~deepseek model
DeepSeek V4 Flash Latest API cost calculator
DeepSeek V4 Flash Latest costs $0.03 per 1M input tokens and $0.07 per 1M output tokens on the ~deepseek API, with a 1.3M-token context window. A typical request (2K input, 500 output tokens) costs <$0.0001 — about $2.85/month at 1,000 requests per day. Use the calculator below to model your exact workload.
Find me a cheaper modelWhat real workloads cost on DeepSeek V4 Flash Latest
| Workload | Tokens (in / out) | Per request | Per 1K requests |
|---|---|---|---|
| Chatbot message | 500 / 300 | <$0.0001 | $0.04 |
| RAG query with context | 4,000 / 500 | $0.0002 | $0.15 |
| Document summarization | 20,000 / 1,000 | $0.0007 | $0.67 |
| Agent coding session | 100,000 / 5,000 | $0.0034 | $3.35 |
Frequently asked questions
How much does DeepSeek V4 Flash Latest cost per 1M tokens?
According to current pricing data, DeepSeek V4 Flash Latest costs $0.03 per 1M input tokens and $0.07 per 1M output tokens. Processing 1M tokens each way costs $0.10.
What does a typical API request to DeepSeek V4 Flash Latest cost?
A typical request with 2,000 input tokens and 500 output tokens costs <$0.0001. At 1,000 requests per day that is $0.10 daily, or about $2.85 per month.
What is DeepSeek V4 Flash Latest's context window?
DeepSeek V4 Flash Latest supports a 1.3M-token context window (1,310,720 tokens).
Does DeepSeek V4 Flash Latest support prompt caching?
Yes. Cached input tokens cost $0.00 per 1M — a 90% discount versus the standard input rate, which matters for agents and chat apps that resend the same system prompt.
What is a cheaper alternative to DeepSeek V4 Flash Latest?
Granite 4.0 Micro from Ibm-granite is currently the cheapest comparable option at $0.02 per 1M input tokens versus $0.03 for DeepSeek V4 Flash Latest — roughly 2x cheaper on input.
Compare all current prices on the live model pricing dashboard, see DeepSeek V4 Flash Latest vs Granite 4.0 Micro pricing, or run DeepSeek V4 Flash Latest head-to-head against other models in the side-by-side comparison playground.
Pricing data via the OpenRouter models API.