DeepSeek-V3-0324
March 2025 refresh of DeepSeek-V3. Small quality bump on coding and reasoning over the original V3 release.
DeepSeek-V3-0324 is a frontier AI model from DeepSeek. It costs $0.270 per million input tokens and $1.100 per million output tokens (blended $0.519/M), with a 128,000-token context window.
+24.4%over 91 days · hover to read
- Open weights
- Slightly stronger code than V3
- 128K context
- MoE inference economics
- Self-hosted production chat
- Code generation
- Migration from earlier V3
Benchmarks
More from DeepSeek
See all 11 →Price history
6 recorded changes| Date | Rate | Was | Now | Change |
|---|---|---|---|---|
| 8 Sept 2026 | Input | $0.270 | $0.290 | +7.4% |
| 8 Sept 2026 | Output | $1.120 | $1.140 | +1.8% |
| 16 Jul 2026 | Input | $0.240 | $0.270 | +13% |
| 16 Jul 2026 | Output | $0.900 | $1.120 | +24% |
| 2 Jul 2026 | Input | $0.200 | $0.240 | +20% |
| 2 Jul 2026 | Output | $0.770 | $0.900 | +17% |
Rates per million tokens, as published by the provider or its router listing. Tracking runs since 3 May; anything earlier is not on record. See every tracked price change.
Frequently asked questions
How much does DeepSeek-V3-0324 cost?
DeepSeek-V3-0324 costs $0.270 per million input tokens and $1.100 per million output tokens, for a blended reference rate of $0.519 per million tokens.
What is DeepSeek-V3-0324's context window?
DeepSeek-V3-0324 supports up to 128,000 tokens of context in a single request.
What is DeepSeek-V3-0324 best for?
DeepSeek-V3-0324 is well suited to Open weights, Slightly stronger code than V3 and 128K context.
Who makes DeepSeek-V3-0324?
DeepSeek-V3-0324 is developed and served by DeepSeek. It was released in Mar 2025.