DeepSeek API pricing
10 DeepSeek models, from price book 2026-10-22.
Billing rules Veqen applies
- Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
Also recognized as: deepseek-ai (framework, gateway and OpenTelemetry names).
Reconcile your bill
DeepSeek doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.
Prices come from DeepSeek's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.
Text 10 models
| Model | Input | Output | Cached input | Batch input | Context | Status |
|---|---|---|---|---|---|---|
| deepseek-coder | $0.14 | $0.28 | $0.014 | — | 128K | |
| deepseek-v3 | $0.27 | $1.10 | $0.07 | — | 65.5K | |
| deepseek-v3.2 | $0.28 | $0.40 | $0.028 | — | 163.8K | |
| deepseek-flash | $0.30 | $1.20 | $0.006 | — | 1M | |
| deepseek-v4-flash | $0.30 | $1.20 | $0.006 | — | 1M | |
| deepseek-v4-flash-vision-exp | $0.30 | $1.20 | $0.006 | — | 1M | |
| deepseek-r1 | $0.55 | $2.19 | $0.14 | — | 65.5K | |
| deepseek-v4-pro | $1.32 | $3.96 | $0.044 | — | 1M | |
| deepseek-chat | $0.28 | $0.42 | $0.028 | — | 131.1K | Retired 2026-07-24 |
| deepseek-reasoner | $0.28 | $0.42 | $0.028 | — | 131.1K | Retired 2026-07-24 |