DeepSeek V3DeprecatedPointer
DeepSeek V3 is a rolling pointer, not a fixed model. The provider moves this name to new models over time, so the price on this page is what it costs today.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.28 to $0.32 per 1M tokens across 2 providers, so the dearest route costs 14% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepSeekCheapest | $0.28 | $0.42 | 1 | |||||||||||||
Standarddeepseek-chat
| ||||||||||||||||
| OpenRouter | $0.32 | $0.89 | 1 | |||||||||||||
Standarddeepseek/deepseek-chat
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokensCost calculator
estimate your monthly spend on this modelModel IDs
copy the exact identifier for your platformFrequently asked questions
DeepSeek V3 pricing, context and availabilityIs DeepSeek V3 still available?
DeepSeek V3 was deprecated on 2026-07-24, but 2 serving providers still list it.
How much does DeepSeek V3 cost?
DeepSeek V3 costs $0.28 per 1M input tokens from DeepSeek, and $0.42 per 1M output tokens from DeepSeek. Across 2 serving providers, input prices range from $0.28 to $0.32 per 1M tokens.
What is the context window of DeepSeek V3?
DeepSeek V3 accepts up to 131K tokens of context and can return up to 8K output tokens.
Which providers serve DeepSeek V3?
DeepSeek V3 is available from 2 serving providers, each with its own pricing and model ID. DeepSeek is currently the cheapest.
What can DeepSeek V3 do?
DeepSeek V3 supports tool use, prompt caching and structured output.
Other DeepSeek models
compare pricing across the DeepSeek lineupEvery weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI