Sail Research
Explore Sail Research models on TrustedRouter with current routes, token pricing, policy sources, privacy posture, regional availability, and API support.
Sail Researchsail-research
No provider claim
| Provider | Sail Research |
|---|---|
| Routing status | Active |
| Provider website | https://www.sailresearch.com/ |
| Models | 6 public models |
| Prepaid routes | 6 |
| BYOK routes | 0 |
| Zero data retention | not claimed |
| Confidential compute | not claimed |
| Provider E2EE | not claimed |
| Policy note | No contractual zero-retention, confidential-compute, or E2EE claim is tracked for TrustedRouter's Sail Research account. This route is Standard. Policy source |
Measured performance
35 samplesContinuously sampled across Sail Research's routed models: p50 TTFT, effective throughput, and success rate. Effective throughput uses provider-reported output tokens over complete request time. Unsupported route and probe-configuration rows are separated from provider downtime. No prompt or output content stored.
| p50 TTFT | 9255 ms |
|---|---|
| Effective throughput | 54 tok/s n=5 |
| Uptime | 100.00% |
| Model | p50 TTFT | Effective throughput | Uptime | Config excluded | Availability samples |
|---|---|---|---|---|---|
| deepseek/deepseek-v4-flash-0731 | 3251 ms | 54 tok/s n=1 | 100.00% | — | 7 |
| z-ai/glm-5.2 | 5189 ms | 79 tok/s n=2 | 100.00% | — | 8 |
| google/gemma-4-31b-it-nvfp4 | 9255 ms | — | 100.00% | — | 6 |
| google/gemma-4-31b-it | 9763 ms | 18 tok/s n=1 | 100.00% | — | 5 |
| openai/gpt-oss-120b | 10664 ms | 37 tok/s n=1 | 100.00% | — | 3 |
| moonshotai/kimi-k2.6 | 10918 ms | — | 100.00% | — | 6 |
Sail Research performance history · Full provider & model leaderboard.
Models served by Sail Research.
Each row links to pricing, provider, benchmark, and API pages for the model.
| Model | AI IQ | Context | Endpoints | Prompt | Completion | Routes |
|---|---|---|---|---|---|---|
deepseek/deepseek-v4-flash-0731DeepSeek: DeepSeek V4 Flash 0731 |
— | 1,310,720 | 1 | $0.09495/1M | $0.1899/1M | prepaid |
google/gemma-4-31b-itGoogle: Gemma 4 31B |
IQ 101#75 | 262,144 | 1 | $0.422/1M | $0.633/1M | prepaid |
google/gemma-4-31b-it-nvfp4nvidia/Gemma-4-31B-IT-NVFP4 |
— | 0 | 1 | $0.1477/1M | $0.422/1M | prepaid |
moonshotai/kimi-k2.6MoonshotAI: Kimi K2.6 |
IQ 119#24 | 262,144 | 1 | $1.055/1M | $4.22/1M | prepaid |
openai/gpt-oss-120bOpenAI: gpt-oss-120b |
IQ 105#63 | 131,072 | 1 | $0.0633/1M | $0.422/1M | prepaid |
z-ai/glm-5.2Z.ai: GLM 5.2 |
IQ 120#20 | 1,048,576 | 1 | $0.844/1M | $3.165/1M | prepaid |
Questions
Does Sail Research have zero data retention?
TrustedRouter does not currently mark Sail Research as provider-level zero data retention. Use trustedrouter/zdr or provider.min_privacy=zdr to select a different eligible route, and review the linked policy source for changes.
Is Sail Research end-to-end encrypted?
TrustedRouter does not currently mark Sail Research as end-to-end encrypted at the provider boundary. The TrustedRouter gateway is still attested, but the selected provider normally receives the request in order to run the model. Use trustedrouter/e2e for the stronger route requirement.
Which Sail Research models are available through TrustedRouter?
This page currently lists 6 public Sail Research models, with live pricing, route count, context length, measured performance when available, and links to each model's provider and benchmark pages.