All models
DeepSeek
deepseek/deepseek-v4-pro
See the API documentation for supported features
- Input per 1M tokens
- $1.75
- Output per 1M tokens
- $3.50
What it costs and how fast it runs
You pay only for the tokens you use. Speed figures come from our own status checks.
Token pricing
| USD per million tokens | |
|---|---|
| Input | $1.75 |
| Cached input | $0.44 |
| Output | $3.50 |
No base fee. Caching applies only where listed. Check the model's processing region before sending data.
Speed on Lyceum
| Last 7 days | |
|---|---|
| Time to first token | 260 ms |
| Output speed | 73 tokens/s |
Median over the last 7 days from our status checks: short requests. Measured 8 October 2026, 16:42 UTC. Reasoning tokens count towards both figures. Live status and availability
The model in detail
Checked against the sources below. Anything they don't state is left out.
Availability
- API model ID
deepseek/deepseek-v4-pro- Provider
- DeepSeek
- Processing region
- EU-hosted
Sources
- Capabilities and request fields: Lyceum API documentation, checked 9 September 2026.