Verified 2026-10-07 · sourced from DeepSeek
100K DeepSeek V4.1 Flash Tokens — Cost Breakdown
Use this guide to benchmark budgets for 100,000 tokens. Standard pricing is $0.30 per million input tokens and $1.20 per million output tokens. Cached input, when available, reduces costs significantly for repeated contexts.
Reference rates: Peak rates · select off-peak when applicable
USD per million text tokens. Verified 2026-10-07 · Official source
| Mode / prompt size | Input | Cache read | Cache write | Output |
|---|---|---|---|---|
| Peak | $0.3 | $0.006 | Not estimated | $1.2 |
| Off-peak | $0.15 | $0.003 | Not estimated | $0.6 |
1,000,000 context tokens · max output 384,000. Local token counts are estimates; use the provider’s usage counts for an invoice estimate.
Direct DeepSeek API. Peak: Monday–Friday 01:00–04:00 and 06:00–10:00 UTC, excluding Chinese public holidays. All other times are off-peak. Choose the applicable mode explicitly; no holiday calendar is inferred.
Cache hit and cache miss are separate input rates. Batch and cache-write prices have not been verified and are not estimated. Text token counts are approximate; provider-reported usage is authoritative.
Scenario breakdown
Cost estimates for different input/output distributions using 100K total tokens.
| Scenario | Tokens in | Tokens out | Standard cost | Cached cost |
|---|---|---|---|---|
Balanced conversation 50% input · 50% output | 50,000 | 50,000 | $0.0750 | $0.0603 |
Input-heavy workflow 80% input · 20% output | 80,000 | 20,000 | $0.0480 | $0.0245 |
Generation heavy 30% input · 70% output | 30,000 | 70,000 | $0.0930 | $0.0842 |
Cached system prompt 90% cached input · 10% fresh output | 90,000 | 10,000 | $0.0390 | $0.0125 |
Workload multipliers
Convert 100K tokens into daily and monthly run-rate budgets.
| Profile | Runs/day | Tokens/day | Daily cost | Monthly cost | Cached daily | Cached monthly |
|---|---|---|---|---|---|---|
| Single workload | 1 | 100,000 | $0.0750 | $2.25 | $0.0125 | $0.376 |
| Daily batch (10 runs) | 10 | 1,000,000 | $0.750 | $22.50 | $0.125 | $3.76 |
| Team workload (100 runs) | 100 | 10,000,000 | $7.50 | $225.00 | $1.25 | $37.62 |
Frequently asked questions
What is the standard cost of 100K DeepSeek V4.1 Flash tokens?
100K tokens in a 50/50 conversation mix cost roughly $0.0750 at the published DeepSeek rates.
What happens if cached input is enabled?
With cached contexts, the same 100K tokens drop to $0.0603 because input costs fall to $0.006 per million tokens.
How many requests does 100K tokens cover?
If your prompts average around 3,000 tokens per call, 100K total tokens cover about 33 requests.
How fresh is the pricing information?
Prices are taken from https://api-docs.deepseek.com/quick_start/pricing/ and were last verified on 2026-10-07. models.json keeps this guide in sync with upstream changes.