DeepSeek V4.1 Flash 1017 Fast pricing
Source: litellm · updated 2026-11-17
Short answer: DeepSeek V4.1 Flash 1017 Fast costs $0.600 per million input tokens and $2.40 per million output tokens. That is a 3:1 blended rate of $1.05 per million tokens, ranking it #476 of 823 tracked models by input price.
Input / 1M
$0.600
Output / 1M
$2.40
Output ÷ input
4.00×
Context window
1,048,576
Price breakdown
| Metric | USD |
|---|---|
| Input, per 1M tokens | $0.600 |
| Output, per 1M tokens | $2.40 |
| Output ÷ input multiple | 4.00× |
| 3:1 blended, per 1M tokens | $1.05 |
| Context window | 1,048,576 tokens |
| Vendor | baseten |
What a typical workload costs
| Monthly volume | Input cost | Output cost | Total |
|---|---|---|---|
| 1M in / 250K out | $0.600 | $0.600 | $1.20 |
| 10M in / 2.5M out | $6.00 | $6.00 | $12.00 |
| 100M in / 25M out | $60.00 | $60.00 | $120 |
Other baseten models
| Model | Input | Output |
|---|---|---|
| Nvidia Nemotron 3.5 Super VL 120 B A12 B | $0.200 | $0.500 |
| Beam 1.0 | $0.400 | $1.20 |
| Nvidia Nemotron 3 Ultra 550 B A55 B | $0.600 | $2.40 |
| GLM 5.2 Fast | $2.10 | $6.60 |
Cheaper alternatives
Next cheaper option: Qwen 3.6 27 B at $0.320 per 1M input tokens. Next step up: DeepSeek V4 Pro at $0.900 per 1M input tokens.
Spotted a price that is out of date? Submit a correction.