DeepSeek API Pricing 2026
DeepSeek provides models for chat, reasoning, and coding. Compare V4.1 Flash, V4 Pro, and earlier models, and check the provider's current API availability and rates.
Pricing data updated 2026-11-02. Provider rate card: api-docs.deepseek.com/quick_start/pricing.
Get DeepSeek API access →DeepSeek Model Pricing
Prices in USD per 1M tokens
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
DeepSeek V4.1 Flash 1017 Auto-added 2026-11; set isCurrent: true after review | $0.3 | $1.2 | 1,048,576 |
DeepSeek V4.1 Flash Auto-added 2026-11; set isCurrent: true after review | $0.05 | $0.5 | 1,048,576 |
DeepSeek V4 Pro 0813 Auto-added 2026-08; set isCurrent: true after review | $0.12 | $4 | 1,048,576 |
DeepSeek V4 Flash 0731 Auto-added 2026-08; set isCurrent: true after review | $0.12 | $0.24 | 1,048,576 |
DeepSeek V4 Flash Default chat model (deepseek-chat alias); cache hit $0.0028/1M input | $0.09 | $0.18 | 1,048,576 |
DeepSeek V4 Pro DeepSeek flagship; 1M context; promo 75% off ($0.435/$0.87) until May 31 2026 | $1.6 | $3.2 | 1,048,576 |
DeepSeek V3.2 DeepSeek V3.2; improved over V3 base | $0.26 | $0.38 | 163,840 |
DeepSeek V3.1 Terminus Auto-added 2026-08; set isCurrent: true after review | $0.27 | $1 | 163,840 |
DeepSeek V3.1 Auto-added 2026-06 | $0.25 | $0.95 | 163,840 |
R1 0528 DeepSeek R1 May-2025 snapshot; improved reasoning | $0.5 | $2.15 | 163,840 |
DeepSeek V3 Legacy V3 pricing; API now routes chat workloads to V4 Flash | $0.26 | $1.03 | 163,840 |
DeepSeek V3 (Mar 2025) March 2025 snapshot; same pricing as V3, improved performance | $0.27 | $1.1 | 128,000 |
DeepSeek V3 0324 Auto-added 2026-08; set isCurrent: true after review | $0.29 | $1.14 | 163,840 |
DeepSeek R1 Reasoning model (deepseek-reasoner alias maps to V4 Flash thinking mode) | $0.7 | $2.5 | 64,000 |
R1 Distill Llama 70B Auto-added 2026-08; set isCurrent: true after review | $0.8 | $0.8 | 8,192 |
How to read these estimates
The monthly table assumes 70% input tokens and 30% output tokens. It is a consistent comparison baseline, not a prediction of your workload. Actual bills can also include cached-input discounts, batch pricing, tool calls, minimum charges, regional differences, retries, and taxes.
The linked source is the provider's pricing documentation. Catalog rates may include third-party prices. Verify the current rate card and model availability before committing to a budget.
Estimated Monthly Cost (70% input / 30% output split)
| Model | 1M tokens/mo | 10M tokens/mo | 100M tokens/mo | 1B tokens/mo |
|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | $0.570 | $5.70 | $57.00 | $570 |
| DeepSeek V4.1 Flash | $0.185 | $1.85 | $18.50 | $185 |
| DeepSeek V4 Pro 0813 | $1.28 | $12.84 | $128 | $1,284 |
| DeepSeek V4 Flash 0731 | $0.156 | $1.56 | $15.60 | $156 |
| DeepSeek V4 Flash | $0.117 | $1.17 | $11.70 | $117 |
| DeepSeek V4 Pro | $2.08 | $20.80 | $208 | $2,080 |
| DeepSeek V3.2 | $0.296 | $2.96 | $29.60 | $296 |
| DeepSeek V3.1 Terminus | $0.489 | $4.89 | $48.90 | $489 |
| DeepSeek V3.1 | $0.460 | $4.60 | $46.00 | $460 |
| R1 0528 | $0.995 | $9.95 | $99.50 | $995 |
| DeepSeek V3 | $0.491 | $4.91 | $49.10 | $491 |
| DeepSeek V3 (Mar 2025) | $0.519 | $5.19 | $51.90 | $519 |
| DeepSeek V3 0324 | $0.545 | $5.45 | $54.50 | $545 |
| DeepSeek R1 | $1.24 | $12.40 | $124 | $1,240 |
| R1 Distill Llama 70B | $0.800 | $8.00 | $80.00 | $800 |
Frequently Asked Questions
How much does DeepSeek LLM API cost?
DeepSeek offers 15 models ranging from $0.050/1M to $1.60/1M input tokens. DeepSeek provides models for chat, reasoning, and coding. Compare V4.1 Flash, V4 Pro, and earlier models, and check the provider's current API availability and rates.
Is DeepSeek cheaper than self-hosting?
For low-volume workloads (under 100M tokens/month), cloud APIs like DeepSeek are almost always cheaper than purchasing and maintaining GPU hardware. Use our calculator to find the exact break-even point for your usage.