Sail Research: Models and Prices
Throughput-optimized inference and long-running sandboxes for agent workloads.
Sail Research served 1.71T tokens of other labs' open-weight models over Oct 3 to Oct 9, 2026 through a large public LLM router, #10 among providers.
Open-weight models
| Model | Family | Share of model | Tokens, 7d | Input $/M | Output $/M | Tokens/s | Uptime 3d | Context |
|---|---|---|---|---|---|---|---|---|
| DeepSeek V4 Flash 0731 | DeepSeek | 13.8% | 703B | $0.10 | $0.30 | 19 | 96.7% | 1.05M |
| DeepSeek V4.1 Flash | DeepSeek | 1.8% | 675B | $0.08 | $0.40 | 50 | 99.2% | 1.05M |
| GLM 5.3 | GLM | 3.5% | 117B | $0.20 | $3.40 | 69 | 100.0% | 1.05M |
| GLM 5.3 Flash | GLM | 0.8% | 91B | $0.045 | $0.60 | 32 | 99.9% | 1.05M |
| DeepSeek V4 Pro 0813 | DeepSeek | 6.7% | 71B | $0.40 | $3.00 | 72 | 100.0% | 1.05M |
| Kimi K3 | Kimi | 2.7% | 52B | $0.84 | $13.50 | 39 | 98.9% | 1.05M |
List prices per million tokens as of October 9, 2026. Share: of all tokens served on that model; a dash where the volume is not reported.
Company
- Website
- sailresearch.com
- Headquarters
- United States
- Latest financing
- $80M across seed and Series A at a $450M valuation (June 2026).
- Status page
- status.sailresearch.com
Sources: SiliconANGLE.
Finance your GPUs
Serving tokens on your own GPUs? Tell us the cluster, the models you serve and the contracts behind them, and we will share it with partner funders that fit.
Prefer email? hello@amcompute.com