Providers /Sail Research
Inference provider

Sail Research

Models
3
Regions
00

Our take

Editorial by LLMap · updated Jul 28, 2026

This niche provider carries just three tracked offers, two of which are duplicate listings of the same model. It is only worth considering if you specifically need z-ai-glm-5-2 or moonshotai-kimi-k2-6 and cannot find them elsewhere.

Use this when you specifically need z-ai-glm-5-2 or moonshotai-kimi-k2-6 and cannot source them at lower cost from another host. Pick it if measured throughput matters for z-ai-glm-5-2 — it shows 19 TPS. Skip it if you need a broad model catalogue, verified compliance credentials, or consistent throughput data across all offers.

Strengths
  • One model with measured throughput — z-ai-glm-5-2 shows 19 TPS.
  • Access to moonshotai-kimi-k2-6 at two throughput tiers: 19 TPS or unmeasured.
Trade-offs
  • Extremely limited catalogue depth: only 3 tracked offers, with 2 being duplicates of the same model.
  • No verified compliance or data governance credentials: SOC 2, zero retention, training-on-prompts policy, headquarters, and EU endpoint are all unverified in our data.
  • Throughput data is sparse and inconsistent: only 1 of 3 offers has throughput measured, and the duplicate moonshotai-kimi-k2-6 entries disagree — 19 TPS versus unmeasured.
01

Privacy & data handling

Yes
No
No answer on record

The colour says whether the answer favours you, not whether it is a yes — not training on your prompts earns a green cross, no zero-retention option earns a red one.

Trains on your prompts
No
Logs prompts
No
Offered
No answer on record

Prompt retention: none.

02

Models & pricing

Something wrong on this page? Tell us