DeepSeek-V3 0324: Benchmarks, Pricing & Context Window
DeepSeek-V3 0324 is a language model from DeepSeek, released in March 2025, with a 164K-token context window, and pricing from $0.240/M input, $0.135/M cached input, $0.900/M output.
A powerful Mixture-of-Experts (MoE) language model with 671B total parameters (37B activated per token). Features Multi-head Latent Attention (MLA), auxiliary-loss-free load balancing, and multi-token prediction training. Pre-trained on
DeepSeek-V3 0324 benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for DeepSeek-V3 0324 across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How DeepSeek-V3 0324 holds up as conversations get longer.
Quality Tracker
DeepSeek-V3 0324 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Thu Oct 08 2026DeepSeek-V3 0324 pricing
Providers
DeepSeek-V3 0324 starts at $0.240 per million input tokens and $0.900 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.135 per million cached input tokens. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.240 | $0.135 | $0.900 | 163.8K/163.8K | — | — | / |
 Novita | $0.280 | — | $1.14 | 163.8K/163.8K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
DeepSeek-V3 0324 model size
DeepSeek-V3 0324 has 671 billion parameters and was trained on 14.8 trillion tokens. See how it compares to other models in the same parameter range.
DeepSeek-V3 0324 context window
Input and output token limits for DeepSeek-V3 0324, plus how it ranks on long-context understanding.
Try now
huggleMake it with
DeepSeek-V3 0324.
DeepSeek-V3 0324 latency
DeepSeek-V3 0324 time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
DeepSeek-V3 0324 examples
Recent arena outputs from DeepSeek-V3 0324, picked from the highest-ranked matchups.
DeepSeek-V3 0324 license
DeepSeek-V3 0324 is released under the MIT + Model License (Commercial use allowed) license, which restricts commercial use, has 671.0B parameters.
- License
- MIT + Model License (Commercial use allowed)
- Non-commercial
- Parameters
- 671.0B
DeepSeek-V3 0324 resources
Official sources for DeepSeek-V3 0324: provider documentation, official playground, paper or system card, source repository, model weights.
DeepSeek-V3 0324 vs other models
The most-compared alternatives to DeepSeek-V3 0324 are Phi 4 Reasoning Plus, DeepSeek R1 Zero, Nova 2 Pro. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like DeepSeek-V3 0324
Models ranked just above and below DeepSeek-V3 0324 by LLM Stats score.
FAQ
Common questions about DeepSeek-V3 0324.