Deepseek V4.1 Flash API Pricing
Deepseek V4.1 Flash costs $0.3 per 1M input tokens and $1.20 per 1M output tokens on DeepSeek's API. Prices are provider list prices in USD, refreshed as sources update; see the Deepseek V4.1 Flash model profile for capability scores.
Price List
| Rate | Price (USD) | Notes |
|---|---|---|
| Input | $0.3 | per 1M tokens |
| Output | $1.20 | per 1M tokens |
| Blended input + output | $1.50 | 1M in + 1M out at list price |
| Context window | 1M tokens |
What a Workload Costs
Computed straight from the list prices above — token counts are illustrative workload sizes, not measurements of Deepseek V4.1 Flash.
| Workload | Cost | Tokens |
|---|---|---|
| Short chat turn | $0.00090 | 1K in / 500 out |
| Summarize a long document | $0.032 | 100K in / 2K out |
| Agentic coding session | $0.270 | 500K in / 100K out |
| 1M input + 1M output tokens | $1.50 | 1M in / 1M out |
Effective Cost
In AI IQ's scoring, Deepseek V4.1 Flash's list price is adjusted by a token-usage multiplier of 0.792, giving an effective cost of $1.19 per 1M input + output tokens. That places it #26 of 121 models on the effective-cost ranking (lower is cheaper). Some models spend far more tokens than others on the same task, so effective cost compares what a unit of work really costs. Method details are on the methodology page; see all models on the cost charts and the falling cost of intelligence over time.