- input
- $0.111
- cached
- $0.097
- output
- $4.44
- Context
- 1Mtokens
- Released
- 3mo ago
- Size
- 1.7Tparameters
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 |
|---|---|---|---|---|---|---|---|---|
| relace/fp4 | 1M | $0.0999 | $8.00 | $0.0999 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| wafer/us | 1M | $0.111 | $4.44 | $0.097 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| wafer/mxfp4 | 1M | $0.285 | $4.30 | $0.284 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| deepseek | 1M | $0.66 | $1.98 | $0.022 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| streamlake | 1M | $0.66 | $1.98 | $0.022 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| novita/fp8 | 1M | $0.99 | $2.97 | $0.033 | — | 99.86% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| gmicloud/fp8 | 1M | $1.056 | $3.168 | $0.0352 | — | 99.66% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| alibaba | 1M | $1.122 | $3.366 | $0.1122 | — | 99.93% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| deepinfra/fp8 | 1M | $1.30 | $2.60 | $0.10 | — | 99.37% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| coreweave/fp8 | 1M | $1.31 | $3.96 | $0.044 | — | 99.72% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| alibaba/us-east-1 | 1M | $1.32 | $3.96 | $0.132 | — | 100.00% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| atlas-cloud/fp8 | 1M | $1.32 | $3.96 | $0.132 | — | 99.79% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| baidu/fp8 | 1M | $1.32 | $3.96 | $0.042 | — | 99.72% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| baseten/fp4 | 1M | $1.32 | $3.96 | $0.132 | — | 98.51% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-11 | |
| cloudflare | 1M | $1.32 | $3.96 | $0.044 | — | 93.86% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| digitalocean | 1M | $1.32 | $3.96 | $0.044 | — | 99.79% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| nebius/fp8 | 1M | $1.32 | $3.96 | $0.04 | — | 99.79% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| parasail/fp8 | 1M | $1.32 | $3.96 | $0.044 | — | 99.85% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| siliconflow/fp8 | 1M | $1.32 | $3.96 | $0.044 | — | 99.85% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| together | 1M | $1.32 | $3.96 | $0.13 | — | 99.93% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| sail-research/us | 1M | $1.35 | $2.40 | $0.195 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| sail-research/fp4 | 1M | $1.35 | $2.40 | $0.195 | — | 100.00% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| venice | 1M | $1.65 | $4.95 | $0.165 | — | 98.65% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 | |
| parasail/fast | 1M | $1.98 | $5.94 | $0.066 | — | 99.86% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-11-12 |
Provider data:OpenRouter