- input
- $0.435
- cached
- $0.0036
- output
- $0.87
- Context
- 1.1Mtokens
- Released
- 1mo ago
- Size
- 528Bparameters
Cost/1M tokens
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| gmicloud/bf16 | 1.1M | $0.3263 | $0.6525 | $0.003 | — | 97.48% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| deepinfra/fp8 | 1M | $0.387 | $0.783 | $0.00324 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| xiaomi/fp8 | 1M | $0.435 | $0.87 | $0.0036 | — | 99.86% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| streamlake | 1M | $0.522 | $1.044 | $0.00432 | — | 77.73% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-11 | |
| primalabs/fp8 | 1M | $4.00 | $8.00 | $0.036 | — | 95.66% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
Provider data:OpenRouter