Compare models
Pick two to four models. No markup on model usage: you pay the provider's list price.
| Attribute | Eagle |   DeepSeek V4 Pro |
|---|---|---|
| Provider | Safeguard | DeepSeek |
| Model id | safeguard/eagle | deepseek/deepseek-v4-pro |
| Status | Available via Safeguard | Available via Safeguard |
| Input / 1M tokens | $0.00001 | $1.32 |
| Output / 1M tokens | $0.00001 | $3.96 |
| Price notes | Peak-hour list price (cache miss). Off-peak is half: $0.66 in / $1.98 out. Cache-hit input $0.044 peak. DeepSeek says it is phasing V4 Pro out but continues to serve it. | |
| Context | 1M | 1M |
| Parameters | 70B | Not published |
| Max output | Not published | 384,000 tokens |
| Modality | Text | Text |
| Weights | Safeguard | Open |
| Zero data retention | Not stated | Not stated |
| Prompts go to | Safeguard, on its own infrastructure | DeepSeek (People's Republic of China) |
| Retention | Customer data is never used to train shared models. | Privacy policy: personal data stored in the PRC and kept as long as necessary to provide the service, may be used to train models, with a right to opt out. No API-specific retention period or ZDR offering published |
| Region | The region your Safeguard workspace runs in | China (PRC) |
| Price checked | 2026-10-09 | 2026-10-08 |
Self-healing security runs on Safeguard.
Your first fix PR is minutes away.
No sales call required, even your agent can complete the purchase over MCP.