1 Flash costs $0.300 per 1M input tokens and $1.20 per 1M output tokens. Cached input tokens cost $0.006 per 1M. Note: Peak-hour price (01-04 and 06-10 UTC, Mon-Fri); off-peak costs half. Replaced DeepSeek V4 Flash. Pricing verified 2026-10-17.
What does a typical workload cost on DeepSeek V4.1 Flash?
Customer-support chatbot: about $0.847/month (2M input + 0.5M output tokens/month, 60% of input served from prompt cache). RAG / document Q&A: about $3.08/month (20M input + 1M output tokens/month, 70% cached (shared context)). Agentic coding assistant: about $9.24/month (50M input + 5M output tokens/month, 80% cached (long sessions))
Is DeepSeek V4.1 Flash expensive compared to other models?
DeepSeek V4.1 Flash ranks #4 of 23 models by blended price in our comparison. The cheapest tracked models are Claude Haiku 5.5 and GPT-6 Luna at $0.100/$0.500 per 1M tokens.