DeepSeek V3 0324 API Pricing
DeepSeek · released 2025-03-25
Pricing
0.084¢ / 1K
0.118¢ / 1K
0.093¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0775¢ |
| RAG query | 4,000 in / 500 out | 0.397¢ |
| Long document summary | 50,000 in / 1,000 out | $0.0434 |
| Code review of a 2k-line file | 30,000 in / 2,000 out | $0.0277 |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $23.25 |
Cost = (input tokens ÷ 1,000,000 × $0.845) + (output tokens ÷ 1,000,000 × $1.175).
Benchmarks
#262 of 533
#141 of 197
#141 of 249
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Llama 3.1 Instruct 8B | 6.9 | $0.028 |
| Gemma 4 E4B (Reasoning) | 8.9 | $0.04 |
| Granite 4.2 3B | 9.1 | $0.052 |
| NVIDIA Nemotron Nano 9B V2 (Reasoning) | 7.4 | $0.07 |
| Sarvam 105B (high) | 8.8 | $0.074 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Qwen3 VL 235B A22B Instruct | 9.9 | $0.70 |
| Qwen3 30B A3B 2507 (Reasoning) | 9.8 | $0.75 |
| o1-mini | 9.8 | — |
| DeepSeek V3 0324 | 9.7 | $0.927 |
| Ling 2.6 Flash | 9.7 | — |
| GPT-4.5 (Preview) | 9.6 | — |
| Qwen3 Coder 30B A3B Instruct | 9.6 | $0.90 |
More from DeepSeek
| Model | Intelligence | Blended $/1M |
|---|---|---|
| DeepSeek V4.1 Flash (Reasoning, Max Effort) | 39.5 | $0.525 |
| DeepSeek V4 Pro 0813 (Reasoning, Max Effort) | 36.0 | $1.98 |
| DeepSeek V4 Flash Vision (Reasoning, Max Effort) | 34.8 | $0.66 |
| DeepSeek V4 Flash 0731 (Reasoning, Max Effort) | 34.3 | $0.66 |
| DeepSeek V4 Pro 0424 (Reasoning, Max Effort) | 30.4 | $0.544 |
| DeepSeek V4 Flash 0420 (Reasoning, High Effort) | 26.0 | $0.168 |
| DeepSeek V3.2 (Reasoning) | 21.5 | $0.315 |
| DeepSeek V3.2 Exp (Reasoning) | 16.6 | $0.315 |
Count tokens & estimate cost for DeepSeek V3 0324 See DeepSeek V3 0324 on the leaderboard
Source: Artificial Analysis · last synced 2026-09-22
FAQ
Who develops DeepSeek V3 0324?
DeepSeek V3 0324 is developed by DeepSeek, released 2025-03-25.
How much does DeepSeek V3 0324 cost per million tokens?
DeepSeek V3 0324 costs $0.845 per 1M input tokens and $1.175 per 1M output tokens ($0.927 blended), per Artificial Analysis's official pricing data.
How does DeepSeek V3 0324 rank on benchmarks?
DeepSeek V3 0324 scores 9.7 on the Artificial Analysis Intelligence Index, ranking #262 of 533 models we track.
Is there a cheaper model with similar intelligence to DeepSeek V3 0324?
Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.927/1M for DeepSeek V3 0324.
Where does this data come from?
Pricing and benchmark data for DeepSeek V3 0324 comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.