DeepSeek V4 Pro Variant 1 pricing
Source: litellm · updated 2026-11-05
Short answer: DeepSeek V4 Pro Variant 1 costs $2.40 per million input tokens and $4.80 per million output tokens. That is a 3:1 blended rate of $3.00 per million tokens, ranking it #700 of 813 tracked models by input price.
Input / 1M
$2.40
Output / 1M
$4.80
Output ÷ input
2.00×
Context window
1,000,000
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $2.40 |
| Output, per 1M tokens | $4.80 |
| Output ÷ input multiple | 2.00× |
| 3:1 blended, per 1M tokens | $3.00 |
| Context window | 1,000,000 tokens |
| Vendor | empiriolabs |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $2.40 | $1.20 | $3.60 |
| 10M in / 2.5M out | $24.00 | $12.00 | $36.00 |
| 100M in / 25M out | $240 | $120 | $360 |
Other empiriolabs models
| Model | Input | Output |
|---|---|---|
| Qwen 3.7 Flash Variant 1 | $0.028 | $0.110 |
| Qwen 3.5 Flash Variant 1 | $0.029 | $0.287 |
| Qwen 3.7 Flash | $0.030 | $0.130 |
| GLM 4.6 V Flashx | $0.040 | $0.400 |
| Nova Micro 1.0 | $0.040 | $0.160 |
Cheaper alternatives
Next cheaper option: Gemini 2.5 Flash Preview Tts at $0.500 per 1M input tokens. Next step up: Qwen 3.7 Max at $2.07 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.