- Good as a general-purpose model for text generation and everyday reasoning.
- Good when you want package quota first, with pay-as-you-go enabled by key configuration.
DeepSeek active
DeepSeek-v4-flash API Pricing and Package Multipliers
DeepSeek-v4-flash
Model
deepseek-v4-flash DeepSeek-v4-flash API Pricing
Official base: Input 0.05 / Output 0.16 / Cache read 0.007
| Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|
| DeepSeek | Input $0.045 Output $0.144 Cache read $0.0063 | USD / 1M | 6.048x | 0.9x |
Cache hits are billed at the cache read price. Cache writes use the cache write price, and the Console usage detail shows the final cost breakdown.
DeepSeek-v4-flash available packages and multipliers
| Package | Channel | SU8 price | Billing unit | Quota multiplier | Effective multiplier |
|---|---|---|---|---|---|
| Lite | DeepSeek | Input $0.0723 Output $0.2312 Cache read $0.0101 | USD / 1M | 60x | 1.445x |
| Pro | DeepSeek | Input $0.0607 Output $0.1941 Cache read $0.0085 | USD / 1M | 60x | 1.2134x |
| Plus | DeepSeek | Input $0.065 Output $0.208 Cache read $0.0091 | USD / 1M | 60x | 1.3x |
| Max | DeepSeek | Input $0.052 Output $0.1664 Cache read $0.0073 | USD / 1M | 60x | 1.0402x |
| Super Ultra | DeepSeek | Input $0.0424 Output $0.1357 Cache read $0.0059 | USD / 1M | 60x | 0.8481x |
| Ultra | DeepSeek | Input $0.0433 Output $0.1387 Cache read $0.0061 | USD / 1M | 60x | 0.8668x |
| SU500 | DeepSeek | Input $0.04 Output $0.128 Cache read $0.0056 | USD / 1M | 60x | 0.8x |
| SU750 | DeepSeek | Input $0.0395 Output $0.1263 Cache read $0.0055 | USD / 1M | 60x | 0.7895x |
| SU1000 | DeepSeek | Input $0.04 Output $0.128 Cache read $0.0056 | USD / 1M | 60x | 0.8x |
DeepSeek-v4-flash OpenAI-compatible API access
After creating a key in the console, call this model with the unified model name deepseek-v4-flash. When package and pay-as-you-go balance are both available, package quota is used first.
model: "deepseek-v4-flash"
- Not ideal for legacy integrations that only accept OpenAI-compatible APIs.
- Not ideal when you need dedicated SLA terms, private capacity, or a fixed-cost enterprise commitment.
This model is available through the public catalog and unified gateway pricing configuration.
Open this model in the console
The public model page is for discovery and comparison. Actual API access, key creation, and model scopes are managed after sign-in.